This report presents the findings of 2000-2001 Tanzania Household Budget Survey(HBS).It focuses on poverty- monitoring indicators and offers a set of baseline mesurements for the future.Data on key poverty indicators are presented for each region. Trends over the 1990s are also assessed by comparison with the 1991/92 HBS.
The HBS collected information on a range of individual and household characteristics. These included;
*household members, education,economic activities, and health status
*household expenditure, consumption and income
*ownership of consumer goods and assets
*housing structure and materials
*household access to services and facilities, and
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Individuals and households,
Economic,condition and indicators
Income/propety and investiment/savings
Rural economics/general health/housing
Basic skills education
land use and planning [10.2]
Unit of Analysis
Individuals and households,
The survey covered all de jure household members
Producers and sponsors
MINISTRY OFS TATE PRESIDENT,S OFFICE PLANNING AND PRIVATISATION
Professor Joseph Semboja
Arthur van Diesen
Proffesor. Beno Ndulu
SWEDEN INTERNATIONAL DEVELOPEMENT AGENCY
CANADA INTERNATIONAL DEVELOPEMENT AGENCY
JAPAN INTERNATIONAL DEVELOPEMENT AGENCY
DANISH INTERNATIONAL DEVELOPEMENT AGENCY
United Kingdom Department for International Developement
United Nation Developement Program
TANZANIA,S POVERTY REDUCTION STRATEGY
UNIVESITY OF DAR-ES-SALAAM
OXFORD POLICY MANAGEMENT
PATRICK WARD,TRUDY OWENS
The sample of households interviewed in the 2000/2001 HBS was selected in two stage.In the first stage 1,161 small areas called Primary Sampling Units (PSUs) were selected throughout the country.In the second stage. 24 households were initialy selected in each PSU.
The sampled households are located in the National Master Sample (NMS) of PSUs. The NMS is a generalised set of area units that can be used as PSUs for conducting various household surveys. It is a fixed sample of rural and urban clusters, which among other things, make possible the performance of a continuous survey programme as well as ad hoc sample surveys. the NMS has four modules, A,A+B,A+B+C and A+B+C+D, which can provide urban and rural estimates at National, Zonal, Regional and District levels respectively.
The HBS 2000/01 used Module A+B+C of the NMS comprising 621 urban EAS and 540 rural villages drawn from each of the 20 regions of Mainland Tanzania. In the second stage,24 households were selected using systematic random sampling(SRS) from stratified lists of households complied from each of the sampled PSUs. These lists were stratified into high, middle and low socio-economic groups based on socio-economic data collected during the listing exercise. The stratification and selection of households was conducted in the NBS head office and interviewers were supplied with a list of pre-selected households for interview,
RURAL frame.The initial rural NMS frame was based on the 1978 Population Census and later updated with information from the 1988 Population Census.At the beginning, a ward or group of wards was used as Primary Sampling Unit (PSU), but later a village was used insted. The rural frame of the NMS was divided into :normal: large town surroundings; and Low density; strata. In total.150 strata were created and 2 to 8 PSUs (villages) were selected from each stratum to come up with the samp;e of villages that can provide estimates for each region of Mainland Tanzania (Module A+B+C).These villages were selected using the probability proportional to size (PPS) selection procedure. The PSUs (villages) for Module A of the rural NMS are automatically included in the regional sample.
URBAN frame: The urban frame for the NMS was the sample used for 1988 Population Census detailed questionnaire. For each district in a region, a list of the urban EAs was compiled and a specific number of EAs was selected from this frame using the systematic random sampling(SRS) procedure to produce the regional urban sample.
Deviations from the Sample Design
The final sample analysed for the 2000/01 HBS consisted of 22,178 households, a large sample for any household budget survey. Three PSUs were lost entirely from the sample. Households were included in the analysis if they had at least one record in both the roster and the monthly diary. The weights were calculated for this group of household.
Field supervisors were supplied with a list of twelve :replacement: households drawn as a separate sample at the same time as the main household sample, to be used if a sampled household could not be interviewed for the duration of the survey. The 2000/01 HBS sample had a high level of replacement of households that were not interviewed-around12 per cent.
A total of 4,823 households were analysed for the 1991/92 sample. Losses were higher; levels of replacement were lower (Table A1.2). In both surveys, households that were part of the initial selectionons constitute around 85 per cent of the sample analysed.
The 2000/01 HBS inteviewed 98 per cent of the (revised) intended sample size. It did so by relatively frequent use of replacement households, selected from a list provided by the head office. Almost 12 per cent of households included in the final analysis were replacements. The 1991/92 HBS Suffered higher levels of losses but used smaller proportion of replacements.The use of replacements is not usually considered good practice in sampling, since it runs the risk of estimates being biased by replacement with non comparable households.However,it was considered necessary because of the large sample size and demanding character of the data collection process.
DAR-ES-SALAM.First stage sampling weights for Dar-es-salaam are those used for Module A because the PSUs are the same. The EAs from the 1988 Census sample were srtatified into proxy income levels and combined for all districts within the Dar-es-salaam region. They were then selected independently within each level using the SRS procedure. Details on how these weights were calculated are found in ;the National Master Sample (NMS)-Technical Report; (cited above) The formula for calculating the weights is;
Whk= First stage weight for an EA in stratum k of cluster h
VhJAhk=the proportion of the sample that falls into districts h to the selection interval
Nh=number of EAs in district h
nh=number of sampled EAs in district h
Ahk=number of EAs in district h and NMS stratum k
ak=number of sample EAs in NMS stratum k
When the multiple of the selection interval is completely within stratum k of district h, the proportion Vh/Ahk becomes I.
Other Urban. For other urban areas,a sample of about 30 EAs was targeted for each region contributed a certain porportion of the 30 EAs.The EAs were then selected independently from each district in the region using the SRS procedure. EAs. representing municipalities and other urban areas in Moduke A of the NMS were automatically included in the regional sample. The formula for calculating the weights for an EA in district j of region i is given by;
Wij=First stage weight for a selected EA in district j of region i
Tij=total number of urban EAs in district j of region i
Cij=number of selected urban EAs for the census sample in district j of region i
Sij=number of selected urban EAs for the NMS (Module A+B+C) in district j of region i
Rural.The rural NMS (Module A+B+C)has been used by a number of previous agricultural surveys. The first stage selection of PSUs was done using the PPS sampling procedure. The formula for the first stage weights is as follows;
Wij=first stage weight for a selected village j from stratum i
ni=number of villages selected from stratum i
Pi=1998 population of stratum i
pij=1998 population of village j from stratum i
Dates of Data Collection (YYYY/MM/DD)
Time periods (YYYY/MM/DD)
Mode of data collection
The National Bureau of Statistics began preparations for the 2000-2001 Household Badget Survey in late 1999 and training of the fieldworkers took place in March 2000. Fieldwork began in May 2000 for ten regions and in June 2000 for the remaining ten. It lasted for twelve months in each region, with all fieldwork being completed by June2001.The2000/01 sample was much larger than previous Household Budget Survey in order to provide estimates of key poverty measures fo each of twenty regions of Tanzania mainland.It initially covered 1,161 small geographical areas. these were used as primary sampling units(PSUs).If fully implemented, a total of 27,864 households would have been interviewed. However,it was decided during implementation that a number of rural PSUs would be excluded from second six months of the survey as a cost saving mesure.The anticipated final sample then become 22,584 households. Two household were enumerated each month of the survey in each PSU.Enumerators, resident in or near the PSU. conducted an initial interview with the two households at the beginning of the survey month. They then visited the households during that month on regular basis to record household transactions, covering expenditure, consumption and income. These visits were scheduled to take place every day for households without a literate member and every two to three days for others.Enumerators were supervised by field supervisors working out of the NBS regional offices. Supervisors collected and cheked questionnaires, which were then sent to the head office for data entry. Data entry, using the data programme IMPS, went parallel with fieldwork and was completed by July2001. Automated data consistency checking procedures were run on the entered data during fieldwork.The field staff were informed of the errors identified by these programmes and ,where possible,a team in the head office corrected them.Additional consistency checks and cleaning continued until November2001 and the analysis was completed by June2002.
Type of Research Instrument
The questionnaires contain information related to;Household Particulars, Household Facilities, Household Assets, Household Income, Distance to socio-Economic Facilities, Purchase of Durable items and other Services,Food security;
NATIONAL BUREAU OF STATISTICS
MINISTRY OFSTATE PRESIDENT,S OFFICE PLANNING AND PRIVATISATION
A number of data consistency cheks were undertaken early in the fieldwork to assess quality and to assist in the development of the data processing system.These identified a large number of problems in the data coming in from the field, which reflected in part the ambitious size of the survey.The errors identified included consumption unit miscoding,miscoding of transactions, out of range unit prices and problems in the identifier variables. As a consequence, automatic consistency cheking programmes were strengthened and a data editing team was created. where possible,errors were corrected at the data processing centre and the field teams were notified of the problems. This resolved a large number of problems.
NATIONAL BUREAU OF STATISTICS
MINISTRY OF STATE PRESIDENT,S OFFICE PLANNING AND PRIVATISATION
Tanzania NBS considered three levels of accessibility:
1) Public use files, accessible by all
2) Licensed datasets, accessible under certain conditions
3) Datasets only accessible on location, for certain datasets
The dataset has been anonymized and available as a public use dataset. It accessible to all for statistical and research purposes only, under the following terms and conditions:
1.The data and other material will not be redistributed or sold to other individuals, institutions, or organization without the written agreement of the National Bureau of Statistics.
2.The data will be used for statistical and scientific research purposes only. They will be used solely for reporting of aggregated information, and not for investigation of specific individuals or organizations.
3.No attempt will be made to produce links among dataset provided by the National Bureau of Statistics, or among data from the (National Bureau of Statistics) and other datasets that could identify individuals or organizations
4.No attempt will be made to re-identify respondents, and no use will be made of the identify of any person or establishment discovered inadvertently. Any such discovery would immediately be reported to the National Bureau of Statistics.
5.Any books, articles, conference papers, theses, dissertations, reports, or other publications that employ data obtained from the National Bureau of Statistics will cite the source of data in accordance with the Citation Requirement provided with each dataset.
"NATIONAL BUREAU OF STATISTICS, HOUSEHOLD BUDGET SURVEY 2000-2001(HBS 2000-2001) VERSION 1.0 OF THE PUBLIC USE DATASET(JULY2002) PROVIDED BY NATIONAL BUREAU OF STATISTICS, www.nbs.go.tz"
Disclaimer and copyrights
The user of the data acknowledges that National Bureau of Statistics is the origional collector of thedata.the authorized distributor of the data.and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences without a written agreement from the National Bureau of statistics.
@ 2010 NATIONAL BUREAU OF STATISTICS
National Bureau of Statistics
NATIONAL BUREAU OF STATISTICS
MINISTRY OF STATE PRESIDENTS OFFICE PLANNING AND PRIVATISATION