ESS Standard for Quality Reports Structure (ESQRS)
National Statistical Institute
|Contact organisation unit|
Statistics on Living Conditions Department
|Contact person function|
|Contact mail address|
2, P. Volov Str.; 1038 Sofia, Bulgaria
|Contact email address|
|Contact phone number|
+359 2 9857 612
|Contact fax number|
The main objective of the household budget survey is to get reliable and scientifically founded data on the income, expenditure, consumption and other elements of the living standard of the population as well as changes which have occurred during the years.
Household income includes all receipts of the household and its members during the surveyed period. The income is estimate in total and monetary form. Monetary income includes regular receipts from: wages and salaries, other earnings, entrepreneurship, property, pensions, social benefits, regular inter-household transfers, as well as sale of property and other irregular receipts. Total income includes monetary and valued income in kind.
Household expenditure includes all resources spend by the household and its members during the surveyed period. The expenditures are estimated in total and monetary form. Monetary expenditure includes consumer expenditure on foods and non-alcoholic beverages; alcoholic beverages and tobacco; clothing and footwear; housing, water, electricity, gas and other fuels; furnishing and maintenance of the house; health; transport; communication; recreation, culture and education; miscellaneous goods and services; as well as taxes, social insurance, regular intro-household transfers and other non-consumer expenditure. Total expenditure includes monetary and valued expenditure in kind.
Variables of household incomes and expenditures are estimated average per household and per person and as structure.
Household consumption includes the quantities of main foods and beverages consumed at home. The catering data are not included. The variables are estimated by the household budget survey are calculated by balance method and are presented average per person.
Housing conditions variables are: type of dwelling, number of rooms, availability of water supply system, sewerage, electricity, bath and toilet.
Durables observed are: cars, TV sets, washing machines, refrigerators and freezers, telephones, computers, air-conditioners and others.
· Classification on household income;
· Classification of Individual Consumption by Purpose;
· International Standard Classification of Education (ISCED 2011);
· National Classification of Occupations and Duties-2011 (NCOD-2011);
· Classification of Economic Activities (CEA-2008, for international use NACE.BG-2008);
· Classification of territorial units for statistical purposes in Bulgaria (NUTS).
The Household Budget Survey is a sample survey by implementation of two stage cluster. The general population from which the sample for the survey is formed comprises all the households in the country. Institutional households are not studied by the household budget survey. The unit of observation is every randomly chosen ordinary household irrespective of the number of members and their material and personal status. The sample size since 2010 is 3060 households each quarter.
|Statistical concepts and definitions|
Gross household income is aggregated value of all regular incomes of the household and its members during the surveyed period from wages and salaries, other earnings, entrepreneurship, property, pensions, social benefits and regular inter-household transfers.
Net household income is calculated from gross income after deduction of tax and contribution to social insurance.
The consumer expenditure of a household includes the expenditure done by the household for satisfaction of the necessities of the household as a whole or some household members.
A private household consists of two or more persons living in a dwelling or part of dwelling and sharing common budget, having their meals together, no matter relatives or not.
One person living in a dwelling, separate room or part of room on his/her own budget also is considered a household.
Household (ordinary household).
The general population from which the sample is formed comprises all ordinary households in the country.
Institutional households are not studied by the HBS.
According to the Classification of territorial units for statistical purposes in Bulgaria (NUTS).
Up to 2009 (monthly and yearly data), since 2010 - quarterly and yearly data.
The general population from which the sample for the survey is formed comprises all the ordinary households in the country.
When forming the sample a two stage cluster’s sampling on a territorial principle is implemented as follows:
Up to 2009 the selection of territorial units is done with a probability proportional to their size. Since 2010 non-proportional selection has applied in order to produce more accurate sample data in the small regions where the minimum quarter size of the sample include no less 72 households at the expense of decrease of the number of households in the large regions - Sofia (stolitsa), Plovdiv and Varna.
In the selected enumeration areas (clusters) lists of the household are prepared and they are arranged into ascending order, depending on the number of persons. This indicator has a close correlation with the surveyed indicators - income, expenditure, and consumption per capita. 6 households from these lists are chosen from each cluster with a selection step.
Since 2010 the sample size has been 3 060 households divided in three sub-samples each containing 1 020 households. Each sub-sample is surveyed one month per quarter by application of the method of rotation sample. Each household participates in the survey four months during the 12-month period.
The household budget survey applies the principle of the voluntary participation of households which had randomly come into the sample. Every randomly selected household which is not willing or is not able to cooperate is replaced with another from the same cluster and with the same number of members.
Main documents of the Household budget survey are:
|Frequency of data collection|
Monthly (to 2009), quarterly (since 2010)
Data collection methods
· method of writing down the data by one of the members of the observed household
· method of the interview between the interviewer and the members of the household.
The surveyed households keep a regular record in the Household Diary on:
· total daily monetary expenditure per month for food products, non-food products, services and others;
· all monetary incomes from working salary, social insurance, home production and others;
· supply in kind and use of food products and non-food goods;
· manufactured raw materials and products obtained from the processing;
· number of people who had meals.
Since 2010 the households have kept retrospective records on:
· irregular expenditure on non-foods during the previous two months;
· some irregular income during the previous two months.
By interview data are collected on:
· social demographic characteristics of the household and its members
· availability of facilities and durables at the dwelling
· availability of food products at the beginning of the month of observation and residues at the end of the month
· the presence of farm animals in the household.
The interviewers visit the household several times a month. During these visits they have a detailed conversation with the members of the household, check the completeness and reliability of the data entered into the diary.
In the process of entering information, logical control of the received information is performed.
Data processing is done with specially developed software for the research.
The information from the household budget survey is processed monthly at the Statistical Survey Departments of NSI regional offices and NSI and is summarized quarterly and annually in the NSI. Monthly control tables, quarterly, and annual estimates are obtained.
Monthly processing includes:
• input and control of collected data for each household observed during the month;
• summarizing the data for the individual household from the different input documents and forming an individual household budget;
• data control for the individual household budgets;
• applying methodologies for calculating additional result variables:
• obtaining tables with control monthly assessments of the main indicators for the survey;
Quarterly processing includes:
• aggregation of monthly data; • applying methodologies for assessing individual household data for the two months during which they were not directly observed; • obtaining tables with quarterly estimates of the main indicators for the survey; • calculation of stochastic errors in quarterly assessments.
Annual processing includes:
• aggregation of quarterly data;
• applying methodologies to add retrospective data for the months when households are not directly observed;
• obtaining tables with final quarterly estimates of the main indicators for the survey;
• obtaining tables with annual estimates of the main indicators for the survey.
Through checking on field work and control of the thoroughness of the records in the diaries.
Data are accompanied with quality reports analyzing the accuracy, coherence and comparability of the data.
The data is of interest to a wide number of users - state authorities, public and international organizations (Eurostat, UN, UNICEF, ILO, etc), students and others.
Consultations with users:
|Data completeness - rate|
|Accuracy and reliability|
As with any other sample survey, HBS may be burdened with errors due to sampling and other relating to the inability to be interviewed some of the units in the sample, as well as the errors taking place at the stage of data recording, data processing, etc.
The sampling errors calculated for main variables are published in annual publication "Household Budgets in the Republic of Bulgaria".
|Sampling errors - indicators|
Like any statistical survey and household budget survey may contain non-sampling errors that arise at different stages of the study and which cannot be completely eliminated.
Such errors are basically:
· coverage errors
· measurement errors that occur at the time of data collection
· processing errors
· non-response errors
In order to reduce non-sampling errors:
· update of the household lists for each of the first stage selection census enumeration areas;
· development of a clear research methodology, ongoing updating of data coding systems;
· using interviewers with experience in collecting, controlling, encoding and inputting data;
· conducting regular training seminars for the interviewers;
· assistance to the interviewers of the survey team at NSI;
· data control at the collection, input, and processing stage.
Some of the sampled households cannot be found at the address. In order to preserve the sample size, the principle of substitution applies to these households.
Replaced households not contacted in 2020
|Over-coverage - rate|
|Common units - proportion|
At the data collection stage, errors may also occur:
· inaccurate or incomplete answers from respondents - to minimize these errors, interviewers check the correctness and completeness of the records by asking additional reminders;
· improperly recorded data from the interviewers - a large number of arithmetic and logic controls have been introduced in the processing programs to limit this type of error.
|Non response error|
Some of the households in the sample do not want or cannot participate in the survey for a variety of reasons:
· skepticism in respect of the survey objectives
· skepticism in respect of the official institutions
· suspicion in preserving anonymity
· insufficient remuneration for participation
· lack of time
· other reasons for refusal
· poor health
· lack of communication with the household because of misunderstanding and non-communication in Bulgarian
· other reasons
To reduce the negative impact on estimates of non-response, the household budget survey uses the substitution principle.Every randomly selected household which is not willing or is not able to cooperate is replaced with another from the same cluster and with the same number of members.
|Unit non-response - rate|
|Item non-response - rate|
In order to minimize possible errors, a large number of arithmetic and logical controls are included in the programs for input and processing of household budget survey data. For example:
- For the items of the monetary expenses for which they are registered quantities and values, upon data entry automatically is calculated price and it is checked whether the price is within minimum and maximum price limits.
- Ownership of the dwelling is tied to the payment or not of rent for a dwelling, and the availability of central heating - respectively the paid bills for heating.
- A logical link is established between the registered economic activity of the person and the corresponding type of income received by him as salary, pension, compensation etc.
- Completed or ongoing education is tied to the age of the person.
- The presence of farm animals of a given species is associated with the products derived therefrom such as milk, eggs, meat, honey, wool.
All arithmetic and logical controls are detailed in the study's terms of reference.
|Imputation - rate|
|Model assumption error|
|Data revision - policy|
|Data revision - practice|
|Data revision - average size|
|Timeliness and punctuality|
Quarterly data are published 45 days after the reference period.
Annual data are published in April of the year following the reference year.
|Time lag - first results|
First annual results are available 4 months after the end of the surveyed year.
|Time lag - final results|
Final results are available 12 months after the end of the surveyed year.
The deadlines are observed: for quarterly data - 45 days after the reporting period, and for the annual ones - four months after the accounting year.
|Punctuality - delivery and publication|
|Coherence and comparability|
|Comparability - geographical|
|Asymmetry for mirror flows statistics - coefficient|
|Comparability - over time|
Long time series.
|Length of comparable time series|
|Coherence - cross domain|
Household budget survey is consistent with Consumer Price Index, Purchasing Power Parity and National Accounts. Additional analyzes are carried out to ensure consistency with the survey on income and living conditions.
|Coherence - sub annual and annual statistics|
|Coherence - National Accounts|
The structure of consumer expenditures from household budget survey for the 12 major COICOP classification groups is compared with a similar structure, calculated from a National Accounts database.
|Coherence - internal|
|Accessibility and clarity|
Household income, expenditure and consumption - quarterly and yearly.
· Publication "Household Budgets in the Republic of Bulgaria" - detailed annual data for different household groups (by place of residence, by number of household members, by number of employed persons, by number of children under 18, by total annual income per person in the household, by presence of pensioners, by professional and economic status of the household head, by decile groups);
· Publication "Average prices and purchased quantities of main foods and non-foods by households" - contains data on the average prices and purchased quantities foods and non-foods by households by years and by quarters. The information from the survey of household budgets is used and because of that these average prices differ from the consumer prices published by the NSI. The purchased quantities foods are computed average per household and the purchased non-foods - average per 100 households. Published are also data on the purchasing power of households calculated by means of total and monetary income, as well as the changes in the purchasing power.
· Booklet "Household Budget Survey";
· General Publications of the NSI.
Detailed results on Household Budgets are available to all users of the NSI website under the heading Households Income, Expenditure and Consumption: https://www.nsi.bg/en/node/5640
and in the INFOSTAT Information system: https://infostat.nsi.bg/infostat/pages/module.jsf?x_2=27.
|Data tables - consultations|
Anonymised individual data can be provide for scientific and research purposes, and for individual request according to the Rules for the provision of anonymised individual data for scientific and research purposes.
Information service on request, according to the Rules for the dissemination of statistical products and services in NSI.
|Metadata - consultations|
|Documentation on methodology|
· Methodology and organisation of the household budgets survey:
· Instruction for interviewers of Household budget survey.
|Metadata completeness – rate|
Eurostat's quality reports of the Household Budget Survey in EU countries, 2005, 2010 and 2015.
|Cost and burden|
Every household receive 20 BGN per month of participation. It take part in the survey 4 months per year, average 2-3 hour per month.
|Confidentiality - policy|
· Law on Statistics;
· Regulation (EC) No 223/2009 on European statistics (recital 24 and Article 20(4)) of 11 March 2009 (OJ L 87, p. 164), stipulates the need to establish common principles and guidelines ensuring the confidentiality of data used for the production of European statistics and the access to those confidential data with due account for technical developments and the requirements of users in a democratic society.
|Confidentiality – data treatment|
Individual data are not published in accordance with article 25 of the Law on Statistics. The publishing of individual data can be performed only in accordance with article 26 of the same law.