The goal of Estonian Social Survey (ESS) is to measure the income and living conditions of Estonians, and based on this data to evaluate the problematic areas of the society - poverty, inequality and social exclusion. The survey offers a possibility to measure such complex social processes as persistent poverty and the various levels of deprivation. In Estonia, ESS is the official source of income statistics and social exclusion indicators.
ESS is the Estonian branch of a pan-European survey of income and living conditions called the EU-SILC (European Union (EU) Statistics on Income and Living Conditions) coordinated by Eurostat. Statistics Estonia collects data within the framework of EU-SILC, domestically called the Estonian Social Survey. The EU-SILC survey is carried out based on a common methodology in all EU countries and in Iceland, Norway, Switzerland and Turkey, allowing for the publication of internationally comparable statistics on poverty, inequality and income. In addition to the input for Eurostat's variables, many questions from Estonian domestic consumers are included in ESS. Estonian domestic databases are also compiled based on the results of this survey and are every year delivered to domestic contractual users. The ESS data is used by Estonian educational institutions (universities, institutes) and ministries (mainly the Ministry of Social Affairs).
ESS is the first and currently the only panel survey in Estonia. Two kinds of databases are compiled from the survey results. The data from one given survey year is assembled in cross-sectional files, which provide a look into the incomes earned and the living conditions of the residents of Estonia in that year. Several years' data is compiled into longitudinal files which can be used to study changes occurring in the society at the level of the same sample households.
The cross-sectional data for 2012 is documented here.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
The scope of the Estonian Social Survey includes:
- Demographic characteristics of household members
- Schools and day care attendance
- Consumer durables
- Social benefits
- Production of agricultural products for own consumption
- Health and accessibility of medical care
- Height and weight
The survey covers the whole population of Estonia
Producers and sponsors
Statistical Office of the European Communities Eurostat
ESS has been designed as a longitudinal sample survey using sample design with sub-samples or panels independent of one another. Every new panel is taken from the sampling frame by stratified systematic sampling, consequently being probability sample.
The minimum effective sample sizes to be achieved have been defined by Eurostat for all Member States for the evaluation of both cross-sectional component (status quo) and longitudinal changes (which have taken place over time). In the sample size designation process, the previous non-response rate, survey design and other factors determining the quality of evaluations have been taken into consideration. For Estonia, the minimum effective sample size to be achieved is:
- 3,500 households and 7,750 persons aged 16 or over to be interviewed for cross-sectional analysis, i.e. for the evaluation of status quo;
- 2,750 households and 5,750 persons aged 16 or over to be interviewed for longitudinal analysis, i.e. for the evaluation of changes that have taken place over time.
The actual planned sample size is greater than indicated above in order to take into account the impact of various factors that may reduce the precision of evaluation.
In order to calculate the population parameter estimations on the basis of survey data, a weight should be assigned to every object of the sample i.e. it should be indicated how many elements of the population the object represents in the sample. For ESS, both persons and households are weighted. Weights are calculated both for cross-sectional and longitudinal data. The sub-samples or panels are weighted independently and combined thereafter. The used weighting is governed by the procedures worked out for EU-SILC.
The weights are calculated on the basis of design weights derived from inclusion probabilities. The weights, which are first adjusted to compensate for the bias caused by non-response, and then calibrated to the population data, are used in calculating the final data. In the first years of the survey, post-stratification was used to compensate for nonresponse.
Dates of Data Collection
Data Collection Mode
Data Collection Notes
All sample households included in the survey by sampling are interviewed in four consecutive years. Each year, almost a thousand new households are brought into the survey. Around the same number finish their four years’ participation in the survey and they drop out. These so-called "waves" are called panels in ESS — a finishing panel is always replaced by a new panel i.e. a new sub-sample, while the old sub-sample finishes their time. Each year, around 5,500 households and 13,500 persons are interviewed, and they are divided between four panels. Three panels are in the survey from the previous years and one is a first-timer.
The survey is comprised of the household and personal interviews, conducted by using two different questionnaires: the household questionnaire and the personal questionnaire. The household interview is carried out with a grown-up household member who knows the household the best. Personal questionnaires are filled out for all household members aged 15 or more.
The dataset was published as a Public Use File at Statistics Estonia website - http://www.stat.ee/51930
Use of the dataset must be acknowledged using a citation which would include:
- the Identification of the Primary Investigator
- the title of the survey (including country, acronym and year of implementation)
- the survey reference number
- the source and date of download
Statistics Estonia. Estonian Social Survey 2012, Cross-Sectional Database. Ref. EST_2012_ESS-C_v01_M. Dataset downloaded from [URL] on [date].
Disclaimer and copyrights
The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.