Household Budget Survey 2009/2010
Zanzibar, Tanzania, 2009 - 2010
Get Microdata
Reference ID
TZA-2009-HBS-V01-M
Producer(s)
The Office of Chief of Goverment Statistician
Metadata
Created on
Nov 16, 2023
Last modified
Dec 09, 2023
Page views
989
Downloads
3
Identification
Survey ID Number
TZA-2009-HBS-V01-M
Title
Household Budget Survey 2009/2010
Translated Title
English
Country
| Name | Country code |
|---|---|
| Zanzibar, Tanzania | TZA |
Study type
Income/Expenditure/Household Survey [hh/ies]
Series Information
The 2009/10 Household survey is a fourth post revolutionary survey of its kind to be conducted in Zanzibar. The previous surveys conducted were 2004/05 HBS, 1991/92 HBS and 1981/82 HBS. The Survey provides poverty-monitoring indicators which will be used to track changes over time. The survey compared the indicators to those derived in the 2004/05 HBS. The survey studied income, expenditure, consumption patterns and other socio-economic characteristics
of private households.
of private households.
Abstract
The 2009/10 Household Budget Survey (2009/10 HBS) is the fourth in a series of such surveys conducted by the Office o Chief Government Statistician (OCGS), Zanzibar. The last in the series of those surveys was conducted in 2004/05. This
publication presents the findings of 2009/10 HBS; and whenever possible compares the results with those of the 2004/05 HBS.`The 2009/10 HBS is based of a nationally representative sample of 4,296 households, selected from 179 enumeration
areas. While this sample is sufficiently large to allow many indicators to be reported at the district level, the 2004/05 HBS used about twice the sample size opted in 2009/10 HBS, the former may be said to have collected more precise
estimates. The smaller sample and some possible differences in the compostion of the samples call for caution in theinterpretation of some of the trends between the two surveys.
publication presents the findings of 2009/10 HBS; and whenever possible compares the results with those of the 2004/05 HBS.`The 2009/10 HBS is based of a nationally representative sample of 4,296 households, selected from 179 enumeration
areas. While this sample is sufficiently large to allow many indicators to be reported at the district level, the 2004/05 HBS used about twice the sample size opted in 2009/10 HBS, the former may be said to have collected more precise
estimates. The smaller sample and some possible differences in the compostion of the samples call for caution in theinterpretation of some of the trends between the two surveys.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Individual and household
Version
Version Description
- v2.1: Edited, anonymous dataset for public distribution.
Version Date
2010-10-14
Scope
Notes
The 2009/10 Household Budget Survey measures changes in a number of important indicators for poverty monitoring and evaluation. It collected information on:-
Basic information on household members including age, sex and marital status, education, economic activity and health
- Housing Particulars
- Distances to Socio- Economic and other facilities
- Household Assets
- Food security
- Annual household income
- Household expenditure consumption
- Household business
Basic information on household members including age, sex and marital status, education, economic activity and health
- Housing Particulars
- Distances to Socio- Economic and other facilities
- Household Assets
- Food security
- Annual household income
- Household expenditure consumption
- Household business
Coverage
Geographic Coverage
Zanzibar
Urban and Rural
Region and Ditrict
Urban and Rural
Region and Ditrict
Universe
The survey covered
Private household
usual members residing in the households
expenditure of all household member 5+ years
Private household
usual members residing in the households
expenditure of all household member 5+ years
Producers and sponsors
Primary investigators
| Name | Affiliation |
|---|---|
| The Office of Chief of Goverment Statistician | OCGS |
Producers
| Name | Affiliation | Role |
|---|---|---|
| University of Dar es Salaam | Ministry of Education and Higher Learning | Techical assistance in data processing and analysis |
| National Bureau of Statistics | Ministry of Finance and Planning | Techical assistance in data processing and analysis |
| Oxford Policy Management Limited (OPML) | UK | Techical assistance in reviewing data analysis and sampling design |
Funding Agency/Sponsor
| Name | Abbreviation | Role |
|---|---|---|
| United Nation Development Fund | (UNDP) | Financial Surpport |
| United Nation Fund fot Population Activity | UNFPA | Financial Surpport |
Other Identifications/Acknowledgments
| Name | Affiliation | Role |
|---|---|---|
| Mayasa M. Mwinyi | Office of Chief of Government Statistician | Technical Assistance |
| Khalid Chum Haji | Office of Chief of Government Statistician | Technical Support |
| Abdalla Othamn | Office of Chief of Government Statistician | Technical Surpport |
| Salma Saleh Ali | Office of Chief of Government Statistician | Technical Suport |
| Mahmoud Juma | Office of Chief of Government Statistician | Technical Support |
| Dr. adolf Mkenda | University of Dar es Salaam | Technical Assistance |
| Dr John Mduma | University of Dar es Salaam | Technical Assistance |
| Ahmed M. Makbeli | National Bureau of Statistics | Technical Assistance |
| Mr. Martín Cumpa-Castro | Oxford Policy Management Limited (OPML) | Technical Assistance |
| Patrick Ward | Oxford Policy Management Limited (OPML) | Technical Assistance |
| Juan Munoz | Oxford Policy Management Limited (OPML) | Technical Assistance |
| Mr. Edward Mhina | GAD | Consult |
| Mr. Mbwana O. Mbwana | Office of Chief Government Statistician | Author |
| Khadija Khamis Hamad | Office of Chief Government Statistician | Author |
| Attite J. Shaame | Ministry of Health | Author |
| Khadija Khamis Hamad | Office of Chief Government Statistician | Author |
| Amour H. Bakar | Office of Chief Government Statistician | Author |
| Office of Chief Government Statistician | ' |
Sampling
Sampling Procedure
The sample for 2009/10 HBS was selected in two stages. The Primary Sampling Units (PSUs) are Enumeration Areas(EAs); based on the district sample designed from 2002 Population and Housing Census. This is a sample of 179 PSUs, designed to allow estimates of household level variables to be made with reasonable precision for each of ten districts.The sample was stratified by district and urban-rural location.
The second stage sample selection was households. Before the start of 2009/10 HBS enumeration, field staff listed allhouseholds in each of the sampled PSUs. Information on a number of socio economic variables was collected for each houhouseholds. Separate samples were then drawn from each of these groups. To ensure that the analysis wasrepresentative, analytical weights were used which were the inverse of each household's selection probability
The second stage sample selection was households. Before the start of 2009/10 HBS enumeration, field staff listed allhouseholds in each of the sampled PSUs. Information on a number of socio economic variables was collected for each houhouseholds. Separate samples were then drawn from each of these groups. To ensure that the analysis wasrepresentative, analytical weights were used which were the inverse of each household's selection probability
Response Rate
More than 99 percent of the original target sample size was interviewed;
Weighting
Thre are two sets of sampling weight for the Survey . The first set is the EAweights based on the 2002 Population and Housing Census EAs frame.The second set is house hold weight based on listing of households in all the selected EAs
Data Collection
Dates of Data Collection
| Start | End | Cycle |
|---|---|---|
| 2009-06 | 2010-05 | cycle twelve month |
Data Collection Mode
Face-to-face [f2f]
Supervision
Enumerators are supervised closely by field supervisors who are resident nearby EAs; they checked the data quality in the questionnaires in the field on a regular basis, with an average of five EAs supervised by one supervisor. The supervisors working out by the Office of Chief Government Statistician (OCGS) provided an additional check on the questionnaires before sending for office editing and data entry. All filled questionnaires were sent to the OCGS head office, where manual editing, data entry and data processing took place
There were 2 data collecting teams, one was in Unguja and the other was in Pemba. Each team consisted of supervisors and enumerators. Supervisors were responsible for overall administrative work and for checking the quality of the questionnaires before sending them to head office for data editing and processing
There were 2 data collecting teams, one was in Unguja and the other was in Pemba. Each team consisted of supervisors and enumerators. Supervisors were responsible for overall administrative work and for checking the quality of the questionnaires before sending them to head office for data editing and processing
Data Collection Notes
Data collection for the Household Budget Survey (HBS) begun on the first week of June 2009 and was completed in May 2010 There were 2 data collecting teams, one was in Unguja and the other was in Pemba. Each team consisted of supervisors and enumerators. Supervisors were responsible for overall administrative work and for checking the quality of the questionnaires before sending them to head office for data editing and processing.
Data Collectors
| Name | Abbreviation | Affiliation |
|---|---|---|
| The Office of Chief Government Statistician | OCGS | Ministry of Finance and Planning |
Questionnaires
Questionnaires
The 2009/10 HBS collected information using one main household questionnaire, together with two types of diary similar to that used in the 2004/05 Household Budget Survey. Information on consumption / expenditure is collected in two formats. The first is a diary that records all transactions and consumption for that household for one calendar month. This is completed on a regular basis by the interviewers. The second is recall of larger items of expenditure over the twelve months preceding the survey.
HBSQF1 asks questions on demographic and socio-economic topics such as age, sex marital status, economic activities, health and education. It also asks questions on possession of assets as well as purchases of consumer durable items
and the income of the household members for the last 12 months.
HBSQF2 is a summary of all income and consumption expenditure of the household members transferred from the diaries in a particular month.
Diary for household expenditure and income is an individual record book. Everyday each member of the household who may be able to spend is supposed to record income and expenditure in cash or in kind, quantity and value. The task takes a period of one month for each household. This diary is the main source of data on income and expenditure for this survey.
Diary for household Business is a special book for households which have business activity. They are supposed to record daily expenditure and receipt of the business.
HBSQF1 asks questions on demographic and socio-economic topics such as age, sex marital status, economic activities, health and education. It also asks questions on possession of assets as well as purchases of consumer durable items
and the income of the household members for the last 12 months.
HBSQF2 is a summary of all income and consumption expenditure of the household members transferred from the diaries in a particular month.
Diary for household expenditure and income is an individual record book. Everyday each member of the household who may be able to spend is supposed to record income and expenditure in cash or in kind, quantity and value. The task takes a period of one month for each household. This diary is the main source of data on income and expenditure for this survey.
Diary for household Business is a special book for households which have business activity. They are supposed to record daily expenditure and receipt of the business.
Data Processing
Data Editing
Cleaning the consuption data
The consumption data was cleaned largely along the same aproach that was used to clean the 2004\05
Budget Survey data. The cleaning protocol was largely maintained to ensure comparability of the two Survey. The first round of cleaning the data took place during the entry of data mostly to correct data that was wrong took place just before the analysis of the consuption data and the idea was to weed off outliers and correct obvious errors such as misconding of measured of unit. The cleaning of food items involving the following key steps. First, where value of an item is available corresponding quantity is missing, or where the quantity is missing,or the quantity of the item is available but the value is missing, imputation was made.In case of the missing values cash transactions for the data that was missing component we the median unit value. This median unit value together with the actual quantity are used to fill the missing value of the item with regards to the missing quantity, median unit value is also used to get the quantity for had replaced this way.The second aproach involved weeding off outliers. The prices that were found tobe five times the median prices were replaced by the corresponding median price.The quantities that where times the median items quantity were also replaced by the median item quantity. 2.5 percent of record was adjusted in this way, Further, the budget share of each item was used to assess any remaining outliers, where its budget share taht was in access of the median budget share plus three times the standard deviation of the item budget shere was considered to be an outliersand these were equally replaced by the median values. Per capita calorie consumption was also used to assess whether reported food consumption is an outlier. The non-food items were cleaned in two steps. First regression analysis was used to impute rent on own occupiedhouses. The regression was first used to relate the quality of houses (type of walls, number of rooms etc) to the actualrent paid. Once this relationship was established, it was used to predict the rent of own occupied households based onthe quality of houses. The second step was to remove outliers from non-food items. This involved flagging off record ofitem whose budget share is too high (in this case, if it is above the median budget share of the item plus three times thestandard deviation of the item), and replace the outliers with the median values of the items.
The consumption data was cleaned largely along the same aproach that was used to clean the 2004\05
Budget Survey data. The cleaning protocol was largely maintained to ensure comparability of the two Survey. The first round of cleaning the data took place during the entry of data mostly to correct data that was wrong took place just before the analysis of the consuption data and the idea was to weed off outliers and correct obvious errors such as misconding of measured of unit. The cleaning of food items involving the following key steps. First, where value of an item is available corresponding quantity is missing, or where the quantity is missing,or the quantity of the item is available but the value is missing, imputation was made.In case of the missing values cash transactions for the data that was missing component we the median unit value. This median unit value together with the actual quantity are used to fill the missing value of the item with regards to the missing quantity, median unit value is also used to get the quantity for had replaced this way.The second aproach involved weeding off outliers. The prices that were found tobe five times the median prices were replaced by the corresponding median price.The quantities that where times the median items quantity were also replaced by the median item quantity. 2.5 percent of record was adjusted in this way, Further, the budget share of each item was used to assess any remaining outliers, where its budget share taht was in access of the median budget share plus three times the standard deviation of the item budget shere was considered to be an outliersand these were equally replaced by the median values. Per capita calorie consumption was also used to assess whether reported food consumption is an outlier. The non-food items were cleaned in two steps. First regression analysis was used to impute rent on own occupiedhouses. The regression was first used to relate the quality of houses (type of walls, number of rooms etc) to the actualrent paid. Once this relationship was established, it was used to predict the rent of own occupied households based onthe quality of houses. The second step was to remove outliers from non-food items. This involved flagging off record ofitem whose budget share is too high (in this case, if it is above the median budget share of the item plus three times thestandard deviation of the item), and replace the outliers with the median values of the items.
Other Processing
The supervisors working out by the Office of Chief Government Statistician (OCGS) provided an additional check on the questionnaires before sending for office editing and data entry. All filled questionnaires were sent to the OCGS head
office, where manual editing, data entry and data processing took place.
Data entry was done by using CSPro 4.0 application programme. It started in August 2009, went in parallel with fieldworkand was terminated in July 2010. An automated data consistency checking procedure using CSPro and SPSS 13packages was run on the entered data during field work. A data validation team was informed of the errors and correctedthem where possible. Initially data validation was terminated in August 2010. Further consistency checks, validation and
the analysis started in September 2010 and were completed in November 2010
office, where manual editing, data entry and data processing took place.
Data entry was done by using CSPro 4.0 application programme. It started in August 2009, went in parallel with fieldworkand was terminated in July 2010. An automated data consistency checking procedure using CSPro and SPSS 13packages was run on the entered data during field work. A data validation team was informed of the errors and correctedthem where possible. Initially data validation was terminated in August 2010. Further consistency checks, validation and
the analysis started in September 2010 and were completed in November 2010
Access policy
Contacts
| Name | Affiliation | URL | |
|---|---|---|---|
| Head of Data Management Division | The Office of the Chief Government Statistician | abdulla.makam@ocgs.go.tz | www.ocgs.tz |
Confidentiality
Confidentiality of respondent guaranteed under Statistical Act No. 9 of 2007
The Chief Government Statistician may disclose information in the form of individual statistical records solely for bona fide research or statistical purposes provided that:-
(a) all identification such as name and address has been removed;
(b) the information is disclosed in a manner that is not likely to enable the identification of the particular person or undertaking or business to which it relates.
Access conditions
OCGS 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
Any person or organization to whom any statistical records are disclosed shall: -
(a) not attempt to identify any particular person or undertaking or business;
(b) use the information for research or statistical purposes only;
(c) not disclose the information to any other person or organization;
1) Public use files, accessible by all
2) Licensed datasets, accessible under certain conditions
3) Datasets only accessible on location, for certain datasets
Any person or organization to whom any statistical records are disclosed shall: -
(a) not attempt to identify any particular person or undertaking or business;
(b) use the information for research or statistical purposes only;
(c) not disclose the information to any other person or organization;
Citation requirements
"The Office of The Chief Government Statistician, HOUSEHOLD BUDGET SURVEY 2009/10 ( 2009\10 HBS), Version 2.1 of the public use dataset (October 2010), provided by the National Data Archive. www.ocgs.go.tz''
Access authority
| Name | Affiliation | URL | |
|---|---|---|---|
| Chief Government Statistician | The Office of Chief of Government Statistician | zanstat@ocgs.go.tz | www.ocgs.go.tz |
Disclaimer and copyrights
Disclaimer
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.
Copyright
(c) 2010, The Office of the Chief Government Statistician
Metadata production
DDI Document ID
DDI-TZA-2009-HBS-V01-M-OCGS
Producers
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| The Office of Chief Government Statistician | OCGS | Ministry of Finance and Planning | Documentation of the study |
Date of Metadata Production
2023-10-13
DDI Document version
Version 1.0