Central Statistical Bureau of Latvia FINAL QUALITY REPORT RELATING TO EU-SILC OPERATIONS

Transcription

1 Central Statistical Bureau of Latvia FINAL QUALITY REPORT RELATING TO EU-SILC OPERATIONS Riga 2012

2 CONTENTS CONTENTS... 2 Background Common longitudinal European Union Indicators based on the longitudinal component of EU-SILC Accuracy Sample Design Type of sampling Sampling units Stratification and sub-stratification criteria Sample size and allocation criteria Sample selections schemes Sample distribution over time Renewal of sample: rotational groups Weightings Design factor Non-response adjustments Adjustments to external data (level, variables used and sources) Final longitudinal weights Final household cross-sectional weight Substitutions Sampling errors Non-sampling errors Sampling frame and coverage errors Measurement and processing errors Non-response errors Achieved sample size Unit non-response Distribution of households by household status (DB110), by the record of contact at the address (DB120), by the household questionnaire result (DB130) and by the household interview acceptance (DB135) Distribution of persons by membership status (RB110) Item non-response Mode of data collection Imputation procedure Imputed rent Company cars Comparability Basic concepts and definitions Components of income Differences between the national definitions and standard EU-SILC definitions, and an assessment of the differences mentioned Total household gross income Total disposable household income Total disposable household income, before social transfers other than old-age and survivor s benefits Total disposable household income, before social transfers including old age and survivor s benefits Imputed rent Income from rental property and land Family/children-related allowances

3 Social exclusion payments not elsewhere classified Housing allowances Regular inter-household cash transfers received Interest, dividends, profit from capital investments in unincorporated business Interest paid on mortgages Income received by people aged under Regular taxes on wealth Regular inter-household transfers paid Tax on income and social contributions Repayments/receipts for tax adjustments Cash or near-cash employee income Non-cash employee income Employers social contributions Cash profits or losses from self-employment (including royalties) Value of goods produced for own consumption Unemployment benefits Old-age benefits Survivors benefits Sickness benefits Disability benefits Education related benefits The source of collecting income variables The form in which income target variables at component level were obtained The method used for obtaining income target variables in required form Tracing rules Coherence Comparison of income target variables and the number of persons who receive income from each income component with external sources

4 Background In Latvia the EU-SILC survey was launched in The Latvian EU-SILC survey is an annual survey with a four-year rotational panel and it is carried out as an independent survey, by single operation covering cross-sectional and longitudinal primary target variables as well as secondary target variables. 1. Common longitudinal European Union Indicators based on the longitudinal component of EU-SILC Table 1.1. Indicators based on the longitudinal component of EU-SILC Indicator Value At-risk-of-poverty threshold Single person (illustrative values) LVL per year EUR per year 2006 (EU-SILC 2007) (EU-SILC 2008) (EU-SILC 2009) (EU-SILC 2010) Two adults with two children younger than 14 years (illustrative values) LVL per year EUR per year 2006 (EU-SILC 2007) (EU-SILC 2008) (EU-SILC 2009) (EU-SILC 2010) Persistent at-risk-of-poverty rate in 2009 (EU-SILC 2010) to come Persistent at-risk-of-poverty rate: Total Persistent at-risk-of-poverty rate: Males Persistent at-risk-of-poverty rate: Females Persistent at-risk-of-poverty rate: 0-17 total Persistent at-risk-of-poverty rate: 0-17 males Persistent at-risk-of-poverty rate: 0-17 females Persistent at-risk-of-poverty rate: 18+ total Persistent at-risk-of-poverty rate: 18+ males Persistent at-risk-of-poverty rate: 18+ females Persistent at-risk-of-poverty rate: total Persistent at-risk-of-poverty rate: males Persistent at-risk-of-poverty rate: females Persistent at-risk-of-poverty rate: total Persistent at-risk-of-poverty rate: males Persistent at-risk-of-poverty rate: females Persistent at-risk-of-poverty rate: total Persistent at-risk-of-poverty rate: males Persistent at-risk-of-poverty rate: females Persistent at-risk-of-poverty rate: total Persistent at-risk-of-poverty rate: males Persistent at-risk-of-poverty rate: females Persistent at-risk-of-poverty rate: 65+ total Persistent at-risk-of-poverty rate: 65+ males Persistent at-risk-of-poverty rate: 65+ females 4

5 2. Accuracy 2.1. Sample Design In Latvia a stratified two-stage sampling design was used for the EU-SILC survey. At the first stage a systematic sampling of the primary sampling units (Population Census 2000 counting areas) was carried out. At the second stage a simple random sampling was made to select secondary sampling units (addresses). The stratification was made depending on a degree of urbanization of the area. The code of administrative territories was used for stratifying Type of sampling A stratified two-stage sampling was used for the EU-SILC survey in Latvia. A systematic sampling with inclusion probabilities proportional to the unit size was carried out at the first stage and a simple random sampling was carried out at the second stage Sampling units The Population Census counting areas were used as primary sampling units (PSUs) at the first stage. In general, all territory of Latvia is covered in lists of population counting areas. PSUs were selected by a systematic sampling with inclusion probabilities proportional to the population size (number of households) of PSUs. Addresses were used as secondary sampling units (SSUs). Simple random sampling was used to select SSUs from PSUs selected at the first sampling stage. In Latvia several households can be registered in one address. All households and individuals living in the selected address were included in the EU-SILC survey in urban areas, but in rural areas only those households, which were formed by persons enumerated in the Household List (see ). If none of persons enumerated in the Household List lived in the selected address, then it was possible: - to go for an interview to a different address in the same local area (if an interviewer knew the correct address of the persons enumerated in the Household List); - to interview all households and individuals living in the selected address (the same as in urban areas). 5

6 Stratification and sub-stratification criteria The stratification was made depending on a degree of urbanization of the area. Riga (the capital city), six largest towns, other towns and rural areas form four strata. The code of administrative territories was used for stratification. The stratum is identified in the variable DB Sample size and allocation criteria According to Regulation (EC) No 1553/2005 of the European Parliament and of the Council of 7 September 2005 amending Regulation (EC) No 1177/2003 concerning Community statistics on income and living conditions (EU-SILC), Annex II in Latvia the minimum effective sample size is households. The total gross sample size (number of households) was made according to the non-response rate and effective sample size for at-risk-of-poverty rate after social transfers. The non-response rate was estimated by using the results of the EU-SILC survey in the previous years. To compensate the non-response, it was decided to select 6550 addresses in 2007, in 2008, 7610 in 2009 and 8151 in Sample selections schemes In the first stage Population Census counting areas (PSUs) were selected by a systematic sampling with inclusion probabilities proportional to their population size. A simple random sampling without replacement was used to select addresses (SSUs) in sampled PSUs. A non-proportional allocation was used to select SSUs Sample distribution over time A sample distribution over time was not used because the EU-SILC survey is organized on an annual basis. Most interviews were conducted in the four month period from March to July. The number of households successfully interviewed in each month of fieldwork ( ) is shown below in Table

7 Table 2.1. Number of successful interviews (households of longitudinal component) by the date of interview Total Month number % number % number % number % number % February March April May June July August September October November Not specified TOTAL Renewal of sample: rotational groups A rotational sampling design was used for the EU-SILC survey. Latvia applies a rotational panel in which the sample is divided into four sub-samples. Each of them is representing the whole population. Each year one of the rotation groups is dropped out and a new one is added to the sample Weightings The longitudinal data sets contain information on individuals (and their households) traced from the original sample households in 2007, and 2010 (rotational groups 2, 3 and 4) Design factor Longitudinal weights were made from base weights RB060, which were calculated from design weights. The design weights (DB080) for dwellings were calculated according to the sample design: 1 DB080 ; prob_ dw hhpsupop psustrat adrpsus prob _ dw, hhstrpop adrpsup where prob_dw - inclusion probabilities of addresses; hhpsupop - a number of households in each strata s each PSU of all population; psustrat - a number of the PSUs in each strata of sample; dwpsus - a number of dwellings in each strata s each PSU of sample; 7

8 hhstrpop - a number of households in each strata of all population; dwpsup - a number of dwellings in each strata s each PSU of population. The inclusion probability of the household and the individual is equal to the inclusion probability of the address. The design weights were adjusted for outliers (extremely high design weights) at the address level Non-response adjustments Base weights were corrected by non-response in the primary sampling units. The and 2009 data were adjusted for returnees. New household members with RB110 = 3 (moved into from outside sample) and former household members with RB110 = 5, 6 or 7 (moved out, died, not registered in the previous wave and did not live in household anymore) had RB060 = 0. The newly born (household members with RB110 = 4) received the weight of their mother. For each year, each rotational group with adjusted design weights was calibrated on the corresponding year s population Adjustments to external data (level, variables used and sources) For each year, each rotational group with adjusted design weights was calibrated on the corresponding year s population. Weights were calibrated (in the household level) on the basis of demographic data by breaking them down by a degree of urbanization (four groups - strata), 12 age groups (0-15; 16-20; 21-25; 26-30; 31-35; 36-40; 41-45; 46-50; 51-55; 56-60; 61-65; 66+), sex and 6 regions of Latvia (NUTS 3). GREG calibration was used Final longitudinal weights Calibrated weights are base weights RB060. For each rotational group, for each wave, the sums of weights RB060 are equal to the size of the longitudinal population in the scope at each wave from the start of the panel. The longitudinal part of 2007 are the second rotational group, of the second and the third rotational groups, but for 2009 and 2010 the second, the third and the fourth rotational groups. Only they were selected for longitudinal weighting. So weights have a formula RB062 = k * RB060, where k is calculated as a proportion - number of households in the corresponding rotational group against the total number of households in all four longitudinal rotational groups. 8

9 Final household cross-sectional weight The final cross-sectional weights DB090 were calculated as a product of the design factor, non-response adjustment factor and calibration factor: DB 090 nonr _ w g, where g - g-weights of the regression estimator Substitutions No substitution was used Sampling errors The following tables report the mean, the number of observations (before and after imputation) and the standard error for different income components. Estimates and their standard errors were computed with cross-sectional weights DB090 9

10 Table 2.2. Mean, number of observations and standard errors of different income components, 2006 (EU-SILC 2007) Number of observations Income components Mean, LVL 1 Standard Before After errors, LVL 1 imputation imputation HY010 Total household gross income HY020 Total disposable household income HY022 Total disposable household income before social transfer other than old-age and survivor s benefits HY023 Total disposable household income before social transfers including old-age and survivor s benefits Net income components at the household level HY030N Imputed rent HY040N Income from rental of a property or land HY050N Family/Children related allowances HY060N Social exclusion not elsewhere classified HY070N Housing allowances HY080N Regular inter-household cash transfer received HY090N Interest, dividends, profit from capital investments in unincorporated business HY100N Interest repayments on mortgage HY110N Income received by people aged under HY120N Regular taxes on wealth HY130N Regular inter-household cash transfer paid HY140N Tax on income and social contributions Net income components at the personal level PY010N Employee cash or near cash income PY020N Non-Cash employee income PY021N Company car PY035N Contributions to individual private pension plans PY050N Cash benefits or losses from self-employment PY070N Value of goods produced for own consumption PY080N Pension from individual private plans PY090N Unemployment benefits PY100N Old-age benefits PY110N Survivor` benefits PY120N Sickness benefits PY130N Disability benefits PY140N Education-related allowances Zeros are not included in calculations. 10

11 Number of observations Income components Mean, LVL 1 Before After imputation imputation Standard error, LVL 1 Gross income components at the household level HY030G Imputed rent HY040G Income from rental of a property or land HY050G Family/Children related allowances HY060G Social exclusion not elsewhere classified HY070G Housing allowances HY080G Regular inter-household cash transfer received HY090G Interest, dividends, profit from capital investments in unincorporated business HY100G Interest repayments on mortgage HY110G Income received by people aged under HY120G Regular taxes on wealth HY130G Regular inter-household cash transfer paid HY140G Tax on income and social contributions Gross income components at the personal level PY010G Employee cash or near cash income PY020G Non-Cash employee income PY021G Company car PY030G Employer s social insurance contribution PY031G Optional employer s social insurance contribution PY035G Contributions to individual private pension plans PY050G Cash benefits or losses from self-employment PY070G Value of goods produced for own consumption PY080G Pension from individual private plans PY090G Unemployment benefits PY100G Old-age benefits PY110G Survivor` benefits PY120G Sickness benefits PY130G Disability benefits PY140G Education-related allowances Zeros are not included in calculations. 11

12 Table 2.3. Mean, number of observations and standard errors of different income components, 2007 (EU-SILC 2008) Number of observations Income components Mean, LVL 1 Standard Before After errors, LVL 1 imputation imputation HY010 Total household gross income HY020 Total disposable household income HY022 Total disposable household income before social transfer other than old-age and survivor s benefits HY023 Total disposable household income before social transfers including old-age and survivor s benefits Net income components at the household level HY030N Imputed rent HY040N Income from rental of a property or land HY050N Family/Children related allowances HY060N Social exclusion not elsewhere classified HY070N Housing allowances HY080N Regular inter-household cash transfer received HY090N Interest, dividends, profit from capital investments in unincorporated business HY100N Interest repayments on mortgage HY110N Income received by people aged under HY120N Regular taxes on wealth HY130N Regular inter-household cash transfer paid HY140N Tax on income and social contributions Net income components at the personal level PY010N Employee cash or near cash income PY020N Non-Cash employee income PY021N Company car PY035N Contributions to individual private pension plans PY050N Cash benefits or losses from self-employment PY070N Value of goods produced for own consumption PY080N Pension from individual private plans PY090N Unemployment benefits PY100N Old-age benefits PY110N Survivor` benefits PY120N Sickness benefits PY130N Disability benefits PY140N Education-related allowances Zeros are not included in calculations. 12

13 Number of observations Income components Mean, LVL 1 Before After imputation imputation Standard error, LVL 1 Gross income components at the household level HY030G Imputed rent HY040G Income from rental of a property or land HY050G Family/Children related allowances HY060G Social exclusion not elsewhere classified HY070G Housing allowances HY080G Regular inter-household cash transfer received HY090G Interest, dividends, profit from capital investments in unincorporated business HY100G Interest repayments on mortgage HY110G Income received by people aged under HY120G Regular taxes on wealth HY130G Regular inter-household cash transfer paid HY140G Tax on income and social contributions Gross income components at the personal level PY010G Employee cash or near cash income PY020G Non-Cash employee income PY021G Company car PY030G Employer s social insurance contribution PY031G Optional employer s social insurance contribution PY035G Contributions to individual private pension plans PY050G Cash benefits or losses from self-employment PY070G Value of goods produced for own consumption PY080G Pension from individual private plans PY090G Unemployment benefits PY100G Old-age benefits PY110G Survivor` benefits PY120G Sickness benefits PY130G Disability benefits PY140G Education-related allowances Zeros are not included in calculations. 13

14 Table 2.4. Mean, number of observations and standard errors of different income components, 2008 (EU-SILC 2009) Number of observations Income components Mean, LVL 1 Standard Before After errors, LVL 1 imputation imputation HY010 Total household gross income HY020 Total disposable household income HY022 Total disposable household income before social transfer other than old-age and survivor s benefits HY023 Total disposable household income before social transfers including old-age and survivor s benefits Net income components at the household level HY030N Imputed rent HY040N Income from rental of a property or land HY050N Family/Children related allowances HY060N Social exclusion not elsewhere classified HY070N Housing allowances HY080N Regular inter-household cash transfer received HY090N Interest, dividends, profit from capital investments in unincorporated business HY100N Interest repayments on mortgage HY110N Income received by people aged under HY120N Regular taxes on wealth HY130N Regular inter-household cash transfer paid HY140N Tax on income and social contributions Net income components at the personal level PY010N Employee cash or near cash income PY020N Non-Cash employee income PY021N Company car PY035N Contributions to individual private pension plans PY050N Cash benefits or losses from self-employment PY070N Value of goods produced for own consumption PY080N Pension from individual private plans PY090N Unemployment benefits PY100N Old-age benefits PY110N Survivor` benefits PY120N Sickness benefits PY130N Disability benefits PY140N Education-related allowances Zeros are not included in calculations. 14

15 Number of observations Income components Mean, LVL 1 Before After imputation imputation Standard error, LVL 1 Gross income components at the household level HY030G Imputed rent HY040G Income from rental of a property or land HY050G Family/Children related allowances HY060G Social exclusion not elsewhere classified HY070G Housing allowances HY080G Regular inter-household cash transfer received HY090G Interest, dividends, profit from capital investments in unincorporated business HY100G Interest repayments on mortgage HY110G Income received by people aged under HY120G Regular taxes on wealth HY130G Regular inter-household cash transfer paid HY140G Tax on income and social contributions Gross income components at the personal level PY010G Employee cash or near cash income PY020G Non-Cash employee income PY021G Company car PY030G Employer s social insurance contribution PY031G Optional employer s social insurance contribution PY035G Contributions to individual private pension plans PY050G Cash benefits or losses from self-employment PY070G Value of goods produced for own consumption PY080G Pension from individual private plans PY090G Unemployment benefits PY100G Old-age benefits PY110G Survivor` benefits PY120G Sickness benefits PY130G Disability benefits PY140G Education-related allowances Zeros are not included in calculations. 15

16 Table 2.5. Mean, number of observations and standard errors of different income components, 2009 (EU-SILC 2010) Number of observations Income components Mean, LVL 1 Standard Before After errors, LVL 1 imputation imputation HY010 Total household gross income HY020 Total disposable household income HY022 Total disposable household income before social transfer other than old-age and survivor s benefits HY023 Total disposable household income before social transfers including old-age and survivor s benefits Net income components at the household level HY030N Imputed rent HY040N Income from rental of a property or land HY050N Family/Children related allowances HY060N Social exclusion not elsewhere classified HY070N Housing allowances HY080N Regular inter-household cash transfer received HY090N Interest, dividends, profit from capital investments in unincorporated business HY100N Interest repayments on mortgage HY110N Income received by people aged under HY120N Regular taxes on wealth HY130N Regular inter-household cash transfer paid HY140N Tax on income and social contributions Net income components at the personal level PY010N Employee cash or near cash income PY020N Non-Cash employee income PY021N Company car PY035N Contributions to individual private pension plans PY050N Cash benefits or losses from self-employment PY070N Value of goods produced for own consumption PY080N Pension from individual private plans PY090N Unemployment benefits PY100N Old-age benefits PY110N Survivor` benefits PY120N Sickness benefits PY130N Disability benefits PY140N Education-related allowances Zeros are not included in calculations. 16

17 Number of observations Income components Mean, LVL 1 Before After imputation imputation Standard error, LVL 1 Gross income components at the household level HY030G Imputed rent HY040G Income from rental of a property or land HY050G Family/Children related allowances HY060G Social exclusion not elsewhere classified HY070G Housing allowances HY080G Regular inter-household cash transfer received HY090G Interest, dividends, profit from capital investments in unincorporated business HY100G Interest repayments on mortgage HY110G Income received by people aged under HY120G Regular taxes on wealth HY130G Regular inter-household cash transfer paid HY140G Tax on income and social contributions Gross income components at the personal level PY010G Employee cash or near cash income PY020G Non-Cash employee income PY021G Company car PY030G Employer s social insurance contribution PY031G Optional employer s social insurance contribution PY035G Contributions to individual private pension plans PY050G Cash benefits or losses from self-employment PY070G Value of goods produced for own consumption PY080G Pension from individual private plans PY090G Unemployment benefits PY100G Old-age benefits PY110G Survivor` benefits PY120G Sickness benefits PY130G Disability benefits PY140G Education-related allowances Zeros are not included in calculations. 17

18 Table 2.6. Mean, number of observations (before and after imputations) and standard errors of the equivalised disposable income 2006 (EU-SILC 2007), weighted Equivalised disposable income Mean, Number of observations Standard error, LVL Before imputation After imputation LVL By household size 1 household member household members household members and more household members By age groups < By sex Male Female Table 2.7. Mean, number of observations (before and after imputations) and the standard errors of the equivalised disposable income 2007 (EU-SILC 2008), weighted Equivalised disposable income Mean, Number of observations Standard error, LVL Before imputation After imputation LVL By household size 1 household member household members household members and more household members By age groups < By sex Male Female

19 Table 2.8. Mean, number of observations (before and after imputations) and the standard errors of the equivalised disposable income 2008 (EU-SILC 2009), weighted Equivalised disposable income Mean, Number of observations Standard error, LVL Before imputation After imputation LVL By household size 1 household member household members household members and more household members By age groups < By sex Male Female Table 2.9. Mean, number of observations (before and after imputations) and the standard errors of the equivalised disposable income 2009 (EU-SILC 2010), weighted Equivalised disposable income Mean, Number of observations Standard error, LVL Before imputation After imputation LVL By household size 1 household member household members household members and more household members By age groups < By sex Male Female Non-sampling errors Sampling frame and coverage errors Two sampling frames were built for each sampling stage. At the first stage counting areas from the list of the Population Census 2000 were used as a sampling frame. All territory of Latvia was divided in small areas (smaller than LAU 2) during the Population Census The list contained information about the number of households in each counting area. 19

20 At the second stage sampling frame was built from the Population Register, statistical register of dwellings and statistical register of households. The second stage sampling frame was built by using a copy of the Population Register. Both statistical registers of dwellings and households were updated by using the Population Register Measurement and processing errors The measurement errors can arise from the questionnaire (effects of the design, content and wording), from the data collection method (effects of the modes of interviewing), from interviewers (effects of the interviewer on the response to a question) and from respondents (effects of the respondent on the interpretation of items). As it was impossible to avoid such errors completely, several steps were taken by the CSB to reduce them as much as possible. Like as in the first EU-SILC (2005) operation 3 types of questionnaires were developed for the EU-SILC , 2009 and 2010 operations: the Household Register (to collect demographic information about all household members), the Household Questionnaire (to collect all information related to household dwelling costs, housing conditions, income components received at the household level etc.), the Personal Questionnaire (to collect all needed information for each household member aged 16 and over in the previous calendar year) and the Household List (an additional document to record all the necessary information about household members for tracing purposes and for linkage with data from administrative registers). The household members first, second names, contact addresses, phone numbers (fixed and mobile phone numbers) and personal identification codes were recorded in Household List. The Blaise CAPI (since 2006) and CATI (since 2008) applications as well as the paper questionnaires of the EU-SILC survey were available in Latvian and in Russian (the language of the largest ethnic minority in Latvia). Only households that were participating in the EU-SILC survey for the second, third or fourth time and had have specified phone numbers in the previous waves, were used for CATI. Not all, but the majority of households with phone numbers were used for CATI. It was possible for a household to refuse from CATI, and then CAPI was used. CAPI was used also in those cases when a telephone interview was not possible (the phone number was incorrect, the phone line damaged, the phone line busy, etc.). The CSB interviewers carried out the fieldworks of the EU-SILC operation. Prior to each operation an intensive training session for the field staff was organised. The aims of the training were to introduce the fieldwork stuff with methodology of the EU-SILC survey, to instruct interviewers for accurate fieldwork execution of the survey. Several tests (including a 20

21 practical interview to fill the EU-SILC questionnaires) were developed to check interviewers knowledge after the training session. To increase response rates several steps were made to introduce Latvian residents with the EU- SILC survey before starting the fieldwork. A press release was prepared to provide publicity of the EU-SILC survey. An introduction letter with a EU-SILC booklet were sent to selected addresses to establish the first contact with a household before the interview. Measurement errors were detected by analysing Interviewer s reports, by organizing discussions with interviewers after the fieldwork execution and by logical checks and verification of the received data. From 2006 onwards the treatment system of the EU-SILC data became less time consuming as it had been in It was related with the introduction of CAPI by using BLAISE software. It has to be noted that the year of 2006 was the first year when laptops were used in social surveys of the CSB and the EU-SILC was one of the first surveys where the CAPI system was used for carrying out the survey. Overall, the interviewers adopted computer skills very fast but in several cases they needed additional explanations about marking answers by using CAPI. Although laptops were given to all interviewers, a part of them made interviews by using paper questionnaires. This is still true also in a part of interviews were collected by means of paper questionnaires. Paper questionnaires were used when the laptop could not be used (for example, for security considerations, discharged battery, etc.). Completed paper questionnaires later were entered into laptop by the same interviewer, who had done the interview, and then transmitted to the CSB. A remarkable number of logical checks as well as a part of personal data from the previous year of the survey were introduced into the program. There were several factors, which might give the negative impact to the quality of the EU-SILC 2007 data: - the EU-SILC 2007 Questionnaires contain the largest number of questions than ever before. Questions about net income and about gross income were asked to respondents. It was done in that way because a possibility to use administrative data for making cross-sectional database of the EU-SILC 2007 before the fieldwork was unclear. - interviewers had a high workload; - the interviewers stuff was changing very frequently, there were problems to train newcomers; 21

22 - there was a chronic lack of interviewers, especially in Riga and neighboured areas; - interviewers were hesitating to use the opportunity to agree on the meeting time by phone; - the training of interviewers lost its effectiveness if the fieldwork lasted till autumn (in 2007 the training was carried out in the middle of February). The interviewers complained also about the length of the questionnaire covering too much information. Several advantages of using laptops were mentioned: easier interviewing, many mistakes were avoided, laptops increased the respect among respondents, interviewing with laptops was more prestige and also more convenient. Disadvantages of laptop usage were: recharging during the interviews was very difficult (respondents were not willing to allow recharging PC); it was heavy to carry laptops all the time. The quantity of personal data from the previous year of the survey introduced into the program from EU-SILC 2008 onwards had increased compared with EU-SILC For the first time information about respondent s name, surname, personal identification code, date of birth and sex were prefilled in the BLAISE data entry programme for the new rotational group if the respondent actually lived in the same address as specified in the Population Register. Data were transformed from BLAISE to MS ACCESS (a modified version of application of the previous year), where the initial database had been analysed and corrected. Data were compared with data from the previous EU-SILC operations, when it was possible. Compliance of the longitudinal data files with Eurostat requirements was checked with the SAS program. 22

23 Non-response errors Achieved sample size Table Sample size and accepted interviews 2007 Total DB075=2 DB075=3 DB075=4 DB075=1 Accepted household interviews Personal interview accepted: Number of persons 16 years and older Sample persons Co-residents Accepted household interviews Personal interview accepted: Number of persons 16 years and older Sample persons Co-residents Accepted household interviews Personal interview accepted: Number of persons 16 years and older Sample persons Co-residents Accepted household interviews Personal interview accepted: Number of persons 16 years and older Sample persons Co-residents

24 New households in wave Sample outcome in wave EU-SILC Final Quality Report Latvia Unit non-response Table Household response rate: Comparison of result codes between wave 2 and wave 1 (rotational group 2) Sample outcome in wave DB130=11 Total DB135=1 DB135=2 DB120=22 DB130=22 DB130=23 DB130=24 DB130=21 DB120=21 NC DB110=10 DB120=23 DB130=11 DB135= DB135= DB120=21 0 DB120=22 0 DB120=23 0 DB130=21 0 DB130=22 0 DB130=23 0 DB130=24 0 Total DB110= NA NA 0 9 DB110= NA NA Total Wave response rate = Refusal rate = Non-contact and others = Longitudinal follow-up rate = Follow-up ratio = Achieved sample size ratio =

25 New households in wave Sample outcome in wave EU-SILC Final Quality Report Latvia Table Household response rate: Comparison of result codes between wave 3 and wave 2 (rotational groups 2 and 3) Sample outcome in wave DB130=11 Total DB135=1 DB135=2 DB120=22 DB130=22 DB130=23 DB130=24 DB130=21 DB120=21 NC DB110=10 DB120=23 DB130=11 DB135= DB135= DB120= DB120= DB120= DB130= DB130= DB130= DB130= Total DB110= NA NA 1 32 DB110= NA NA Total Wave response rate = Refusal rate = Non-contact and others = Longitudinal follow-up rate = Follow-up ratio = Achieved sample size ratio =

26 New households in wave Sample outcome in wave EU-SILC Final Quality Report Latvia Table Household response rate: Comparison of result codes between wave 4 and wave 3 (rotational groups 2, 3 and 4) Sample outcome in wave DB130=11 Total DB135=1 DB135=2 DB120=22 DB130=22 DB130=23 DB130=24 DB130=21 DB120=21 NC DB110=10 DB120=23 DB130=11 DB135= DB135= DB120= DB120= DB120= DB130= DB130= DB130= DB130= Total DB110= NA NA 1 58 DB110= NA NA 0 0 Total Wave response rate = Refusal rate = Non-contact and others = Longitudinal follow-up rate = Follow-up ratio = Achieved sample size ratio =

27 Table Personal Interview outcome in wave (rotational group 2) RB250 = 11, 12, Not completed because of RB250=21 RB250=22 RB250=23 RB250=31 RB250=32 RB250=33 HHnc Pn Pl Sample persons forwarded from last wave [1] RB110 = [2] RB110 = 6 32 [3] RB110 = -1 0 [4] RB120 = 2 6 [5] RB120 = 3 14 [6] RB120 = 4 50 [7] DB135 = 2 or -1, or 382 DB120 = or -1, or DB130 = or 1 [8] DB110 = New sample persons [9] Reached age [10] Sample additions Non-sample persons 16+ [11] 2008 from Sample persons not forwarded from last wave (excluded died or not eligible according to tracing rules) [13] From SUM OF ROWS: Total Wave response rate of sample persons = Wave response rate of co-residents = - Longitudinal follow-up rate = Rate ( RB250=21 ) = Rate ( RB250=22 ) = - Rate ( RB250=23 ) = Rate ( RB250=31 ) = Rate ( RB250=32 ) = Rate ( RB250=33 ) = - Achieved sample size ratio for sample persons = - Achieved sample size ratio for sample persons and co-residents = - Achieved sample size for co-residents selected the first wave = - Response rate for non-sample persons = - 27

28 Table Personal Interview outcome in wave (rotational group 2 and 3) RB250 = 11, 12, Not completed because of RB250=21 RB250=22 RB250=23 RB250=31 RB250=32 RB250=33 HHnc Pn Pl Sample persons forwarded from last wave [1] RB110 = [2] RB110 = 6 71 [3] RB110 = -1 0 [4] RB120 = 2 4 [5] RB120 = 3 47 [6] RB120 = 4 74 [7] DB135 = 2 or -1, or 617 DB120 = or -1, or DB130 = or 1 [8] DB110 = New sample persons [9] Reached age [10] Sample additions Non-sample persons 16+ [11] 2009 from Sample persons not forwarded from last wave (excluded died or not eligible according to tracing rules) [13] From SUM OF ROWS: Total Wave response rate of sample persons = Wave response rate of co-residents = Longitudinal follow-up rate = Rate ( RB250=21 ) = - Rate ( RB250=22 ) = - Rate ( RB250=23 ) = - Rate ( RB250=31 ) = - Rate ( RB250=32 ) = - Rate ( RB250=33 ) = - Achieved sample size ratio for sample persons = Achieved sample size ratio for sample persons and co-residents = Achieved sample size for co-residents selected the first wave = - Response rate for non-sample persons =

29 Table Personal Interview outcome in wave (rotational groups 2, 3 and 4) RB250 = 11, 12, Not completed because of RB250=21 RB250=22 RB250=23 RB250=31 RB250=32 RB250=33 HHnc Pn Pl Sample persons forwarded from last wave [1] RB110 = [2] RB110 = [3] RB110 = -1 0 [4] RB120 = 2 9 [5] RB120 = [6] RB120 = [7] DB135 = 2 or -1, or 827 DB120 = or -1, or DB130 = or 1 [8] DB110 = New sample persons [9] Reached age [10] Sample additions Non-sample persons 16+ [11] 2010 from from Sample persons not forwarded from last wave (excluded died or not eligible according to tracing rules) [13] From SUM OF ROWS: Total Wave response rate of sample persons = Wave response rate of co-residents = Longitudinal follow-up rate = Rate ( RB250=21 ) = - Rate ( RB250=22 ) = - Rate ( RB250=23 ) = - Rate ( RB250=31 ) = - Rate ( RB250=32 ) = - Rate ( RB250=33 ) = - Achieved sample size ratio for sample persons = Achieved sample size ratio for sample persons and co-residents = Achieved sample size for co-residents selected the first wave = Response rate for non-sample persons =

30 Distribution of households by household status (DB110), by the record of contact at the address (DB120), by the household questionnaire result (DB130) and by the household interview acceptance (DB135) Table 2.17.Distribution of households by DB Total DB Total % Total % Total % Total % Table Distribution of households by DB Total DB Missing (-1) Total % Total % Total % Total % Table Distribution of households by DB Total DB Missing (-1) Total % Total % Total % Total % Table Distribution of households by DB Total DB Missing (-1) Total % Total % Total % Total %

31 Distribution of persons by membership status (RB110) Table Distribution of persons by membership status (RB110) Current household members No current household members Total RB110 RB120 = 2 to RB110 Missing (-1) Total % Total % Total % Total % Table Distribution of persons moving out by RB Total This person is a current household member of the household in this wave RB120 = 1 This person is not a current household member RB110 = 5 RB120 = 2 RB120 = 3 RB120 = 4 Total % Total % Total %