THE WILLIAM DAVIDSON INSTITUTE AT THE UNIVERSITY OF MICHIGAN BUSINESS SCHOOL
|
|
- Owen Nichols
- 6 years ago
- Views:
Transcription
1 THE WILLIAM DAVIDSON INSTITUTE AT THE UNIVERSITY OF MICHIGAN BUSINESS SCHOOL Ex-ante Evaluaton of Condtonal Cash Transfer Programs: The Case of Bolsa Escola By: Franços Bourgugnon, Francsco H. G. Ferrera and Phllppe G. Lete Wllam Davdson Workng Paper Number 516 September 00
2 Frst Draft: September 00 Comments Welcome. Ex-ante Evaluaton of Condtonal Cash Transfer Programs: the Case of Bolsa Escola 1 Franços Bourgugnon, Francsco H. G. Ferrera and Phllppe G. Lete JEL Codes: I38, J13, J, J4 Key Words: Condtonal Transfers; Demand for Schoolng, Chld Labor Abstract: Cash transfers targeted to poor people, but condtonal on some behavor on ther part, such as school attendance or regular vsts to health care facltes, are beng adopted n a growng number of developng countres. Even where ex-post mpact evaluatons have been conducted, a number of polcy-relevant counterfactual questons have remaned unanswered. These are questons about the potental mpact of changes n program desgn, such as beneft levels or the choce of the means-test, on both the current welfare and the behavoral response of household members. Ths paper proposes a method to smulate the effects of those alternatve program desgns on welfare and behavor, based on mcroeconometrcally estmated models of household behavor. In an applcaton to Brazl s recently ntroduced federal Bolsa Escola program, we fnd a surprsngly strong effect of the condtonalty on school attendance, but a muted mpact of the transfers on the reducton of current poverty and nequalty levels. 1 We are grateful for comments receved from partcpants at the WB/UNICEF/ILO conference on Chld Labor (May 00) and at the Latn Amercan Meetngs of the Econometrc Socety n São Paulo (July 00). Bourgugnon s at Delta and The World Bank, Pars. Ferrera and Lete are at The World Bank and the Pontfíca Unversdade Católca do Ro de Janero (PUC-Ro). The vews expressed n ths paper are those of the authors, and do not necessarly represent the vews of the World Bank, ts Executve Drectors, or the countres they represent.
3 1. Introducton Durng the 1990s, a new brand of redstrbuton programs was adopted n many developng countres. Although local versons vared, programs such as Food for Educaton n Bangladesh, Bolsa Escola n Brazl, and Progresa n Mexco are all meanstested condtonal cash transfer programs. As the name ndcates, they share two defnng features, whch jontly set them apart from most pre-exstng programs, whether n developng or developed countres. The frst of these s the means-test, defned n terms of a maxmum household ncome level, above whch households are not elgble to receve the beneft. 3 The second s the behavoral condtonalty, whch operates through the requrement that applcant households, n addton to satsfyng the ncome targetng, have members regularly undertake some pre-specfed acton. The most common such requrement s for chldren between 6 and 14 years of age to reman enrolled and actually n attendance at school. In Mexco s Progresa, addtonal requrements appled to some households, such as oblgatory pre- and post-natal vsts for pregnant women or lactatng mothers. The mplementaton of these programs have generated consderable nterest, both n the countres where they took place and n the nternatonal academc and polcymakng communtes. Accordngly, a great deal of effort has been placed n evaluatng ther mpact. There are two types of approach for evaluatng the effects of these programs on the varous aspects of household welfare that they seek to affect. Ex-post approaches consst of comparng observed benefcares of the program wth non-benefcares, possbly after controllng for selecton nto the frst or the second group f truly random samples are not avalable. An mportant lterature has recently developed on these technques and many applcatons to socal programs have been made n varous countres. 4 3 For verfcaton and enforcement reasons, the means-test s often specfed n terms of a score based on responses to a questonnare and/or a home vst by a socal worker. In some countres, the score s calbrated to be approxmately equvalent to a pre-determned level of household ncome per capta. See Camargo and Ferrera (001) for a dscusson of the Brazlan case. 4 Ths lterature reles heavly on matchng technques, and draws extensvely on the early work by Rubn (1977) and Rubn and Rosenbaum (1985). For a survey of recent applcatons, see Heckman and Vytlacl (00). For a study of the effects of the Food for Educaton program n Bangladesh, see Ravallon and
4 Ex-ante methods consst of smulatng the effect of the program on the bass of some model of the household. These models can vary wdely n complexty and coverage. Arthmetc smulaton models smply apply offcal rules to determne whether or not a household qualfes for the program, and the amount of the transfer to be made, on the bass of data commonly avalable n typcal household surveys. More sophstcated models nclude some behavoral response by households. Ex-ante and ex-post evaluaton methods are complements, rather than substtutes. To begn wth, they have dfferent objectves. Ex-post methods are meant to dentfy the actual effects of a program on varous dmensons of household welfare, by relyng on the drect observaton of people engaged n the program, and comparng them wth those same dmensons n a carefully constructed comparson group, selected so as to provde a sutable proxy for the desred true counterfactual: how would partcpants have fared, had they not partcpated?. In some sense, these are the only true evaluatons of a program. Even when comparson groups are perfectly belevable proxes for the counterfactual, however, ex-post evaluatons leave some polcy-relevant questons unanswered. These questons typcally refer to how mpact mght change f some aspect of the program desgn such as the level of the means-test; the nature of the behavoral condtons mposed; or the level of the transfer benefts - changes. It s dffcult enough to obtan an actual control group to compare wth a sngle program desgn n realty. It s lkely to be mpossble to test many dfferent desgns n expermental condtons. Exante methods are valuable tools exactly because t s easer to experment on computers than on people. These methods are essentally prospectve snce they rely on a set of assumptons about what households are lkely to do when faced wth the program. They also permt drect counterfactual analyss of alternatve programs for whch no ex-post data can be avalable. Thus, they are ndspensable when desgnng a program or reformng exstng ones. Wodon (000). A number of mportant studes of Progresa were undertaken under the auspces of the Internatonal Food Polcy Research Insttute (IFPRI). See, n partcular, Parker and Skoufas (000) and Schultz (000).
5 Smulaton models of redstrbuton schemes based on mcro data sets are wdely used n developed countres, especally to analyze the effect of the numerous and often complex cash transfer nstruments found n those countres. Gven the progress of drect cash transfers n developng countres, buldng the same type of models n developng countres may become necessary. 5 However, the specfc behavoral condtonalty that characterzes these programs requres modfcatons, and a focus on dfferent aspects of household behavor. The present paper takes a step n that drecton by proposng a smple ex-ante evaluaton methodology for condtonal means-tested transfer programs. We apply the method to the new federal desgn of Bolsa Escola, n Brazl, and we are concerned wth both dmensons cted by the program admnstrators as ther objectves: () the reducton of current levels of poverty and nequalty; and () the provson of ncentves for the reducton of future poverty, through ncreased school enrollment among poor chldren today. The paper s organzed as follows. Secton descrbes the Bolsa Escola program, as t was launched at the federal level n Brazl n 001. Secton 3 presents the smple econometrc model used for smulatng the effects of the program. Gven the condtonalty of Bolsa Escola, ths model essentally deals wth the demand for schoolng and therefore draws on the recent lterature on chld labor. The estmaton of the model s dealt wth n Secton 4, whereas the smulaton of program effects and a comparson wth alternatve program desgns are dscussed n Secton 5. Secton 6 concludes.. Man features of the Bolsa Escola program The Brazlan natonal Bolsa Escola program, created by a law of Aprl 001 wthn the broader context of the socal development ntatve known as Projeto Alvorada, s the generalzaton at the federal level of earler programs, whch were poneered n the Federal Dstrct and n the cty of Campnas (SP) n 1995, and later 5 See, for nstance, Hardng (1996). On the need for and dffcultes wth buldng the same type of models n developng countres, see Atknson and Bourgugnon (1991).
6 extended to several other localtes. 6 The law of Aprl 001 made these varous programs unform n terms of coverage, transfer amounts and the assocated condtonalty. It also provded federal fundng. Yet, the montorng of the program tself s left under the responsblty of muncpal governments. The rules of the program are rather smple. Households wth monetary ncome per capta below 90 Reas (R$) 7 per month whch was equvalent to half a mnmum wage when the law was ntroduced - and wth chldren aged 6 to 15 qualfy for the Bolsa Escola program, provded that chldren attend school regularly. The mnmum rate of school attendance s set at 85 per cent and schools are supposed to report ths rate to muncpal governments for program benefcares. The monthly beneft s R$15 per chld attendng school, up to a maxmum of R$45 per household. Transfers are generally pad to the mother, upon presentaton of a magnetc card that greatly facltates the montorng of the whole program. The management of the program s essentally local. Yet, control wll be operated at two levels. At the federal level, the number of benefcares clamed by muncpal governments wll be checked for consstency aganst local aggregate ndcators of affluence. In case of dscrepancy, local governments wll have to adjust the number of benefcares on the bass of ncome per capta rankngs. At the local level, the responsblty for checkng the veracty of self-reported ncomes s left to muncpaltes. It s estmated that some ten mllon chldren (n sx mllon households) wll beneft from ths program. Ths represents approxmately 17 percent of the whole populaton, reached at a cost slghtly below 0. percent of GDP. The latter proporton s hgher n terms of household dsposable ncome: 0.45 percent when usng household ncome reported n the PNAD survey and 0.3 per cent when usng Natonal Accounts. Of course, ths fgure s consderably hgher when expressed n terms of targeted households. Even so, t amounts to no more than 5 percent of the ncome of the bottom two decles. 6 Early studes of these orgnal programs nclude Abramovay et. al. (1998); Rocha and Sabóa (1998) and Sant Ana and Moraes (1997). A comprehensve assessment of dfferent experences wth Bolsa Escola across Brazl can be found n World Bank (001). There s much less wrtten on the federal program, for the good reason that ts mplementaton n practce s only just begnnng. The descrpton gven n ths secton draws on the offcal Mnstéro da Educação webste, at 7 Approxmately US$ 30, at August 00 exchange rates.
7 3. A smple framework for modelng and smulatng Bolsa Escola The effects of such a transfer scheme on the Brazlan dstrbuton of ncome could be smulated by smply applyng the aforementoned rules to a representatve sample of households, as gven for nstance by the Pesqusa Naconal por Amostra de Domcílos (PNAD), felded annually by the Brazlan Central Statstcal Offce (IBGE). Ths would have been an example of what was referred to above as 'arthmetc' smulaton. Yet, for a program whch has a change n household behavor as one of ts explct objectves, ths would clearly be napproprate. After all, Bolsa Escola ams not only to reduce current poverty by targetng transfers to today s poor, but also to encourage school attendance by poor chldren who are not currently enrolled, and to dscourage evason by those who are. Any ex-ante evaluaton of such a polcy must therefore go beyond smply countng the addtonal ncome accrung to households under the assumpton of no change n schoolng behavor. Smulatng Bolsa Escola thus requres some structural modelng of the demand for schoolng. Ths secton presents and dscusses the model beng used n ths paper. There s a rather large lterature on the demand for schoolng n developng countres and the related ssue of chld labor. The man purpose of that lterature s to understand the reasons why parents would prefer to have ther kds workng wthn or outsde the household rather than gong to school. Varous motves have been dentfed and analyzed from a theoretcal pont of vew, 8 whereas numerous emprcal attempts have been made at testng the relevance of these motves, measurng ther relatve strength and evaluatng the lkely effects of polces. 9 The emprcal analyss s dffcult for varous nter-related reasons. Frst, the ratonale behnd the decson on chld labor or school enrollment s by tself ntrcate. In partcular, t s an nherently ntertemporal decson, and t wll dffer dependng on whether households behave as a untary model, or whether nternal barganng takes place. Second, t s dffcult to clam exogenety for most plausble explanatory varables, and yet no obvous nstrument s avalable for 8 See the well-known survey by Basu (1999) as well as the recent contrbuton by Baland and Robnson (001). 9 Early contrbutons to that lterature nclude Rosenzweg and Evenson (1977), as well as Gertler and Glewwe (1990). For more recent contrbutons and short surveys of the recent lterature see Freje and Lopez-Calva (000), Bhalotra (000). On polcy see Grootaert and Patrnos (1999).
8 correctng the resultng bases. Thrd, fully structural models that would permt a rgorous analyss of polces are complex and therefore hard to estmate whle mantanng a reasonable degree of robustness. In lght of these dffcultes, our ams are modest and our approach s operatonal: rather than proposng a new, more complete structural model of the demand for schoolng and ntra-household labor allocaton, we am smply to obtan reasonable orders of magntude for the lkely effects of transfer programs of ths knd. We thus make the choce to lmt the structural aspects of the modelng exercse to the mnmum necessary to capture the man effects of the program. In partcular, we make four crucal smplfyng assumptons. Frst, we entrely gnore the ssue of how the decson about a chld s tme allocaton s made wthn the household. We thus bypass the dscusson of untary versus collectve decson-makng models of household. Instead, we treat our model of occupatonal choce as a reducedform reflecton of the outcome of whchever decson-makng process took place wthn the household. 10 Second, we consder that the decson to send a chld to school s made after all occupatonal decsons by adults wthn the household have been made, and does not affect those decsons. Thrd, we do not dscuss here the ssue of varous sblngs n the same household and the smultanety of the correspondng decson. The model that s dscussed thus s supposed to apply to all chldren at schoolng age wthn a household. Fourth, we take the composton of the household as exogenous. Under these assumptons, let S be a qualtatve varable representng the occupatonal choce made for a chld n household. Ths varable wll take the value 0 f the chld does not attend school, the value 1 f she goes to school and works outsde the household and the value f she goes to school and does not work outsde the household. When S =0, t wll be assumed that the chld works full tme ether at home or on the market, earnngs beng observed only n the latter case. Smlarly, S = allows for the possblty that the chld may be employed n domestc actvtes at the same tme he/she goes to school. The occupatonal choce varable S wll be modeled usng the standard utlty-maxmzng nterpretaton of the multnomal Logt framework, so that: 10 For a dscusson of how ntra-household barganng affects the occupatonal choce of members, see Chappor (199). See also Bourgugnon and Chappor (1994) and Brownng et. al. (1994).
9 S = k ff S k (A, X, H ; Y - y k ) v k > S j (A, X, H ; Y - y j ) v j for j k (1) where S k ( ) s a latent functon reflectng the net utlty of choosng alternatve k (=0, 1 or ) for decders n the household. A s the age of the chld I; X s a vector of her characterstcs; H, s a vector of the characterstcs of the household she belongs to - sze, age of parents, educaton of parents, presence of other chldren at school age, dstance from school, etc.; Y - s the total ncome of household members other than the chld and y j s the total contrbuton of the chld towards the ncome of the household, dependng on her occupatonal choce j. Fnally, v j s a random normal varable that stands for the unobserved heterogenety of observed schoolng/partcpaton behavor. If we collapse all non-ncome explanatory varables nto a sngle vector Z and lnearze, (1) can be wrtten as: U (j) = S j (A, X, H ; Y - y j ) v j = Z.γ j (Y - y j )α j v j () Ths representaton of the occupatonal choce of chldren s very parsmonous. In partcular, by allowng the coeffcents γ j and α j to dffer wthout any constrants across the varous alternatves, we are allowng all possble tradeoffs between the schoolng of the chld and hs/her future ncome, and the current ncome of the household. Note also that the precedng model mplctly treats the chld's number of hours of work as a dscrete choce. Presumably that number s larger n alternatve 0 than n alternatve 1 because schoolng s takng some tme away. Ths may be reflected n the defnton of the chld ncome varable y j as follows. Denote the observed market earnngs of the chld as w. Assumng that these are determned n accordance wth the standard Becker- Mncer human captal model, wrte: Log w = X.δ m*ind(s j =1) u (3) where X s a set of ndvdual characterstcs ncludng age and schoolng acheved - and where u s a random term that stands for unobserved earnngs determnants. Assumptons on that term wll be dscussed below. The second term on the rght hand sde takes nto account the precedng remark on the number of hours of work. Chldren who attend school and are also reported to work on the market presumably have
10 less tme avalable and may thus earn less. Based on (3), the chld's contrbuton to the household ncome, y j, n the varous alternatve j s defned as follows: y 0 = Kw ; y 1 = M y 0 = MKw ; y = D y 0 = D Kw wth M = Exp(m) (4) where t s assumed that y j covers both market and domestc chld labor. Thus domestc ncome s proportonal to actual or potental market earnngs, w, n a proporton K for people who do not go to school. Gong to school whle keepng workng outsde the household means a reducton n the proporton 1-M of domestc and market ncome. Fnally, gong to school wthout workng on the market means a reducton n the proporton 1-D of total chld ncome, whch n that case s purely domestc. The proportons K and D are not observed. However, the proporton M s taken to be the same for domestc and market work and may be estmated on the bass of observed earnngs. Replacng (4) n () leads to : U (j) = S j (A, X, H ; Y - y j ) v j = Z.γ j Y - α j β j.w v j wth : β 0 = α 0 K ; β 1 = α 1 MK; β = α DK (5) We now have a complete smulaton model. If all coeffcents α, β, γ are known, as well as the actual or potental market earnngs, w and the resdual terms v j, then the chld s occupatonal type selected by household s: k* = Arg max[u (j)] (6) Equaton (5) represents the utlty of household under occupatonal choce j [U (j)] n the benchmark case. If the Bolsa Escola program enttled all chldren 11 gong to school to a transfer T, (5) would be replaced by: U (j) = Z.γ j (Y -I BE j ).α j β j.w v j wth BE 0 =0 and BE 1 = BE = T (7) Under the assumptons we have made, equaton (7) s our full reduced-form model of the occupatonal choce of chldren, and would allow for smulatons of the mpact of Bolsa Escola transfers on those choces. All that remans s to obtan estmates of β, γ, α, w and the v j 's. 11 It wll prove smpler to dscuss the estmaton problem under ths smplfyng assumpton. We rentroduce the means test, wthout any loss of generalty, at the smulaton stage.
11 Estmaton of the dscrete choce model Assumng that the v j are d across sample observatons wth a double exponental dstrbuton leads to the well-known mult-logt model. However, some precautons must be taken n ths case. It s well known that the probablty that household wll select occupatonal choce k s gven by: p k Exp( Z. γ k Y α k w. β k = Exp( Z. γ j Y α j w. β j ) j (8) Takng regme j = 0 as a reference, the precedng probablty may be wrtten as: p j = 1 Exp j= 1 [ Z.( γ j γ 0 ) Y.( α j α 0 ) w ( β j β 0 )] [ Z.( γ γ ) Y.( α α ) w ( β β )] Exp and p 0 = 1 p 1 p. j 0 j 0 j 0 for j = 1, (9) The dffculty s that the Multnomal logt estmaton permts dentfyng only the dfferences (α j -α 0 ), (β j -β 0 ), and (γ j -γ 0 ) for j = 1,. Yet, nspecton of (6) and (7) ndcates that snce the Bolsa Escola transfer s state-contngent, meanng that the ncome varable s asymmetrc across alternatves - t s necessary to know all three coeffcents α 0, α 1 and α n order to fnd the utlty maxmzng alternatve, k*. and Ths s where the only structural assumpton made so far becomes useful. Call bˆ j the estmated coeffcents of the multlogt model correspondng to the ncome and the chld earnng varables for alternatves j = 1,, the alternatve 0 beng taken as the default. Then (5) mples the followng system of equatons: â j α α = aˆ ( α M α ). K = bˆ ( α D α ) K = bˆ α α = aˆ 1 (10) M s known from equaton (3). It follows that arbtrarly settng a value for K or for D allows us to dentfy α 0, α 1 and α and the remanng parameter n the par (K,D). The dentfyng assumpton made n what follows s that kds workng on the market and not
12 gong to school have zero domestc producton,.e. K = 1. In other words, t s assumed that the observed labor allocatons between market and domestc actvtes are corner solutons n all alternatves. 1 It then follows that : α aˆ bˆ 1 M = and α = α1 aˆ aˆ 1 (11) Of course, a test of the relevance of the dentfyng assumpton s that both α 1 and α must be postve. One could also requre that the value of D obtaned from system (9) wth K=1 be n the nterval (0,1). For completeness, t remans to ndcate how estmates of the resdual terms v j -v 0 may be obtaned. In a dscrete choce model these values cannot be observed. It s only known that they belong to some nterval. The dea s then to draw them for each observaton n the relevant nterval, that s: n a way consstent wth the observed choce. For nstance f observaton has made choce 1, t must be the case that : Z.γ 1 Y -. â 1 ˆb 1.w (v 1 -v 0 ) > Sup[0, Z.γ Y -. â ˆb.w (v -v 0 )] The terms v j -v 0 must be drawn so as to satsfy that nequalty. All that s mssng now s a complete vector of chld earnngs values, w. Estmaton of potental earnngs The dscrete choce model requres a potental earnng for each chld, ncludng those who do not work outsde the household. To be fully rgorous, one could estmate both the dscrete choce model and the earnng equaton smultaneously by maxmum lkelhood technques. Ths s a rather cumbersome procedure. Practcally, a multnomal probt would then be preferable to a multnomal logt n order to handle smultaneously the random terms of the dscrete choce model and that of the earnng equaton. Integratng tr-varate normal dstrbutons would then be requred. Also, other ssues whch are already apparent wth a smpler technque would not necessarly be solved. 1 In effect, ths assumpton may be weakened usng some lmted nformaton on hours of work avalable n the survey.
13 We adopt a smpler approach, whch has the advantages of transparency and robustness. It conssts of estmatng (3) by OLS, and then to generate random terms u for non-workng kds, by drawng n the dstrbuton generated by the resduals of the OLS estmaton. There are several reasons why correctng the estmaton of the earnng functon for a selecton bas was problematc. Frst, nstrumentng earnngs wth a selecton bas correcton procedure requres fndng nstruments that would affect earnngs but not the schoolng/labor choce. No such nstrument was readly avalable. Second, the correcton of selecton bas wth the standard two-stage procedure s awkward n the case of more than two choces. Lee (1983) proposed a generalzaton of the Heckman procedure, but t has been shown that Lee's procedure was justfed only n a rather unlkely partcular case. 13 For both of these reasons, falng to correct for possble selecton bas n (3) dd not seem too serous a problem. On the other hand, tryng to correct usng standard technques and no convncng nstrument led to rather mplausble results. Smulatng programs of the Bolsa Escola type As mentoned n footnote 11, the model (6)-(7) does not provde a complete representaton of the choce faced by households n the presence of a program such as Bolsa Escola. Ths s because t takes nto account the condtonalty on the schoolng of the chldren, but not the means-test. Takng nto account both the means-test and the condtonalty leads to choosng the alternatve wth maxmum utlty among the three followng condtonal cases: > = = > = = = Y Y f v w Y Z U Y Y f v w T Y Z U Y Mw Y f v w Y Z U Y Mw Y f v w T Y Z U v w Y Z U I I I I I I I I I () ) (. (). (1) ) (. (1). (0) β α γ β α γ β α γ β α γ β α γ (1) where Y stands for the means test. Of course, as mentoned above, only the dfferences between the utlty correspondng to the three cases matter, so that one only need to know 13 See Bourgugnon et al. (001).
14 the dfferences (β j -β 0 ), (γ j -γ 0 ) and (v j - v 0 ) but the three coeffcents α j. In ths system, one can see how the ntroducton of Bolsa Escola mght lead households from choce (0) no schoolng to choces (1) or (), but also from choce (1) to choce (). In the latter case, a household mght not qualfy for the transfer T when the chld both works and attends school, but qualfes f she stops workng. A wde varety of programs may be easly smulated usng ths framework. Both the means-test and the transfer T could be made dependent on characterstcs of ether the household or the chld (X and H). In partcular, T could depend on age or gender. Some examples of such alternatve desgns are smulated and dscussed n Secton 5. Before presentng the model estmatons results, we should draw attenton to two mportant lmtatons of the framework just descrbed. Both arse from the set of assumptons dscussed n the begnnng of ths secton. The frst lmtaton s that we can not take nto account the household transfer celng of R$45 per household. The reason s that by gnorng mult-chldren nteractons n the model, t s as though we had effectvely assumed that all households were sngle-chld, from a behavoral pont of vew. In the non-behavoral part of the welfare smulatons whch are reported n Secton 5 below, however, each chld was treated separately, and the R$45 lmt was appled. The second lmtaton has to do wth the exogenety of non-chld ncome Y -I. Ths exogenety would clearly be a problem when there are more than one chld at schoolng age. But t s also unrealstc even when only adult ncome s taken nto account. It s clearly possble that the presence of the means-test mght affect the labor supply behavor of adults, snce there are crcumstances n whch t mght be n the nterest of the famly to work slghtly less n order to qualfy for Bolsa Escola. Note, however, that ths mght not be so sharply the case f the means-test s based, not on current ncome, but on some score-based proxy for permanent ncome, as appears to be the case n practce.
15 4. Descrptve statstcs and estmaton results The model consstng of equatons (3) and (1) was estmated on data from the 1999 PNAD household survey. Ths survey s based on a sample of approxmately 60,000 households, whch s representatve of the natonal populaton 14. Although all chldren aged 6-15 qualfy for partcpaton n the program, the model was only estmated for year-olds, snce school enrollment below age 10 s nearly unversal. 15 At the smulaton stage, however, transfers are of course smulated for the whole unverse of qualfyng 6-15 year-olds. Table 1 contans the basc descrpton of the occupatonal structure of chldren aged n Brazl, n In ths age range, 77% of chldren report that they dedcate themselves exclusvely to studyng. Some 17% both work and study, and 6% do not attend school at all. Ths average pattern hdes consderable varaton across ages: school attendance declnes and work ncreases monotoncally wth age. Whereas only.5% of ten year-olds are out of school, the fgure for ffteen year-olds s 13%. Whereas 90% of ten year-olds dedcate themselves exclusvely to studyng, fewer than 60% of ffteen year-olds do so. From a behavoral pont of vew, t s thus clear that most of the acton s to be found among the eldest chldren. Table presents the mean ndvdual and household characterstcs of those chldren, by occupatonal category. Chldren not gong to school are both older and less educated than those stll enrolled. As expected, households wth school drop-outs are on average poorer, less educated and larger than households where kds are stll gong to school. Droppng out of school and engagng n chld labor are relatvely more frequent among non-whtes and n the North-East. Both forms of behavor are least common n metropoltan areas, but proportonately more common n non-metropoltan urban areas than n rural areas. Interestngly, households where chldren both work and go to school 14 Except for the rural areas of the states of Acre, Amazonas, Pará, Rondôna and Rorama. 15 We know that school enrolment s nearly unversal from answers to schoolng questons n the PNAD. An addtonal reason to lmt the estmaton of the behavoral model to chldren aged ten or older s that the ncdence of chld labor at lower ages s probably measured wth much greater error, snce PNAD ntervewers are nstructed to pose labor and ncome questons only to ndvduals aged ten or older.
16 are n an ntermedate poston, along all dmensons, between those whose chldren specalze, but are generally closer to the group of drop-outs. A remarkable feature of Table s the observed amount of chldren s earnngs, when they work and do not study. Rangng from around R$80 to R$10 per month, chldren's earnngs represent approxmately half the mnmum wage, an order of magntude that seems rather reasonable. These amounts compares wth the R$15 transfer that s granted by the Bolsa Escola program for chldren enrolled n school. Note, however, that the R$90 fgure s not a good measure for the opportunty cost of schoolng, snce school attendance s evdently consstent wth some amount of market work. Tables 3 and 4 contan the estmaton results. Because of the great behavoral varaton across ages even wthn the range - as revealed, for nstance, n Table 1 - we estmated the (dentcally specfed) model separately for each age, as well as for the pooled sample of all year-olds. The smulatons reported n the next secton rely on the age-specfc models, but n ths secton we focus on the jont estmaton, both for ease of dscusson and because the larger sample sze allowed for more precse estmaton n ths case. Table 3 shows the results of the OLS estmaton of the earnngs functon (3), both for the pooled sample and for the 15 year-old group. 16 Geographcal varables 17, race and gender have the expected sgn, and the same qualtatve effect as for adults. So does (the logarthm of) the average earnngs of chldren n the census cluster, whch s ncluded as a proxy for the spatal varaton n the demand for chld labor. The effect of prevous schoolng s best descrbed as nsgnfcant. Even though the coeffcent of the squared term s postve and sgnfcant, the nfluence of the (negatve and nsgnfcant) lnear term mples that earnngs declne wth schoolng n the range relevant for yearolds. It should be noted that our separate specfcatons mask the man determnant of earnngs for chldren, namely age. In an alternatve (unreported) specfcaton for the pooled sample, when age was ncluded as an explanatory varable, an addtonal year of 16 Analogous results for the 10, 11, 1, 13 and 14 year-old samples are avalable from the authors on request. 17 Wth the South beng nsgnfcantly dfferent from the reference Southeast regon, as expected.
17 age ncreased earnngs by approxmately 40 per cent. But there was a clear non-lnearty n the way age affected earnngs, whch s reflected n changes n the coeffcent estmates when the model s separately estmated. These non-lneartes and nteractons between age and other determnants are the reason why the separate specfcaton was preferred. The estmate for m the coeffcent for dummy WS n Table 3 reveals that, as expected, the fact that a chld goes to school at the same tme as she works outsde the household reduces total earnngs n comparson wth a comparable chld who dedcates herself exclusvely to market work. If one nterprets ths coeffcent as reflectng fewer hours of work, then a chld gong to school works on average 40 per cent less than a dropout (for the pooled sample), or just under a quarter less for ffteen year-olds. These seem lke reasonable orders of magntude. The results from the estmaton of the multnomal logt for occupatonal choce also appear emnently plausble. They are reported n Table 4 (for the pooled sample) and Tables 4a and 4b for 10-1 and year-olds, respectvely. The reference category was not studyng (j = 0), throughout. As expected, household ncome (net of the chld s) has a postve effect on schoolng, whereas the chld s own (predcted) earnngs have a negatve effect. Household sze reduces the probablty of studyng, compared to the alternatves. 18 Prevous schoolng at a gven age has a postve (but concave) effect. Race has an nsgnfcant effect on occupatonal choce, unlke gender whch reflects the usual asymmetry between market work for males and domestc work for females. Parents' educaton has the expected postve effect on top of the ncome effect - on chldren's schoolng. In vew of ths general consstency of both the earnngs and the dscrete occupatonal choce models, the queston now arses of whether the structural restrctons necessary for the consstency of the proposed smulaton work postve α 1 and α, and 0 < D < 1 - hold or not. For the pooled sample and usng (11), we fnd that: aˆ ˆ 1 b α = = = 0.03 and α ˆ ˆ = α1 a a 1 M 1 Exp( ) 1 1 = To the extent that household sze reflects a larger number of chldren, ths s consstent wth Becker s quantty-qualty trade-off.
18 The coeffcents of ncome n the utlty of alternatves j = 1 and s thus postve, whch s n agreement wth the orgnal model. Ths s also true of the utlty of alternatve j =0 snce t may be computed that α 0 = The value of the parameter D may also be derved. Under the dentfyng assumpton that K =1, t s gven by : bˆ α 0 D = α = = Ths fgure means that chldren who are gong to school but do not work on the market are estmated to provde domestc producton for approxmately two-thrds of ther potental market earnngs. Note that ths s almost dentcal to the estmated value for M [= Exp ( ) = 0.665]. Snce M denotes the average contrbuton to household ncome from chldren both studyng and workng, as a share of ther potental contrbuton f not studyng, ths mples that the estmated value of non-market work by chldren studyng (and not workng n the market) s approxmately equal to the market value of work by those studyng (and workng n the market). If there was lttle selecton on unobservables nto market work, ths s exactly what one would expect. Overall, the estmates obtaned from the multnomal dscrete occupatonal choce model and the earnng equaton seem therefore remarkably consstent wth ratonal, utlty-maxmzng behavor. We may thus expect smulatons run on the bass of these models and the dentfyng structural assumptons about the parameter K to yeld sensble results. We can now turn to our man objectve: gaugng the order of magntude of the effects of programs such as Bolsa Escola. 5. An ex-ante evaluaton of Bolsa Escola and alternatve program desgns Bolsa Escola and many condtonal cash transfer schemes lke t are sad to have two dstnct objectves: () to reduce current poverty (and sometmes nequalty) through the targeted transfers, and () to reduce future poverty, by ncreasng the ncentves for today s poor to nvest n ther human captal. Later on n ths secton, we wll turn to the frst objectve. We begn by notng, however, that, as stated, the second objectve s mpossble to evaluate, even n an ex-ante manner. Whether ncreased school
19 enrollment translates nto greater human captal depends on the trends n the qualty of the educatonal servces provded, and there s no nformaton on that n ths data set. 19 Fnally, whether more human captal, however measured., wll help reduce poverty n the future or not, depends on what happens to the rates of return to t between now and then. Ths s a complex, general equlbrum queston, whch goes well beyond the scope of ths exercse. What we mght be able to say somethng about s the ntermedate target of ncreasng school enrollment. Whle the precedng remarks suggest that ths s not suffcent to establsh whether the program wll have an mpact on future poverty, t s at least necessary. 0 An ex-ante evaluaton of mpact on ths dmenson of the program thus requres smulatng the number of chldren that may change schoolng and workng status because of t. Ths s done by applyng the decson system (1) - wth behavoral parameter values (α, β, γ, M and D) estmated from (9) - (11), and polcy parameter values (T and Y 0 ) taken from the actual specfcaton of Bolsa Escola - to the orgnal data. Equaton (1) s then used to smulate a counterfactual dstrbuton of occupatons, on the bass of the observed characterstcs and the restrctons on resdual terms for each ndvdual chld. Comparng the vector of occupatonal choces thus generated wth the orgnal, observed vector, we see that the program leads to some chldren movng from choce S = 0 to choces S =1 or, and from S = 1 to choces S =. The correspondng transton matrx s shown n table 5 for all chldren between 10 and 15, as well as for all chldren n the same age group lvng n poor households. 1 Despte the small value of the proposed transfer, Table 5 suggests that one n every three chldren (aged 10-15) who are presently not enrolled n school would get 19 There s lmted nformaton n other data sets, such as the Educaton Mnstry s Sstema de Acompanhamento do Ensno Básco (SAEB), but not for suffcently long perods of tme. See Albernaz et. al. (00). 0 One could argue that t s not even necessary, snce the transfers mght, by themselves, allevate credt constrants and have long-term postve mpacts, e.g. through mproved nutrton. We focus on whether the condtonal nature of these transfers actually have any mpact of the chldren s occupatonal choces (or tme allocaton decsons). 1 A household was consdered poor f ts (regonally prce-deflated and mputed rent-adjusted) per capta ncome was less than R$74.48 n the reference month of the 1999 PNAD survey. For the dervaton of the poverty lne, see Ferrera et al. (forthcomng).
20 enough ncentve from Bolsa Escola to change occupatonal status and go to school. Among them, just over a quarter would enroll, but reman employed on the labor market. The other three quarters would actually cease work outsde ther household. Ths would reduce the proporton of chldren outsde school from 5.8% to 3.9%. The mpact on those currently both studyng and workng would be much smaller. Barely % of them would abandon work to dedcate themselves exclusvely to ther studes. As a result of ths small outflow, combned wth an nflow from occupatonal category 1, the group of chldren both studyng and workng would actually grow n the smulated scenaro, albet margnally. The mpacts are even more pronounced, as one would expect, among the poor who are the target populaton for the program. Accordng to the poverty lne beng used, the ncdence of poverty n Brazl s 30.5%. However, because there are more chldren n poor households ths beng one of the reasons why they are poor the proporton of chldren n poor households s much hgher: 4%. The second panel n Table 5 shows that dropouts are much more frequent among them 9.1 nstead of 5.8 per cent for the whole populaton. It also shows that Bolsa Escola s more effectve n ncreasng school enrollment. The fall n the proporton of dropouts s one-half, rather than one-thrd. As a result, the smulaton suggests that Bolsa Escola could ncrease the school enrollment rate among the poor by approxmately 4.4 percentage ponts. Once agan, ths ncrease comes at the expense of the not studyng category, whose numbers are halved, rather than of the workng and studyng category, whch actually becomes margnally more numerous. A 50% reducton n the proporton of poor chldren outsde school s by no means an nsubstantal achevement, partcularly n lght of the fact that t seems to be manageable wth farly small transfers (R$15 per chld per month). Ths s partly due to the fact that the value of the current contrbutons of chldren who are enrolled n school s a szable proporton of ther potental earnngs when completely outsde school. Those proportons are exactly the nterpretaton of the parameters M (for those who work on the market as well as study) and D (for those who work at home as well as study), whch we estmated to be of the order of Applyng that factor to R$100, as a rough average of the earnngs of chldren n category j = 0 (see Table ), we are left wth some R$33 as the
21 true opportunty cost of enrollng n school. Consequently, those chldren who change occupaton from that category n response to the R$15 transfer must have average personal present valuatons of the expected stream of benefts from enrollng greater than R$18. Those who don t, must on average value educaton at less than that. Because our smulatons suggest that Bolsa Escola, as currently formulated, would stll leave some 4% of all year-olds (4.7% among the poor ones) outsde school, t s nterestng to nvestgate the potental effects of changng some of the program parameters. Ths was, after all, one of the ntal motvatons for undertakng ths knd of ex-ante counterfactual analyss. Table 6 shows the results of such a comparatve exercse n terms of occupatonal choce, usng transton matrces analogous to those n Table 5, once agan both for all chldren and then separately for poor households only. Table 7 compares the mpact of each scenaro wth that of the benchmark program specfcaton, n terms of poverty and nequalty measures. Four standard nequalty measures were selected, namely the Gn coeffcent and three members of the Generalzed Entropy Class: the mean log devaton, the Thel-T ndex and (one half of) the square of the coeffcent of varaton. For poverty, we present the three standard FGT (0, 1, ) measures, wth respect to the aforementoned Ferrera et. al. (forthcomng) poverty lne. Ths later table allows us to gauge mpact n terms of the frst objectve of the program, namely the reducton of current poverty (and possbly nequalty). In both tables, the smulaton results for sx alternatve scenaros are presented. In scenaro 1, the elgblty crtera (ncludng the means test) are unchanged, but transfer amounts (and the total household celng) are both doubled. In scenaro, the unform R$15 per chld transfer s replaced by an age-contngent transfer, whereby 10 year-olds would receve R$15, 11 year-olds would receve R$0, 1 year-olds would receve R$5, 13 year-olds would receve R$35, 14 year-olds would receve R$40, and 15 year-olds receved R$45. In scenaro 3, transfer amounts were unchanged, but the means-test was rased from R$90 to R$10. Scenaro 4 combnes scenaros 1 and 3: the transfer was doubled, and the means-test rased to R$10. Scenaro 5 combnes scenaros and 3 n the same way: an age-progressve transfer wth a R$10 means-test. Scenaro 6 smulated a targeted transfer exactly as n Bolsa Escola, but wth no condtonalty: every chld n The household celng was also doubled to R$90 n ths case.
22 households below the means-test receved the beneft, wth no requrement relatng to school attendance. Table 6 gves rse to three man results. Frst of all, a comparson of Scenaro 6 and the actual Bolsa Escola program suggests that condtonalty plays a crucal role n nducng the change n chldren s tme-allocaton decsons. The proportons of chldren n each occupatonal category under Scenaro 6 are almost dentcal to the orgnal data (.e. no program). Ths suggests that t s the condtonal requrement to enroll n order to receve the beneft rather than the pure ncome effect from the transfer - whch s the prmary cause of the extra demand for schoolng evdent n the Bolsa Escola column. Second, scenaro 1 reveals that the occupatonal mpact of the program s reasonably elastc wth respect to the transfer amount. The proporton of un-enrolled chldren drops another percentage pont (.e. some 5%) n response to a doublng of the transfers. The proporton of chldren n the studyng only category rses by the same percentage pont. Scenaro suggests that t doesn t matter much, n aggregate terms, whether ths ncrease n transfers s unform across ages, or made to become ncreasng n the age of the chld. Fnally, scenaro 3 (and the combnatons n scenaros 4 and 5) suggest that occupatonal effects are less senstve to the means-test than to the transfer amount. Results are consderably less mpressve n terms of the program s frst stated objectve, namely the reducton n current poverty (and nequalty) levels. Table 7 suggests that the program, as currently envsaged, would only mply a one percentage pont declne n the short-run ncdence of poverty n Brazl, as measured by P(0). However, there s some evdence that the transfers would be rather well targeted, snce the nequalty-averse poverty ndcator P() would fall by proportonately more than P(0), from 8% to 7%. Ths s consstent wth the nequalty results: whereas the Gn would fall by only half a pont as a result of the scheme, measures whch are more senstve to the bottom, such as the mean log devaton, fall by a lttle more. Overall, however, the evdence n column of Table 7 falls consderably short of a rngng endorsement of Bolsa Escola as a program for the allevaton of current poverty or nequalty. The stuaton could be somewhat mproved by ncreases n the transfer amounts (scenaros 1 and ). Nevertheless, even a doublng of the transfer amount to R$30 per
23 month would only shave another 1.3 percentage ponts off the headcount. 3 An ncrease n the means-test would not help much, as ndcated by Scenaro 3. Ths s consstent wth our earler suggeston that the program already appears to be well-targeted to the poor. If t fals to lft many of them above the poverty lne, ths s a consequence of the small sze of the transfers, rather than of the targetng. These results contrast wth the arthmetc smulatons reported by Camargo and Ferrera (001), n whch a somewhat broader, but essentally smlar program would reduce the ncdence of poverty (wth respect to the same poverty lne and n the same sample) by two-thrds, from 30.5% to 9.9%. Ths was despte the fact that the absence of a behavoral component to the smulaton weakened ts power, by excludng from the set of recpents those households whose chldren mght have enrolled n response to the program. The reason s smple: Camargo and Ferrera smulate much hgher transfer levels, rangng from R$150 to R$0 per household (rather than chld). 6. Conclusons In ths paper, we proposed a mcro-smulaton method for evaluatng and expermentng wth condtonal cash-transfer program desgns, ex-ante. We were concerned wth the mpacts of the Brazlan Bolsa Escola program, whch ams to reduce both current and future poverty by provdng small targeted cash transfers to poor households, provded ther chldren are enrolled n and n actual attendance at school. We were nterested n assessng two dmensons of the program: ts mpact on the occupatonal choce (or tmeallocaton) decsons of chldren, and the effects on current poverty and nequalty. For ths purpose, we estmated a dscrete occupatonal choce model (a multnomal logt) on a natonally representatve household-level sample, and used ts estmated parameters to make predctons about the counterfactual occupatonal decsons of chldren, under dfferent assumptons about the avalablty and desgn of cash transfer programs. These assumptons were bascally expressed n terms of dfferent values for 3 The smulated one-percentage-pont fall n P() s, once agan, more respectable.
24 two key polcy parameters: the means-test level of household ncome; and the transfer amount. Because predcted earnngs values were needed for all chldren n the smulaton, ths procedure also requred estmatng a Mnceran earnngs equaton for chldren n the sample, and usng t to predct earnngs n some cases. Also, because the ncome values accrung to each household were not symmetrc across dfferent occupatonal choces, standard estmaton procedures for the multnomal logt were not vald. An dentfcaton assumpton was needed, and we chose t to be that chldren not enrolled n school work only n the market, and have a zero contrbuton to domestc work. Under ths assumpton, the estmaton of the model generated remarkably consstent results: margnal utltes of ncome were always postve, and very smlar across occupatonal categores. Tme spent workng by those enrolled n school, as a fracton of tme spent workng by those not enrolled, was always n the (0, 1) nterval and was bascally dentcal and equal to two-thrds - whether work was domestc or n the market. When ths estmated occupatonal choce model was used to smulate the offcal (Aprl 001) desgn of the federal Brazlan Bolsa Escola program, we found that there was consderable behavoral response from chldren to the program. About one thrd of all year-olds not currently enrolled n school would accordng to the model enrol n response to the program. Among poor households, ths proporton was even hgher: one half would enter school. The proporton of chldren n the mddle occupatonal category ( studyng and workng n the market ) would not fall. In fact, t would rse, margnally. Results n terms of the reducton of current poverty, however, were less heartenng. As currently desgned, the federal Bolsa Escola program would reduce poverty ncdence by one percentage pont only, and the Gn coeffcent by half a pont. Results were better for measures more senstve to the bottom of the dstrbuton, but the effect was never remarkable. Both the proporton of chldren enrollng n school n response to program avalablty and the degree of reducton n current poverty turn out to be rather senstve to transfer amounts, and rather nsenstve to the level of the means-test. Ths suggests that the targetng of the Brazlan Bolsa Escola program s adequate, but that poverty
Tests for Two Correlations
PASS Sample Sze Software Chapter 805 Tests for Two Correlatons Introducton The correlaton coeffcent (or correlaton), ρ, s a popular parameter for descrbng the strength of the assocaton between two varables.
More informationUNIVERSITY OF NOTTINGHAM
UNIVERSITY OF NOTTINGHAM SCHOOL OF ECONOMICS DISCUSSION PAPER 99/28 Welfare Analyss n a Cournot Game wth a Publc Good by Indraneel Dasgupta School of Economcs, Unversty of Nottngham, Nottngham NG7 2RD,
More informationMgtOp 215 Chapter 13 Dr. Ahn
MgtOp 5 Chapter 3 Dr Ahn Consder two random varables X and Y wth,,, In order to study the relatonshp between the two random varables, we need a numercal measure that descrbes the relatonshp The covarance
More informationChapter 6. Ex-Ante Evaluation of Policy Reforms using Behavioral Models. François Bourguignon and Francisco H.G. Ferreira
Chapter 6 Ex-Ante Evaluaton of Polcy Reforms (Bourgugnon & Ferrera) Chapter 6 Ex-Ante Evaluaton of Polcy Reforms usng Behavoral Models Franços Bourgugnon and Francsco H.G. Ferrera Abstract. The tools for
More informationCS 286r: Matching and Market Design Lecture 2 Combinatorial Markets, Walrasian Equilibrium, Tâtonnement
CS 286r: Matchng and Market Desgn Lecture 2 Combnatoral Markets, Walrasan Equlbrum, Tâtonnement Matchng and Money Recall: Last tme we descrbed the Hungaran Method for computng a maxmumweght bpartte matchng.
More information3/3/2014. CDS M Phil Econometrics. Vijayamohanan Pillai N. Truncated standard normal distribution for a = 0.5, 0, and 0.5. CDS Mphil Econometrics
Lmted Dependent Varable Models: Tobt an Plla N 1 CDS Mphl Econometrcs Introducton Lmted Dependent Varable Models: Truncaton and Censorng Maddala, G. 1983. Lmted Dependent and Qualtatve Varables n Econometrcs.
More informationClearing Notice SIX x-clear Ltd
Clearng Notce SIX x-clear Ltd 1.0 Overvew Changes to margn and default fund model arrangements SIX x-clear ( x-clear ) s closely montorng the CCP envronment n Europe as well as the needs of ts Members.
More informationFORD MOTOR CREDIT COMPANY SUGGESTED ANSWERS. Richard M. Levich. New York University Stern School of Business. Revised, February 1999
FORD MOTOR CREDIT COMPANY SUGGESTED ANSWERS by Rchard M. Levch New York Unversty Stern School of Busness Revsed, February 1999 1 SETTING UP THE PROBLEM The bond s beng sold to Swss nvestors for a prce
More information3: Central Limit Theorem, Systematic Errors
3: Central Lmt Theorem, Systematc Errors 1 Errors 1.1 Central Lmt Theorem Ths theorem s of prme mportance when measurng physcal quanttes because usually the mperfectons n the measurements are due to several
More information15-451/651: Design & Analysis of Algorithms January 22, 2019 Lecture #3: Amortized Analysis last changed: January 18, 2019
5-45/65: Desgn & Analyss of Algorthms January, 09 Lecture #3: Amortzed Analyss last changed: January 8, 09 Introducton In ths lecture we dscuss a useful form of analyss, called amortzed analyss, for problems
More informationDomestic Savings and International Capital Flows
Domestc Savngs and Internatonal Captal Flows Martn Feldsten and Charles Horoka The Economc Journal, June 1980 Presented by Mchael Mbate and Chrstoph Schnke Introducton The 2 Vews of Internatonal Captal
More informationA MODEL OF COMPETITION AMONG TELECOMMUNICATION SERVICE PROVIDERS BASED ON REPEATED GAME
A MODEL OF COMPETITION AMONG TELECOMMUNICATION SERVICE PROVIDERS BASED ON REPEATED GAME Vesna Radonć Đogatovć, Valentna Radočć Unversty of Belgrade Faculty of Transport and Traffc Engneerng Belgrade, Serba
More informationRaising Food Prices and Welfare Change: A Simple Calibration. Xiaohua Yu
Rasng Food Prces and Welfare Change: A Smple Calbraton Xaohua Yu Professor of Agrcultural Economcs Courant Research Centre Poverty, Equty and Growth Unversty of Göttngen CRC-PEG, Wlhelm-weber-Str. 2 3773
More informationTests for Two Ordered Categorical Variables
Chapter 253 Tests for Two Ordered Categorcal Varables Introducton Ths module computes power and sample sze for tests of ordered categorcal data such as Lkert scale data. Assumng proportonal odds, such
More informationSpatial Variations in Covariates on Marriage and Marital Fertility: Geographically Weighted Regression Analyses in Japan
Spatal Varatons n Covarates on Marrage and Martal Fertlty: Geographcally Weghted Regresson Analyses n Japan Kenj Kamata (Natonal Insttute of Populaton and Socal Securty Research) Abstract (134) To understand
More informationoccurrence of a larger storm than our culvert or bridge is barely capable of handling? (what is The main question is: What is the possibility of
Module 8: Probablty and Statstcal Methods n Water Resources Engneerng Bob Ptt Unversty of Alabama Tuscaloosa, AL Flow data are avalable from numerous USGS operated flow recordng statons. Data s usually
More informationMeasures of Spread IQR and Deviation. For exam X, calculate the mean, median and mode. For exam Y, calculate the mean, median and mode.
Part 4 Measures of Spread IQR and Devaton In Part we learned how the three measures of center offer dfferent ways of provdng us wth a sngle representatve value for a data set. However, consder the followng
More informationSpurious Seasonal Patterns and Excess Smoothness in the BLS Local Area Unemployment Statistics
Spurous Seasonal Patterns and Excess Smoothness n the BLS Local Area Unemployment Statstcs Keth R. Phllps and Janguo Wang Federal Reserve Bank of Dallas Research Department Workng Paper 1305 September
More informationA Utilitarian Approach of the Rawls s Difference Principle
1 A Utltaran Approach of the Rawls s Dfference Prncple Hyeok Yong Kwon a,1, Hang Keun Ryu b,2 a Department of Poltcal Scence, Korea Unversty, Seoul, Korea, 136-701 b Department of Economcs, Chung Ang Unversty,
More informationRandom Variables. b 2.
Random Varables Generally the object of an nvestgators nterest s not necessarly the acton n the sample space but rather some functon of t. Techncally a real valued functon or mappng whose doman s the sample
More informationPrice and Quantity Competition Revisited. Abstract
rce and uantty Competton Revsted X. Henry Wang Unversty of Mssour - Columba Abstract By enlargng the parameter space orgnally consdered by Sngh and Vves (984 to allow for a wder range of cost asymmetry,
More informationQuiz on Deterministic part of course October 22, 2002
Engneerng ystems Analyss for Desgn Quz on Determnstc part of course October 22, 2002 Ths s a closed book exercse. You may use calculators Grade Tables There are 90 ponts possble for the regular test, or
More information- contrast so-called first-best outcome of Lindahl equilibrium with case of private provision through voluntary contributions of households
Prvate Provson - contrast so-called frst-best outcome of Lndahl equlbrum wth case of prvate provson through voluntary contrbutons of households - need to make an assumpton about how each household expects
More informationAn Application of Alternative Weighting Matrix Collapsing Approaches for Improving Sample Estimates
Secton on Survey Research Methods An Applcaton of Alternatve Weghtng Matrx Collapsng Approaches for Improvng Sample Estmates Lnda Tompkns 1, Jay J. Km 2 1 Centers for Dsease Control and Preventon, atonal
More informationThe Integration of the Israel Labour Force Survey with the National Insurance File
The Integraton of the Israel Labour Force Survey wth the Natonal Insurance Fle Natale SHLOMO Central Bureau of Statstcs Kanfey Nesharm St. 66, corner of Bach Street, Jerusalem Natales@cbs.gov.l Abstact:
More informationElements of Economic Analysis II Lecture VI: Industry Supply
Elements of Economc Analyss II Lecture VI: Industry Supply Ka Hao Yang 10/12/2017 In the prevous lecture, we analyzed the frm s supply decson usng a set of smple graphcal analyses. In fact, the dscusson
More informationEvaluating Performance
5 Chapter Evaluatng Performance In Ths Chapter Dollar-Weghted Rate of Return Tme-Weghted Rate of Return Income Rate of Return Prncpal Rate of Return Daly Returns MPT Statstcs 5- Measurng Rates of Return
More information2) In the medium-run/long-run, a decrease in the budget deficit will produce:
4.02 Quz 2 Solutons Fall 2004 Multple-Choce Questons ) Consder the wage-settng and prce-settng equatons we studed n class. Suppose the markup, µ, equals 0.25, and F(u,z) = -u. What s the natural rate of
More informationUniversity of Toronto November 9, 2006 ECO 209Y MACROECONOMIC THEORY. Term Test #1 L0101 L0201 L0401 L5101 MW MW 1-2 MW 2-3 W 6-8
Department of Economcs Prof. Gustavo Indart Unversty of Toronto November 9, 2006 SOLUTION ECO 209Y MACROECONOMIC THEORY Term Test #1 A LAST NAME FIRST NAME STUDENT NUMBER Crcle your secton of the course:
More informationUniversity of Toronto November 9, 2006 ECO 209Y MACROECONOMIC THEORY. Term Test #1 L0101 L0201 L0401 L5101 MW MW 1-2 MW 2-3 W 6-8
Department of Economcs Prof. Gustavo Indart Unversty of Toronto November 9, 2006 SOLUTION ECO 209Y MACROECONOMIC THEORY Term Test #1 C LAST NAME FIRST NAME STUDENT NUMBER Crcle your secton of the course:
More informationMoney, Banking, and Financial Markets (Econ 353) Midterm Examination I June 27, Name Univ. Id #
Money, Bankng, and Fnancal Markets (Econ 353) Mdterm Examnaton I June 27, 2005 Name Unv. Id # Note: Each multple-choce queston s worth 4 ponts. Problems 20, 21, and 22 carry 10, 8, and 10 ponts, respectvely.
More informationECONOMETRICS - FINAL EXAM, 3rd YEAR (GECO & GADE)
ECONOMETRICS - FINAL EXAM, 3rd YEAR (GECO & GADE) May 17, 2016 15:30 Frst famly name: Name: DNI/ID: Moble: Second famly Name: GECO/GADE: Instructor: E-mal: Queston 1 A B C Blank Queston 2 A B C Blank Queston
More informationBid-auction framework for microsimulation of location choice with endogenous real estate prices
Bd-aucton framework for mcrosmulaton of locaton choce wth endogenous real estate prces Rcardo Hurtuba Mchel Berlare Francsco Martínez Urbancs Termas de Chllán, Chle March 28 th 2012 Outlne 1) Motvaton
More informationMULTIPLE CURVE CONSTRUCTION
MULTIPLE CURVE CONSTRUCTION RICHARD WHITE 1. Introducton In the post-credt-crunch world, swaps are generally collateralzed under a ISDA Master Agreement Andersen and Pterbarg p266, wth collateral rates
More informationMonetary Tightening Cycles and the Predictability of Economic Activity. by Tobias Adrian and Arturo Estrella * October 2006.
Monetary Tghtenng Cycles and the Predctablty of Economc Actvty by Tobas Adran and Arturo Estrella * October 2006 Abstract Ten out of thrteen monetary tghtenng cycles snce 1955 were followed by ncreases
More informationLinear Combinations of Random Variables and Sampling (100 points)
Economcs 30330: Statstcs for Economcs Problem Set 6 Unversty of Notre Dame Instructor: Julo Garín Sprng 2012 Lnear Combnatons of Random Varables and Samplng 100 ponts 1. Four-part problem. Go get some
More informationLabor Market Transitions in Peru
Labor Market Transtons n Peru Javer Herrera* Davd Rosas Shady** *IRD and INEI, E-mal: jherrera@ne.gob.pe ** IADB, E-mal: davdro@adb.org The Issue U s one of the major ssues n Peru However: - The U rate
More informationII. Random Variables. Variable Types. Variables Map Outcomes to Numbers
II. Random Varables Random varables operate n much the same way as the outcomes or events n some arbtrary sample space the dstncton s that random varables are smply outcomes that are represented numercally.
More informationFinance 402: Problem Set 1 Solutions
Fnance 402: Problem Set 1 Solutons Note: Where approprate, the fnal answer for each problem s gven n bold talcs for those not nterested n the dscusson of the soluton. 1. The annual coupon rate s 6%. A
More informationCh Rival Pure private goods (most retail goods) Non-Rival Impure public goods (internet service)
h 7 1 Publc Goods o Rval goods: a good s rval f ts consumpton by one person precludes ts consumpton by another o Excludable goods: a good s excludable f you can reasonably prevent a person from consumng
More informationChapter 10 Making Choices: The Method, MARR, and Multiple Attributes
Chapter 0 Makng Choces: The Method, MARR, and Multple Attrbutes INEN 303 Sergy Butenko Industral & Systems Engneerng Texas A&M Unversty Comparng Mutually Exclusve Alternatves by Dfferent Evaluaton Methods
More informationCOS 511: Theoretical Machine Learning. Lecturer: Rob Schapire Lecture #21 Scribe: Lawrence Diao April 23, 2013
COS 511: Theoretcal Machne Learnng Lecturer: Rob Schapre Lecture #21 Scrbe: Lawrence Dao Aprl 23, 2013 1 On-Lne Log Loss To recap the end of the last lecture, we have the followng on-lne problem wth N
More informationProblem Set 6 Finance 1,
Carnege Mellon Unversty Graduate School of Industral Admnstraton Chrs Telmer Wnter 2006 Problem Set 6 Fnance, 47-720. (representatve agent constructon) Consder the followng two-perod, two-agent economy.
More informationA Comparison of Statistical Methods in Interrupted Time Series Analysis to Estimate an Intervention Effect
Transport and Road Safety (TARS) Research Joanna Wang A Comparson of Statstcal Methods n Interrupted Tme Seres Analyss to Estmate an Interventon Effect Research Fellow at Transport & Road Safety (TARS)
More informationEXTENSIVE VS. INTENSIVE MARGIN: CHANGING PERSPECTIVE ON THE EMPLOYMENT RATE. and Eliana Viviano (Bank of Italy)
EXTENSIVE VS. INTENSIVE MARGIN: CHANGING PERSPECTIVE ON THE EMPLOYMENT RATE Andrea Brandoln and Elana Vvano (Bank of Italy) 2 European User Conference for EU-LFS and EU-SILC, Mannhem 31 March 1 Aprl, 2011
More informationEstimation of Wage Equations in Australia: Allowing for Censored Observations of Labour Supply *
Estmaton of Wage Equatons n Australa: Allowng for Censored Observatons of Labour Supply * Guyonne Kalb and Rosanna Scutella* Melbourne Insttute of Appled Economc and Socal Research The Unversty of Melbourne
More informationMembers not eligible for this option
DC - Lump sum optons R6.1 Uncrystallsed funds penson lump sum An uncrystallsed funds penson lump sum, known as a UFPLS (also called a FLUMP), s a way of takng your penson pot wthout takng money from a
More informationLeast Cost Strategies for Complying with New NOx Emissions Limits
Least Cost Strateges for Complyng wth New NOx Emssons Lmts Internatonal Assocaton for Energy Economcs New England Chapter Presented by Assef A. Zoban Tabors Caramans & Assocates Cambrdge, MA 02138 January
More informationAsset Management. Country Allocation and Mutual Fund Returns
Country Allocaton and Mutual Fund Returns By Dr. Lela Heckman, Senor Managng Drector and Dr. John Mulln, Managng Drector Bear Stearns Asset Management Bear Stearns Actve Country Equty Executve Summary
More informationCHAPTER 9 FUNCTIONAL FORMS OF REGRESSION MODELS
CHAPTER 9 FUNCTIONAL FORMS OF REGRESSION MODELS QUESTIONS 9.1. (a) In a log-log model the dependent and all explanatory varables are n the logarthmc form. (b) In the log-ln model the dependent varable
More informationProblems to be discussed at the 5 th seminar Suggested solutions
ECON4260 Behavoral Economcs Problems to be dscussed at the 5 th semnar Suggested solutons Problem 1 a) Consder an ultmatum game n whch the proposer gets, ntally, 100 NOK. Assume that both the proposer
More informationSolutions to Odd-Numbered End-of-Chapter Exercises: Chapter 12
Introducton to Econometrcs (3 rd Updated Edton) by James H. Stock and Mark W. Watson Solutons to Odd-Numbered End-of-Chapter Exercses: Chapter 1 (Ths verson July 0, 014) Stock/Watson - Introducton to Econometrcs
More informationInformation Flow and Recovering the. Estimating the Moments of. Normality of Asset Returns
Estmatng the Moments of Informaton Flow and Recoverng the Normalty of Asset Returns Ané and Geman (Journal of Fnance, 2000) Revsted Anthony Murphy, Nuffeld College, Oxford Marwan Izzeldn, Unversty of Lecester
More informationNotes are not permitted in this examination. Do not turn over until you are told to do so by the Invigilator.
UNIVERSITY OF EAST ANGLIA School of Economcs Man Seres PG Examnaton 2016-17 BANKING ECONOMETRICS ECO-7014A Tme allowed: 2 HOURS Answer ALL FOUR questons. Queston 1 carres a weght of 30%; queston 2 carres
More informationStochastic ALM models - General Methodology
Stochastc ALM models - General Methodology Stochastc ALM models are generally mplemented wthn separate modules: A stochastc scenaros generator (ESG) A cash-flow projecton tool (or ALM projecton) For projectng
More informationCapability Analysis. Chapter 255. Introduction. Capability Analysis
Chapter 55 Introducton Ths procedure summarzes the performance of a process based on user-specfed specfcaton lmts. The observed performance as well as the performance relatve to the Normal dstrbuton are
More informationA Bootstrap Confidence Limit for Process Capability Indices
A ootstrap Confdence Lmt for Process Capablty Indces YANG Janfeng School of usness, Zhengzhou Unversty, P.R.Chna, 450001 Abstract The process capablty ndces are wdely used by qualty professonals as an
More informationOPERATIONS RESEARCH. Game Theory
OPERATIONS RESEARCH Chapter 2 Game Theory Prof. Bbhas C. Gr Department of Mathematcs Jadavpur Unversty Kolkata, Inda Emal: bcgr.umath@gmal.com 1.0 Introducton Game theory was developed for decson makng
More informationUnderstanding price volatility in electricity markets
Proceedngs of the 33rd Hawa Internatonal Conference on System Scences - 2 Understandng prce volatlty n electrcty markets Fernando L. Alvarado, The Unversty of Wsconsn Rajesh Rajaraman, Chrstensen Assocates
More informationISyE 512 Chapter 9. CUSUM and EWMA Control Charts. Instructor: Prof. Kaibo Liu. Department of Industrial and Systems Engineering UW-Madison
ISyE 512 hapter 9 USUM and EWMA ontrol harts Instructor: Prof. Kabo Lu Department of Industral and Systems Engneerng UW-Madson Emal: klu8@wsc.edu Offce: Room 317 (Mechancal Engneerng Buldng) ISyE 512 Instructor:
More informationLecture Note 2 Time Value of Money
Seg250 Management Prncples for Engneerng Managers Lecture ote 2 Tme Value of Money Department of Systems Engneerng and Engneerng Management The Chnese Unversty of Hong Kong Interest: The Cost of Money
More informationSolution of periodic review inventory model with general constrains
Soluton of perodc revew nventory model wth general constrans Soluton of perodc revew nventory model wth general constrans Prof Dr J Benkő SZIU Gödöllő Summary Reasons for presence of nventory (stock of
More informationConsumption Based Asset Pricing
Consumpton Based Asset Prcng Mchael Bar Aprl 25, 208 Contents Introducton 2 Model 2. Prcng rsk-free asset............................... 3 2.2 Prcng rsky assets................................ 4 2.3 Bubbles......................................
More informationWelfare Aspects in the Realignment of Commercial Framework. between Japan and China
Prepared for the 13 th INFORUM World Conference n Huangshan, Chna, July 3 9, 2005 Welfare Aspects n the Realgnment of Commercal Framework between Japan and Chna Toshak Hasegawa Chuo Unversty, Japan Introducton
More informationMaturity Effect on Risk Measure in a Ratings-Based Default-Mode Model
TU Braunschweg - Insttut für Wrtschaftswssenschaften Lehrstuhl Fnanzwrtschaft Maturty Effect on Rsk Measure n a Ratngs-Based Default-Mode Model Marc Gürtler and Drk Hethecker Fnancal Modellng Workshop
More informationMembers not eligible for this option
DC - Lump sum optons R6.2 Uncrystallsed funds penson lump sum An uncrystallsed funds penson lump sum, known as a UFPLS (also called a FLUMP), s a way of takng your penson pot wthout takng money from a
More informationECE 586GT: Problem Set 2: Problems and Solutions Uniqueness of Nash equilibria, zero sum games, evolutionary dynamics
Unversty of Illnos Fall 08 ECE 586GT: Problem Set : Problems and Solutons Unqueness of Nash equlbra, zero sum games, evolutonary dynamcs Due: Tuesday, Sept. 5, at begnnng of class Readng: Course notes,
More informationInternational ejournals
Avalable onlne at www.nternatonalejournals.com ISSN 0976 1411 Internatonal ejournals Internatonal ejournal of Mathematcs and Engneerng 7 (010) 86-95 MODELING AND PREDICTING URBAN MALE POPULATION OF BANGLADESH:
More information/ Computational Genomics. Normalization
0-80 /02-70 Computatonal Genomcs Normalzaton Gene Expresson Analyss Model Computatonal nformaton fuson Bologcal regulatory networks Pattern Recognton Data Analyss clusterng, classfcaton normalzaton, mss.
More informationSingle-Item Auctions. CS 234r: Markets for Networks and Crowds Lecture 4 Auctions, Mechanisms, and Welfare Maximization
CS 234r: Markets for Networks and Crowds Lecture 4 Auctons, Mechansms, and Welfare Maxmzaton Sngle-Item Auctons Suppose we have one or more tems to sell and a pool of potental buyers. How should we decde
More informationEquilibrium in Prediction Markets with Buyers and Sellers
Equlbrum n Predcton Markets wth Buyers and Sellers Shpra Agrawal Nmrod Megddo Benamn Armbruster Abstract Predcton markets wth buyers and sellers of contracts on multple outcomes are shown to have unque
More informationWork, Offers, and Take-Up: Decomposing the Source of Recent Declines in Employer- Sponsored Insurance
Work, Offers, and Take-Up: Decomposng the Source of Recent Declnes n Employer- Sponsored Insurance Lnda J. Blumberg and John Holahan The Natonal Bureau of Economc Research (NBER) determned that a recesson
More informationUrban Effects on Participation and Wages: Are there Gender. Differences? 1
Urban Effects on Partcpaton and Wages: Are there Gender Dfferences? 1 Euan Phmster ** Department of Economcs and Arkleton Insttute for Rural Development Research, Unversty of Aberdeen. Centre for European
More informationFinite Math - Fall Section Future Value of an Annuity; Sinking Funds
Fnte Math - Fall 2016 Lecture Notes - 9/19/2016 Secton 3.3 - Future Value of an Annuty; Snkng Funds Snkng Funds. We can turn the annutes pcture around and ask how much we would need to depost nto an account
More informationIn the 1990s, Japanese economy has experienced a surge in the unemployment rate,
Productvty Growth and the female labor supply n Japan Yoko Furukawa * Tomohko Inu Abstract: In the 990s, Japanese economy has experenced a surge n the unemployment rate, and ths s due partly to the recent
More informationTHE ECONOMICS OF TAXATION
THE ECONOMICS OF TAXATION Statc Ramsey Tax School of Economcs, Xamen Unversty Fall 2015 Overvew of Optmal Taxaton Combne lessons on ncdence and effcency costs to analyze optmal desgn of commodty taxes.
More informationTHE VOLATILITY OF EQUITY MUTUAL FUND RETURNS
North Amercan Journal of Fnance and Bankng Research Vol. 4. No. 4. 010. THE VOLATILITY OF EQUITY MUTUAL FUND RETURNS Central Connectcut State Unversty, USA. E-mal: BelloZ@mal.ccsu.edu ABSTRACT I nvestgated
More informationPivot Points for CQG - Overview
Pvot Ponts for CQG - Overvew By Bran Bell Introducton Pvot ponts are a well-known technque used by floor traders to calculate ntraday support and resstance levels. Ths technque has been around for decades,
More informationOCR Statistics 1 Working with data. Section 2: Measures of location
OCR Statstcs 1 Workng wth data Secton 2: Measures of locaton Notes and Examples These notes have sub-sectons on: The medan Estmatng the medan from grouped data The mean Estmatng the mean from grouped data
More informationFM303. CHAPTERS COVERED : CHAPTERS 5, 8 and 9. LEARNER GUIDE : UNITS 1, 2 and 3.1 to 3.3. DUE DATE : 3:00 p.m. 19 MARCH 2013
Page 1 of 11 ASSIGNMENT 1 ST SEMESTER : FINANCIAL MANAGEMENT 3 () CHAPTERS COVERED : CHAPTERS 5, 8 and 9 LEARNER GUIDE : UNITS 1, 2 and 3.1 to 3.3 DUE DATE : 3:00 p.m. 19 MARCH 2013 TOTAL MARKS : 100 INSTRUCTIONS
More informationProspect Theory and Asset Prices
Fnance 400 A. Penat - G. Pennacch Prospect Theory and Asset Prces These notes consder the asset prcng mplcatons of nvestor behavor that ncorporates Prospect Theory. It summarzes an artcle by N. Barbers,
More informationGeneral Examination in Microeconomic Theory. Fall You have FOUR hours. 2. Answer all questions
HARVARD UNIVERSITY DEPARTMENT OF ECONOMICS General Examnaton n Mcroeconomc Theory Fall 2010 1. You have FOUR hours. 2. Answer all questons PLEASE USE A SEPARATE BLUE BOOK FOR EACH QUESTION AND WRITE THE
More informationEconomics 1410 Fall Section 7 Notes 1. Define the tax in a flexible way using T (z), where z is the income reported by the agent.
Economcs 1410 Fall 2017 Harvard Unversty Yaan Al-Karableh Secton 7 Notes 1 I. The ncome taxaton problem Defne the tax n a flexble way usng T (), where s the ncome reported by the agent. Retenton functon:
More informationDiscounted Cash Flow (DCF) Analysis: What s Wrong With It And How To Fix It
Dscounted Cash Flow (DCF Analyss: What s Wrong Wth It And How To Fx It Arturo Cfuentes (* CREM Facultad de Economa y Negocos Unversdad de Chle June 2014 (* Jont effort wth Francsco Hawas; Depto. de Ingenera
More informationHighlights of the Macroprudential Report for June 2018
Hghlghts of the Macroprudental Report for June 2018 October 2018 FINANCIAL STABILITY DEPARTMENT Preface Bank of Jamaca frequently conducts assessments of the reslence and strength of the fnancal system.
More informationOnline Appendix for Merger Review for Markets with Buyer Power
Onlne Appendx for Merger Revew for Markets wth Buyer Power Smon Loertscher Lesle M. Marx July 23, 2018 Introducton In ths appendx we extend the framework of Loertscher and Marx (forthcomng) to allow two
More informationApplications of Myerson s Lemma
Applcatons of Myerson s Lemma Professor Greenwald 28-2-7 We apply Myerson s lemma to solve the sngle-good aucton, and the generalzaton n whch there are k dentcal copes of the good. Our objectve s welfare
More informationPhysics 4A. Error Analysis or Experimental Uncertainty. Error
Physcs 4A Error Analyss or Expermental Uncertanty Slde Slde 2 Slde 3 Slde 4 Slde 5 Slde 6 Slde 7 Slde 8 Slde 9 Slde 0 Slde Slde 2 Slde 3 Slde 4 Slde 5 Slde 6 Slde 7 Slde 8 Slde 9 Slde 20 Slde 2 Error n
More informationWhich of the following provides the most reasonable approximation to the least squares regression line? (a) y=50+10x (b) Y=50+x (d) Y=1+50x
Whch of the followng provdes the most reasonable approxmaton to the least squares regresson lne? (a) y=50+10x (b) Y=50+x (c) Y=10+50x (d) Y=1+50x (e) Y=10+x In smple lnear regresson the model that s begn
More information>1 indicates country i has a comparative advantage in production of j; the greater the index, the stronger the advantage. RCA 1 ij
69 APPENDIX 1 RCA Indces In the followng we present some maor RCA ndces reported n the lterature. For addtonal varants and other RCA ndces, Memedovc (1994) and Vollrath (1991) provde more thorough revews.
More informationSurvey of Math: Chapter 22: Consumer Finance Borrowing Page 1
Survey of Math: Chapter 22: Consumer Fnance Borrowng Page 1 APR and EAR Borrowng s savng looked at from a dfferent perspectve. The dea of smple nterest and compound nterest stll apply. A new term s the
More informationTaxation and Externalities. - Much recent discussion of policy towards externalities, e.g., global warming debate/kyoto
Taxaton and Externaltes - Much recent dscusson of polcy towards externaltes, e.g., global warmng debate/kyoto - Increasng share of tax revenue from envronmental taxaton 6 percent n OECD - Envronmental
More informationc slope = -(1+i)/(1+π 2 ) MRS (between consumption in consecutive time periods) price ratio (across consecutive time periods)
CONSUMPTION-SAVINGS FRAMEWORK (CONTINUED) SEPTEMBER 24, 2013 The Graphcs of the Consumpton-Savngs Model CONSUMER OPTIMIZATION Consumer s decson problem: maxmze lfetme utlty subject to lfetme budget constrant
More informationEQUALITAS Working Paper No. 39
EQUALITAS Workng Paper No. 39 Behavoral Mcrosmulaton of the Impact of In-Work Benefts on Female Labor Supply and Income Dstrbuton: Evdence from Span Lus Ayala Mlagros Panagua Aprl 2016 Behavoral Mcrosmulaton
More informationData Mining Linear and Logistic Regression
07/02/207 Data Mnng Lnear and Logstc Regresson Mchael L of 26 Regresson In statstcal modellng, regresson analyss s a statstcal process for estmatng the relatonshps among varables. Regresson models are
More informationEconomic Design of Short-Run CSP-1 Plan Under Linear Inspection Cost
Tamkang Journal of Scence and Engneerng, Vol. 9, No 1, pp. 19 23 (2006) 19 Economc Desgn of Short-Run CSP-1 Plan Under Lnear Inspecton Cost Chung-Ho Chen 1 * and Chao-Yu Chou 2 1 Department of Industral
More informationISE High Income Index Methodology
ISE Hgh Income Index Methodology Index Descrpton The ISE Hgh Income Index s desgned to track the returns and ncome of the top 30 U.S lsted Closed-End Funds. Index Calculaton The ISE Hgh Income Index s
More information5. Market Structure and International Trade. Consider the role of economies of scale and market structure in generating intra-industry trade.
Rose-Hulman Insttute of Technology GL458, Internatonal Trade & Globalzaton / K. Chrst 5. Market Structure and Internatonal Trade Learnng Objectves 5. Market Structure and Internatonal Trade Consder the
More informationMacroeconomic equilibrium in the short run: the Money market
Macroeconomc equlbrum n the short run: the Money market 2013 1. The bg pcture Overvew Prevous lecture How can we explan short run fluctuatons n GDP? Key assumpton: stcky prces Equlbrum of the goods market
More informationreferences Chapters on game theory in Mas-Colell, Whinston and Green
Syllabus. Prelmnares. Role of game theory n economcs. Normal and extensve form of a game. Game-tree. Informaton partton. Perfect recall. Perfect and mperfect nformaton. Strategy.. Statc games of complete
More information