Household Income, Expenditure, and Consumption Survey, HIECS 2004/2005 - Egypt

Abstract --------------------------- THE CLEANED AND HARMONIZED VERSION OF THE SURVEY DATA PRODUCED AND PUBLISHED BY THE ECONOMIC RESEARCH FORUM REPRESENTS 100% OF THE ORIGINAL SURVEY DATA COLLECTED BY THE CENTRAL AGENCY FOR PUBLIC MOBILIZATION AND STATISTICS (CAPMAS) Income, Expenditure and Consumption Surveys assume a prime importance among all household surveys undertaken by the national statistical offices all over the world. On the basis of such surveys, the standard of living of both households and individuals can be measured. Determining poverty line and setting up a basis for social welfare assistance depend on these surveys. In addition, weights for consumer price index which in turn is an important measure of inflation are derived from such surveys. Egypt has recognized the greatest importance of these surveys long time ago, the current HIECS 2004/2005 is the eighth Household Income, Expenditure and Consumption Survey that was carried out in 2004/2005, on a sample of 48000 households, among a long series of similar surveys that started back in 1955, and followed by several surveys. The survey main objectives are: To identify expenditure levels and patterns of population as well as socio-economic and demographic differentials. To estimate the quantities, values of commodities and services consumed by households during the survey period to determine the levels of consumption and estimate the current demand which is an important input for national planning. Current and past demand estimates are utilized to predict future demands. To measure mean household and per-capita expenditure for various expenditure items along with socio-economic correlates. To define percentage distribution of expenditure for various items used in compiling consumer price indices which is considered important indicator for measuring inflation. To define mean household and per-capita income from different sources. To provide data necessary to measure standard of living for households and individuals. Poverty analysis and setting up a basis for social welfare assistance are highly dependent on the results of this survey. To provide essential data to measure elasticity which reflects the percentage change in expenditure for various commodity and service groups against the percentage change in total expenditure for the purpose of predicting the levels of expenditure and consumption for different commodity and service items in urban and rural areas. To provide data essential for comparing change in expenditure against change in income to measure income elasticity of expenditure. To study the relationships between demographic, geographical, housing characteristics of households and their income and expenditure for commodities and services. To provide data necessary for national accounts especially in compiling inputs and outputs tables. To identify consumers behavior changes among socio-economic groups in urban and rural areas. To identify per capita food consumption and its main components of calories, proteins and fats according to its sources and the levels of expenditure in both urban and rural areas. To identify the value of expenditure for food according to sources, either from household production or not, in addition to household expenditure for non food commodities and services. To identify distribution of households according to the possession of some appliances and equipments such as (cars, satellites, mobiles ...) in urban and rural areas. To identify the percentage distribution of income recipients according to some background variables such as housing conditions, size of household and characteristics of head of household. It is the first time that the Household Income, Expenditure and Consumption Survey implies the following issues: 1- The use of the classification of individual consumption according to purpose (COICOP) in designing the expenditure and consumption questionnaire. 2- The inclusion of the main sales outlets of food and beverages. 3- The addition of school enrollment (6+ years) to the household schedule. 4- The inclusion of expenditure for used commodities (durables and semi durables). 5- The addition of data related to change in assets owned by the household during the reference year. The raw survey data provided by the Statistical Agency were cleaned and harmonized by the Economic Research Forum, in the context of a major project that started in 2009. During which extensive efforts have been exerted to acquire, clean, harmonize, preserve and disseminate micro data of existing household surveys in several Arab countries. Geographic coverage --------------------------- Covering a sample of urban and rural areas in all the governorates. Analysis unit --------------------------- 1- Household/family. 2- Individual/person. Universe --------------------------- The survey covered a national sample of households and all individuals permanently residing in surveyed households. Kind of data --------------------------- Sample survey data [ssd] Sampling procedure --------------------------- THE CLEANED AND HARMONIZED VERSION OF THE SURVEY DATA PRODUCED AND PUBLISHED BY THE ECONOMIC RESEARCH FORUM REPRESENTS 100% OF THE ORIGINAL SURVEY DATA COLLECTED BY THE CENTRAL AGENCY FOR PUBLIC MOBILIZATION AND STATISTICS (CAPMAS) The sample of the Household Income, Expenditure and Consumption Survey (HIECS) of 2004/2005 is a multi-stage stratified cluster sample and self-weighted to the practical extent. Its designed size is 48000 households allocated among governorates and their urban/rural components in proportion to size. The sample was selected in three stages (the second stage is considered dummy), the first two stages is related to the Master Sample which has been drawn directly before the fieldwork of HIECS started. The third sampling stage concerns with the selection of a sample of 40 households from each Master Sample Areas (1200 areas with approximately 700 households in each). The Master Sample (1200 areas) has been allocated among the governorates of Egypt, with its urban/rural components, in proportion with the estimated size of households of every stratum (governorate) and substratum (urban/rural populations). At the first sampling stage, the shiakha in urban and village in rural are considered the smallest administrative divisions for which census data are available. Therefore such divisions were considered Primary Sampling Units (PSUs) for urban and rural samples of all governorates respectively. Small towns which are not further subdivided into smaller administrative units are dealt with as urban PSUs. While the larger shiakhas or towns were subdivided into several PSUs using the 1996 census data. At the contrary, a village with less than 600 households in 1996 (700 households at present) was joined to the adjacent village so as to make certain that all PSUs are greater than 600 households in 1996. Subsequently, the sampling frames of the first stage sample of urban/rural substrata for all governorates were formed. Implicit stratification was introduced to both urban and rural frames. At the second stage of sampling, a single area segment was selected following the equal probability selection method. A field operation has been carried out for the purpose of creating a household list for each selected second stage sample segment. In the third sampling stage representing the final stage, 40 households were selected from each area segment selected in the second sampling stage of the master sample. With the aim of reducing the field efforts it was deemed efficient to limit the spread of the household sample over the entire area segments by sampling clusters of 5 households each instead of sampling individual households directly. It is worth mentioning that the method of systematic selection will jeopardize the property of equal probability selection as each household in the list still has 40 chances of being selected in the sample. A more detailed description of the different sampling stages and allocation of sample across governorates is provided in the Methodology document available among the documentation materials published in both Arabic and English. Mode of data collection --------------------------- Face-to-face [f2f] Research instrument --------------------------- Three different questionnaires have been designed as following: 1- Expenditure and consumption questionnaire. 2- Diary questionnaire for expenditure and consumption. 3- Income questionnaire. In designing the questionnaires of expenditure, consumption and income, we were taking into our consideration the following: - Using the recent concepts and definitions of International Labor Organization approved in the International Convention of Labor Statisticians held in Geneva, 2003. - Using the recent Classification of Individual Consumption according to Purpose (COICOP). - Using more than one approach of expenditure measurement to serve many purposes of the survey. A brief description of each questionnaire is given next: 1- Expenditure and Consumption Questionnaire ---------------------------------------------------------- This questionnaire comprises 14 tables in addition to identification and geographic data of household on the cover page. The questionnaire is divided into two main sections. Section one: Household schedule and other information. It includes: - Demographic characteristics and basic data for all household individuals consisting of 16 questions for every person. - Members of household who are currently working abroad. - The household ration card. - The main outlets that provide food and beverage. - Domestic and foreign tourism. - The housing conditions including 15 questions. - Means of transportation used to go to work or school. - The household possession of appliances and means of transportation. - This section includes some questions which help to define the social and economic level of households which in turn, help interviewers to check the plausibility of expenditure, consumption and income data. Section two: Expenditure and consumption data It includes 14 tables as follows: - The quantity and value of food and beverages commodities actually consumed. - The quantity and value of the actual consumption of alcoholic beverages, tobacco and narcotics. - The quantity and value of the clothing and footwear. - The household expenditure for housing. - The household expenditure for furnishings, household equipment and routine maintenance of the house. - The household expenditure for health care services. - The household expenditure for transportation. - The household expenditure for communication. - The household expenditure for recreation and culture. - The household expenditure for education. - The household expenditure at restaurants and hotels. - The household expenditure for miscellaneous goods and services. - Transfer payments. - Total annual household expenditure (prepared in office) The tables from 1 to 13 include all types of commodities and services (746 Items), 47 Sub-group and 12 Main groups in addition to transfer payments. This questionnaire has been designed to be pre coded for all expenditure items and household characteristics except occupation and industry. Whenever relevant, the questionnaire provides spaces for different reference periods such as two weeks, monthly, quarterly and annually. The total number of items is 746 commodity and service comparing with 587 in the last survey. 2 - Diary Questionnaire ----------------------------- It has been prepared to help households recording - on a daily basis- the quantity and value of what have been consumed of food and beverages during the reference period (the survey month). The interviewers are instructed to check what households have recorded in the preceding three days. In case of the inability of some households to record their daily expenditure, the interviewer has to do so. The questionnaire includes: a- Letter addressed to the head of household to inform him/her about the importance of survey so that his/her cooperation may be stimulated. b- Instructions of data recording for households and interviewers. c- Twenty pages to record the daily consumed, quantity and value of food and beverages including date, source of commodities, quantity and value. d- Eight pages to record the value of expenditure for meals and tobacco outside the house, in addition to the value of expenditure for food prepared outside the house and consumed inside the house. e- Four pages to record the total of quantity and value of consumed food and beverages according to source, either from household production or not. f- Two pages to record total expenditure on food and beverages consumed outside home. 3- Income questionnaire ------------------------------- It includes household income data according to income sources. It consists of several tables; each is designated to a specific income source. These sources are: - Wages and salaries for wage/salary earners among household members. - Agriculture and non Agriculture projects. - Financial properties. - Non- financial properties. - Imputed rent of owner-occupied dwellings. - Received cash and in kind transfers A new table has been added for absent household members who spent a part of the survey year with the household and contributed in its aggregated income during that period. Absence of a household member can be for several reasons such as traveling, marriage, death, etc. Cleaning operations --------------------------- Raw Data ======= Office Editing: It is one of the main stages of the survey. It started as soon as the questionnaires were received from the field and accomplished by selected work groups. It includes: a- Editing of coverage and completeness b- Editing of consistency c- Arithmetic editing of quantities and values. Data Coding: Specialized staff has coded the data of industry, occupation and geographical identification. Data Processing and preparing final results It included machine data entry, data validation and tabulation and preparing final survey volumes. Harmonized Data ============ - The Statistical Package for Social Science (SPSS) is used to clean and harmonize the datasets. - The harmonization process starts with cleaning all raw data files received from the Statistical Agency. - Cleaned data files are then all merged to produce one data file on the individual level containing all variables subject to harmonization. - A country-specific program is generated for each dataset to generate/compute /recode/rename/format/label harmonized variables. - A post-harmonization cleaning process is then conducted on the data. - Harmonized data is saved on the household as well as the individual level, in SPSS and converted to STATA format. Response rate --------------------------- For the total sample, the response rate was 96.76% (94.58% in urban areas and 98.72% in rural areas). Response rates on the governorate level in urban and rural areas are presented in the methodology document attached to the documentation materials published in both Arabic and English. Sampling error estimates --------------------------- The sampling error of major survey estimates has been derived using the Ultimate Cluster Method as applied in the CENVAR Module of the Integrated Microcomputer Processing System (IMPS) Package. In addition to the estimate of sampling error, the output includes estimates of coefficient of variation, design effect (DEFF) and 95% confidence intervals. Tables A1 through A6 in the Methodology document attached to the documentation materials published in both Arabic and English present measures of sampling errors for major survey results. Data appraisal --------------------------- Quality Control Procedures: The precision of survey results depends to a large extent on how the survey has been prepared for. As such, it was deemed crucial to exert much effort and to take necessary actions towards rigorous preparation for the present survey. The preparatory activities, extended over a year, included forming Technical Committee from representatives of pertinent ministers and universities. They are ministry of planning, Faculty of Economic and Political Sciences and Cabinet in addition to the Central Agency of Public Mobilization and Statistics. The Committee has set up the general framework of survey implementation such as: 1- Applying the recent international recommendations of different concepts and definitions of income and expenditure considering maintaining the consistency with the previous surveys in order to compare and study the changes in pertinent indicators. 2- Evaluating the quality of data in all different Implementation stages to avoid or minimize errors to the lowest extent possible through: - Implementing field editing after finishing data collection for households in governorates to avoid any errors in suitable time. - Setting up a program for the Survey Technical Committee Members and survey staff for visiting field work in all governorates (each 15 days) to solve any problem in the proper time. - Re-interviewing a sample of households by Quality Control Department and examining the differences with the original responses. - For the purpose of quality assurance, tables were generated for each survey round where internal consistency checks were performed to study the plausibility of mean household expenditure on major expenditure commodity groups and its variability over major geographic regions. In addition, an external consistency checks were performed to study the reasonableness of changes in mean household expenditure, broken down by commodity group, since 1999/2000. To this end, corresponding tables have been extracted from the previous 1999/2000 survey.