National Panel Survey 2010-2011, Wave 2
Tanzania, 2010 - 2011
Get Microdata
Reference ID
TZA_2010_NPS-R2_v03_M
Producer(s)
National Bureau of Statistics
Collection(s)
Metadata
Created on
Oct 10, 2012
Last modified
Mar 13, 2019
Page views
299080
Downloads
30408
Identification
Survey ID Number
TZA_2010_NPS-R2_v03_M
Title
National Panel Survey 2010-2011, Wave 2
Subtitle
Wave 2
Country/Economy
| Name |
|---|
| Tanzania |
Study type
Living Standards Measurement Study [hh/lsms]
Series Information
The 2010/2011 Tanzania National Panel Survey (TZNPS) is the second in a series of nationally representative household panel surveys that collect information on a wide range of topics including agricultural production, non-farm income generating activities, consumption expenditures, and a wealth of other socio-economic characteristics. Both the first and second rounds of the TZNPS were implemented by the Tanzania National Bureau of Statistics (NBS). The first round of the survey was conducted over twelve months from October 2008 to September 2009. The main fieldwork of the second round of the TZNPS started in October 2010 and completed in September 2011, with specialized tracking teams remaining in the field until November 2011.
Abstract
The main objective of the TZNPS is to provide high-quality household-level data to the Tanzanian government and other stakeholders for monitoring poverty dynamics, tracking the progress of the Mkukuta poverty reduction strategy1, and to evaluate the impact of other major, national-level government policy initiatives. As an integrated survey covering a number of different socioeconomic factors, it compliments other more narrowly focused survey efforts, such as the Demographic and Health Survey on health, the Integrated Labour Force Survey on labour markets, the Household Budget Survey on expenditure, and the National Sample Census of Agriculture. Secondly, as a panel household survey in which the same households are revisited over time, the TZNPS allows for the study of poverty and welfare transitions and the determinants of living standard changes
Kind of Data
Sample survey data [ssd]
Unit of Analysis
A living standards survey with community-level questionnaire with the following units of analysis: individuals, household, and communities.
Version
Version Description
Version 03: Edited, anonymous dataset for public distribution.
Version Date
2012-09
Version Notes
Version 02 - "HH.Geovariables_Y2" dataset has been revised.
Version 03 - "comsec_cc" dataset has been provided.
Version 03 - "comsec_cc" dataset has been provided.
Scope
Notes
- HOUSEHOLD: Household Identification, Household Member Roster, Eduaction, Health, Labour, Food Outside the Household, Subject welfare, Government, Food Security, Housing, Water and Sanitation, Food Consumption, Non-Food Expenditures, Household Assets, Assistance and Groups, Credit, Finance, Recent Shocks to HH Welfare, Anthropometry;
- AGRICULTURE:Household Roster, Plot Roster, Plot Details, Annual Crops by plot, Annual Crop Production and Sales, Permanent Crops by plot, Permanent crops - production and sales, Outgrower schemes and contract farming, processed agricultural products and agricultural bi-products, livestock, Farm implents and machinery extension;
- FISHERY:Survey Information, fisheries Calendar, household labour, Fishing Labour, input, output, Gear Rentet out, trading;
- COMMUNITY: Community Identification, Survey staff Details, Access to basic services, Investments projects, land use,, Agriculture, Demography and family issues, Governance, Water and sanitation, Roster of Community leaders, Market price.
- AGRICULTURE:Household Roster, Plot Roster, Plot Details, Annual Crops by plot, Annual Crop Production and Sales, Permanent Crops by plot, Permanent crops - production and sales, Outgrower schemes and contract farming, processed agricultural products and agricultural bi-products, livestock, Farm implents and machinery extension;
- FISHERY:Survey Information, fisheries Calendar, household labour, Fishing Labour, input, output, Gear Rentet out, trading;
- COMMUNITY: Community Identification, Survey staff Details, Access to basic services, Investments projects, land use,, Agriculture, Demography and family issues, Governance, Water and sanitation, Roster of Community leaders, Market price.
Topics
| Topic |
|---|
| Agricultural production |
| Non-farm income generating activities |
| Consumption expenditures |
| Wealth of other socio-economic characteristics |
Keywords
| Keyword |
|---|
| NPS |
| National Panel Survey |
Coverage
Geographic Coverage
National Coverage: Dar es Salaam, other urban areas in Mainland, rural areas in Mainland, and Zanzibar
Geographic Unit
National
Producers and sponsors
Primary investigators
| Name | Affiliation |
|---|---|
| National Bureau of Statistics | Ministry of Finance, Tanzania |
Producers
| Name | Affiliation | Role |
|---|---|---|
| Ministry of Agriculture, Food Security and Cooperatives | Line Ministries | - [Technical assistance in] survey design and implementation |
| Ministry of Finance | Line Ministries | - [Technical assistance in] survey design and implementation |
| Millennium Challenge Account - Tanzania | Line Ministries | - [Technical assistance in] survey design and implementation |
| World Bank | Development partners | - [Technical assistance in] survey design and implementation |
| Department for International Development | Technical assistance | |
| United Nation Children's Funds | Technical assistance | |
| United Nation Population Funds | Technical assistance | |
| Japan International Cooperation Agency | Technical assistance |
Funding Agency/Sponsor
| Name | Abbreviation | Role |
|---|---|---|
| The European Commission | EU_Commission | Provide grant |
| The World Bank (Living Standards Measurement Study - Integrated Surveys on Agriculture) | WB_LSMS-ISA | Provide complementary funding |
Other Identifications/Acknowledgments
| Name | Role |
|---|---|
| Poverty Eradication Division | Main supporters |
| Gates Foundation | Main supporters |
Sampling
Sampling Procedure
The sample design for the second round of the NPS revisits all the households interviewed in the first round of the panel, as well as tracking adult split-off household members. The original sample size of 3,265 households was designed to representative at the national, urban/rural, and major agro-ecological zones. The total sample size was 3,265 households in 409 Enumeration Areas (2,063 households in rural areas and 1,202 urban areas). It is also be possible in the final analysis to produce disaggregated poverty rates for 4 different strata: Dar es Salaam, other urban areas on mainland Tanzania, rural mainland Tanzania, and Zanzibar.
Since the TZNPS is a panel survey, the second round of the fieldwork revisits all households originally interviewed during round one. If a household has moved from its original location, the members were interviewed in their new location. If that location was within one hour of the original location, the field team did the interview at the time of their visit to the enumeration area. If the household had located more than an hour from the original location, details of the new location were recorded on specialized forms, and the information passed to a dedicated tracking team for follow-up.
If a member of the original household had split from their original location to form or join a new household, information was recorded on the current whereabouts of this member. All adult former household members (those over the age of 15) were tracked to their new location. Similar to the protocol for the re-located households, if the new household is within one hour of the original location, the new household was interviewed by the main field team at the time of the visit to the enumeration area. For those that have moved more than one hour away, their information was passed to the dedicated tracking team for follow-up. Once the tracking targets have been found, teams are required to interview them and any new members of the household.
The total sample size for the second round of the NPS has a total sample size of 3924 households. This represents 3168 round-one households, a re-interview rate of over 97 percent. In addition, of the 10,420 eligible adults (over age 15 in 2010), 9,338 were re-interviewed, a reinterview rate of approximately 90 percent.
Since the TZNPS is a panel survey, the second round of the fieldwork revisits all households originally interviewed during round one. If a household has moved from its original location, the members were interviewed in their new location. If that location was within one hour of the original location, the field team did the interview at the time of their visit to the enumeration area. If the household had located more than an hour from the original location, details of the new location were recorded on specialized forms, and the information passed to a dedicated tracking team for follow-up.
If a member of the original household had split from their original location to form or join a new household, information was recorded on the current whereabouts of this member. All adult former household members (those over the age of 15) were tracked to their new location. Similar to the protocol for the re-located households, if the new household is within one hour of the original location, the new household was interviewed by the main field team at the time of the visit to the enumeration area. For those that have moved more than one hour away, their information was passed to the dedicated tracking team for follow-up. Once the tracking targets have been found, teams are required to interview them and any new members of the household.
The total sample size for the second round of the NPS has a total sample size of 3924 households. This represents 3168 round-one households, a re-interview rate of over 97 percent. In addition, of the 10,420 eligible adults (over age 15 in 2010), 9,338 were re-interviewed, a reinterview rate of approximately 90 percent.
Deviations from the Sample Design
To obtain the attrition adjustment factor the probability that a sample household was successfully reinterviewed in the second round of surveys is modeled with the linear logistic model at the level of the individual. A binary response variable is created by coding the response disposition for eligible households that do not respond in the second round as 0, and households that do respond as 1. Then a logistic response propensity model is fitted, using 2005 UNHS household and individual characteristics measured in the first wave as covariates.
In a few limited cases, values of unit level variables were missing from the 2008/2009 household dataset. These values were imputed using multivariate regression and logistic regression techniques. Imputations are done using the ‘impute’ command in Stata at the level of the UNPS strata (urban/rural and region). Overall, less than one percent of the variables required imputation to replace missing values.
The estimated logistic model is used to obtain a predicted probability of response for each household member in the 2010/2011 survey. These response probabilities were then aggregated to the household level (by calculating the mean), the using the household-level predicted response probabilities as the ranking variable, all households are ranked into 10 equal groups (deciles). An attrition adjustment factor was then defined as the reciprocal of the empirical response rate for the household-level propensity score decile.
To reduce the overall standard errors, and weight the population totals up to the known population figures, a post-stratification correction is applied. Based on the projected number of households in the urban and rural segments of each region, adjustment factors are calculated. This correction also reduces overall standard errors (see Little et al, 1997).
In a few limited cases, values of unit level variables were missing from the 2008/2009 household dataset. These values were imputed using multivariate regression and logistic regression techniques. Imputations are done using the ‘impute’ command in Stata at the level of the UNPS strata (urban/rural and region). Overall, less than one percent of the variables required imputation to replace missing values.
The estimated logistic model is used to obtain a predicted probability of response for each household member in the 2010/2011 survey. These response probabilities were then aggregated to the household level (by calculating the mean), the using the household-level predicted response probabilities as the ranking variable, all households are ranked into 10 equal groups (deciles). An attrition adjustment factor was then defined as the reciprocal of the empirical response rate for the household-level propensity score decile.
To reduce the overall standard errors, and weight the population totals up to the known population figures, a post-stratification correction is applied. Based on the projected number of households in the urban and rural segments of each region, adjustment factors are calculated. This correction also reduces overall standard errors (see Little et al, 1997).
Response Rate
The total sample size for the second round of the NPS has a total sample size of 3924 households. This represents 3168 round one households, a re-interview rate of over 97 percent. In addition, of the 10,420 eligible adults (over age 15 in 2010), 9,338 were re-interviewed, a re-interview rate of approximately 90 percent.
Weighting
The methodology described in this paper builds upon published documentation from established panel surveys, such as the Panel Study of Income Dynamics [PSID], conducted since 1968 by the Institute for Social Research at the University of Michigan; and the British Household Panel Survey [BHPS], whose first 13 waves were conducted between 1991 and 2003 by Institute for Social and Economic Research at the University of Essex. Both the PSID and the BHPS are nationally-representative panel surveys in the USA and the UK respectively.
The weights are developed following these steps:
1) Begin with the “base weights” or those calculated during the first round of the survey; The panel weight calculations are based on the 2008/2009 household weights. These weights are based on the inverse probability of selection, EA level non-response correction, trimming of outlier weights, and a post-stratification correction11. These probability weights form the first component of the 2010/2011 calculations.
W1=W2008
2) incorporate fair-share weights for composition changes;
Based on the tracking protocols, the tracking for split off rules for the TZNPS allow for the incorporation of people who now live with original sample members. For example a young adult living with his parents in 2008, may be 2010 have formed a new household, getting married and having a child. The wife and infant will be incorporated into the survey and thus require a probability of selection. Such corrections are routinely used to distribute weight to new sample members in panel surveys. See Rendtel and Harms (2009) for a discussion of several different methods of weight correction. Because split-off individuals are tracked and interviewed in their new households, there are multiple ways that a household can become part of the survey.
o Either by being selected initially for the first round of the TZNPS
o By receiving a member that came from a household that was selected for the first round of the TZNPS.
In an ideal world, it would be possible to know the probability of selection that each new member brought into the household, and adjust the household weight accordingly. This is necessary since households receiving members have higher probabilities of selection (and therefore lower weights) because the household could have been selected in multiple ways. Since we cannot know the probabilities of every member, we must make simplifying assumptions. The first simplifying assumption is that the arriving members arrived together from one other household. This would be the case if a man and woman get married and set up a new household, or in the case of an older relative moving in with adult children. In certain cases, however, arriving members come from more than one household. Assuming only two source households underestimates slightly the probability of selection (and therefore over-estimates the weights). Incidence of these cases is believed to be relatively rare, and any resulting bias should be negligible. The second simplifying assumption we make is that the arriving members have the same probability of selection, on average, as those members that are already there. This would not be true on a case-by-case basis but would be true in the aggregate. With these simplifying assumptions, we add a factor of ½ for all households, ‘split’ or ‘parent’ that have new members arriving from other households.
This takes into account the fact that they could have been selected in two ways, and assumes the probability of selection is equal.
A limitation of the panel methodology is that the represented population is not identical to the 2010 Tanzanian household population, as it does not include immigrants in new households. Inclusion of these groups would necessitate refreshing the sample with new households. However, the represented population is close enough to the 2010 Tanzanian population to permit the desired cross-sectional estimates.
3) derive attrition adjusted weights for all individuals, including split-off10 households, then aggregate these weights to the household level; All household panel surveys must tackle the problem of attrition, sample members selected for follow interview which cannot be located and/or interviewed. The methodology used to adjust weights for attrition in the UNPS follows Rosenbaum & Rubin (1984). We use predicted response probabilities from a logistic regression model based on the covariates to form the weighting classes or cells. This approach has also been adopted in the PSID; see for example, Gouskova (2008).
The total sample size for the second round of the NPS has a total sample size of 3924 households. This represents 3168 round one households, a re-interview rate of over 97 percent. In addition, of the 10,420 eligible adults (over age 15 in 2010), 9,338 were re-interviewed, a re-interview rate of approximately 90 percent. To obtain the attrition adjustment factor the probability that a sample household was successfully reinterviewed in the second round of surveys is modeled with the linear logistic model at the level of the
individual. A binary response variable is created by coding the response disposition for eligible households that do not respond in the second round as 0, and households that do respond as 1.
Then a logistic response propensity model is fitted, using 2005 UNHS household and individual characteristics measured in the first wave as covariates. In a few limited cases, values of unit level variables were missing from the 2008/2009 household dataset. These values were imputed using multivariate regression and logistic regression techniques. Imputations are done using the ‘impute’ command in Stata at the level of the UNPS strata (urban/rural and region). Overall, less than one percent of the variables required imputation to replace missing values. The estimated logistic model is used to obtain a predicted probability of response for each household member in the 2010/2011 survey. These response probabilities were then aggregated to the household level (by calculating the mean), the using the household-level predicted response probabilities as the ranking variable, all households are ranked into 10 equal groups (deciles). An attrition adjustment factor was then defined as the reciprocal of the empirical response rate for the household-level propensity score decile.
4) post-stratify the pooled weights to known population totals.
To reduce the overall standard errors, and weight the population totals up to the known population figures, a post-stratification correction is applied. Based on the projected number of households in the urban and rural segments of each region, adjustment factors are calculated. This correction also reduces overall standard errors (see Little et al, 1997).
The weights are developed following these steps:
1) Begin with the “base weights” or those calculated during the first round of the survey; The panel weight calculations are based on the 2008/2009 household weights. These weights are based on the inverse probability of selection, EA level non-response correction, trimming of outlier weights, and a post-stratification correction11. These probability weights form the first component of the 2010/2011 calculations.
W1=W2008
2) incorporate fair-share weights for composition changes;
Based on the tracking protocols, the tracking for split off rules for the TZNPS allow for the incorporation of people who now live with original sample members. For example a young adult living with his parents in 2008, may be 2010 have formed a new household, getting married and having a child. The wife and infant will be incorporated into the survey and thus require a probability of selection. Such corrections are routinely used to distribute weight to new sample members in panel surveys. See Rendtel and Harms (2009) for a discussion of several different methods of weight correction. Because split-off individuals are tracked and interviewed in their new households, there are multiple ways that a household can become part of the survey.
o Either by being selected initially for the first round of the TZNPS
o By receiving a member that came from a household that was selected for the first round of the TZNPS.
In an ideal world, it would be possible to know the probability of selection that each new member brought into the household, and adjust the household weight accordingly. This is necessary since households receiving members have higher probabilities of selection (and therefore lower weights) because the household could have been selected in multiple ways. Since we cannot know the probabilities of every member, we must make simplifying assumptions. The first simplifying assumption is that the arriving members arrived together from one other household. This would be the case if a man and woman get married and set up a new household, or in the case of an older relative moving in with adult children. In certain cases, however, arriving members come from more than one household. Assuming only two source households underestimates slightly the probability of selection (and therefore over-estimates the weights). Incidence of these cases is believed to be relatively rare, and any resulting bias should be negligible. The second simplifying assumption we make is that the arriving members have the same probability of selection, on average, as those members that are already there. This would not be true on a case-by-case basis but would be true in the aggregate. With these simplifying assumptions, we add a factor of ½ for all households, ‘split’ or ‘parent’ that have new members arriving from other households.
This takes into account the fact that they could have been selected in two ways, and assumes the probability of selection is equal.
A limitation of the panel methodology is that the represented population is not identical to the 2010 Tanzanian household population, as it does not include immigrants in new households. Inclusion of these groups would necessitate refreshing the sample with new households. However, the represented population is close enough to the 2010 Tanzanian population to permit the desired cross-sectional estimates.
3) derive attrition adjusted weights for all individuals, including split-off10 households, then aggregate these weights to the household level; All household panel surveys must tackle the problem of attrition, sample members selected for follow interview which cannot be located and/or interviewed. The methodology used to adjust weights for attrition in the UNPS follows Rosenbaum & Rubin (1984). We use predicted response probabilities from a logistic regression model based on the covariates to form the weighting classes or cells. This approach has also been adopted in the PSID; see for example, Gouskova (2008).
The total sample size for the second round of the NPS has a total sample size of 3924 households. This represents 3168 round one households, a re-interview rate of over 97 percent. In addition, of the 10,420 eligible adults (over age 15 in 2010), 9,338 were re-interviewed, a re-interview rate of approximately 90 percent. To obtain the attrition adjustment factor the probability that a sample household was successfully reinterviewed in the second round of surveys is modeled with the linear logistic model at the level of the
individual. A binary response variable is created by coding the response disposition for eligible households that do not respond in the second round as 0, and households that do respond as 1.
Then a logistic response propensity model is fitted, using 2005 UNHS household and individual characteristics measured in the first wave as covariates. In a few limited cases, values of unit level variables were missing from the 2008/2009 household dataset. These values were imputed using multivariate regression and logistic regression techniques. Imputations are done using the ‘impute’ command in Stata at the level of the UNPS strata (urban/rural and region). Overall, less than one percent of the variables required imputation to replace missing values. The estimated logistic model is used to obtain a predicted probability of response for each household member in the 2010/2011 survey. These response probabilities were then aggregated to the household level (by calculating the mean), the using the household-level predicted response probabilities as the ranking variable, all households are ranked into 10 equal groups (deciles). An attrition adjustment factor was then defined as the reciprocal of the empirical response rate for the household-level propensity score decile.
4) post-stratify the pooled weights to known population totals.
To reduce the overall standard errors, and weight the population totals up to the known population figures, a post-stratification correction is applied. Based on the projected number of households in the urban and rural segments of each region, adjustment factors are calculated. This correction also reduces overall standard errors (see Little et al, 1997).
Data Collection
Dates of Data Collection
| Start | End |
|---|---|
| 2010-10 | 2011-09 |
Data Collection Mode
Face-to-face [f2f]
Supervision
The mobile tracking team consisted of one supervisor, two interviewers, one data entry technician, and one driver. In addition, there were two dedicated tracking enumerators that remained in Dar es Salaam. The tracking team began interviews three months after the beginning of fieldwork to allow enough time to accumulate a sufficient number of tracking targets. Tracking targets were grouped into geographic regions, and the team would visit the regions approximately every 2-3 months. Any tracking target not located was remained in the pool to be visited during the next trip, in addition to any new tracking cases that had accumulated in the intervening months. In addition, the regular field teams also sporadically would perform tracking within their interview regions if there was a backlog of cases. Finally, following the completion of the main fieldwork activities, four supervisors led dedicated tracking teams to interview the remaining cases.
Data Collection Notes
The survey was implemented by eight mobile field teams, each composed of: one supervisor, four enumerators, one data entry technician, and one driver.
The teams visited each enumeration area for between 4-5 days. The questionnaires were administered to the selected households over the course of that time. This allowed the field team to make return visits to the household to complete the entire Household questionnaire and, for farm households, Agriculture questionnaires, and for Fishery questionnaires. To ensure the depth and quality of each section of the survey, the questionnaire was administered across multiple respondents to the most knowledgeable about each topic. For all of the sampled households, areas of all owned and/or cultivated agricultural plots were measured via GPS unless the household refused, the terrain was too difficult, or if the plot was more than 1 hour from the location of the household. Anthropometric measurements were taken for all individuals that were at home, not too ill, and willing to participate.
If the field teams enter an enumeration area and find that the entire household or a member(s) of the household has moved, they are required to follow the tracking protocol. If the entire household has moved from the original residence, teams are required to fill a T-1 form. The T-1 form contains information on the new location of the household, allowing for the teams to locate and interview the household members. If a member or members of the household have split from the original household, a T-2 form is filled out by the teams. Similar to the T-1, a T-2 form contains information on the location of the member(s) who have split from the household. Once the tracking targets have been found, teams are required to interview them and any new additions to the household. Out of the tracking individuals/households, only those over 15 years of age are included in the tracking protocol unless an individual under 15 years of age moved with another individual over 15 years of age, and both were part of the round one data collection.
Within the tracking protocol, there are local and distance cases. Local and distance tracking applies to both T-1 and T-2 forms. Local tracking occurred when the tracking target is within one hour traveling distance from the original EA and at least one tracking member from the household is over 15 years of age. If that is the case, the teams are required to interview the tracking target before leaving the original EA. Distance tracking occurs when the tracking target is not within one hour traveling distance from the original EA. In this case, the teams fill out the appropriate tracking form and send the information NBS headquarters. Once at NBS, the distance tracking case is given to the tracking team, who is then responsible for locating that household and conducting the interview.
The mobile tracking team consisted of one supervisor, two interviewers, one data entry technician, and one driver. In addition, there were two dedicated tracking enumerators that remained in Dar es Salaam. The tracking team began interviews three months after the beginning of fieldwork to allow enough time to accumulate a sufficient number of tracking targets. Tracking targets were grouped into geographic regions, and the team would visit the regions approximately every 2-3 months. Any tracking target not located was remained in the pool to be visited during the next trip, in addition to any new tracking cases that had accumulated in the intervening months. In addition, the regular field teams also sporadically would perform tracking within their interview regions if there was a backlog of cases. Finally, following the completion of the main fieldwork activities, four supervisors led dedicated tracking teams to interview the remaining cases.
Data entry was done concurrently with data collection by the data entry technician, using a laptop, known as first data entry. The data entry program was a CSPro-based system, developed by NBS with support from the World Bank. This facilitated the performance of internal crosschecks prior to departure from the enumeration area, allowing enumerators to return to households and clarify inconsistent information on the questionnaires. Data files from completed EAs were then e-mailed to headquarters using 3G modems. These files were concatenated and periodic checks were done to ensure the fieldwork was proceeding according to the calendar. The field teams also send the paper questionnaires back to the headquarters on a monthly basis.
Once the paper questionnaires and data files for completed EAs were received at NBS headquarters, a double entry procedure was implemented. Eight data entrants were hired by NBS to re-enter the data from the paper questionnaires into the CSPro-based data entry system for all households and questionnaires administered. A cross comparison between the entered values in the field based data entry and double entry was conducted and any differences in values between the two were flagged for manual inspection of the physical questionnaire. Corrections based on this inspection exercise were ultimately encoded in the dataset.
Additionally, an extensive review of data files was conducted, including interviewer errors such as missing values, ranges and outliers. Observations were returned for manual inspection of the physical questionnaires if continuous values fell outside five standard deviations of the mean, categorical values were not eligible responses, or there were internal inconsistencies within the dataset (for example, the age of an individual was not consistent with their educational status, there was more than one head of household listed, an individual was engaged in multiple primary activities, the quantity of crops and their byproducts produced, harvested, and sold not listed, the distance from the market and an individual’s plot was not listed, the number of weeks, days per week, and hours per day an individual engaged in fishery activity was not recorded, the species and quantity of fish caught, bought, sold, or traded was not listed, etc).
When it was determined that these values were the result of data-entry error, the values were corrected. In addition, cases deemed to reflect obvious enumerator error were also corrected in this cleaning process. The majority of such cases involved the use of incorrect measurement units, e.g. recording grams as kilograms or vice versa.
The teams visited each enumeration area for between 4-5 days. The questionnaires were administered to the selected households over the course of that time. This allowed the field team to make return visits to the household to complete the entire Household questionnaire and, for farm households, Agriculture questionnaires, and for Fishery questionnaires. To ensure the depth and quality of each section of the survey, the questionnaire was administered across multiple respondents to the most knowledgeable about each topic. For all of the sampled households, areas of all owned and/or cultivated agricultural plots were measured via GPS unless the household refused, the terrain was too difficult, or if the plot was more than 1 hour from the location of the household. Anthropometric measurements were taken for all individuals that were at home, not too ill, and willing to participate.
If the field teams enter an enumeration area and find that the entire household or a member(s) of the household has moved, they are required to follow the tracking protocol. If the entire household has moved from the original residence, teams are required to fill a T-1 form. The T-1 form contains information on the new location of the household, allowing for the teams to locate and interview the household members. If a member or members of the household have split from the original household, a T-2 form is filled out by the teams. Similar to the T-1, a T-2 form contains information on the location of the member(s) who have split from the household. Once the tracking targets have been found, teams are required to interview them and any new additions to the household. Out of the tracking individuals/households, only those over 15 years of age are included in the tracking protocol unless an individual under 15 years of age moved with another individual over 15 years of age, and both were part of the round one data collection.
Within the tracking protocol, there are local and distance cases. Local and distance tracking applies to both T-1 and T-2 forms. Local tracking occurred when the tracking target is within one hour traveling distance from the original EA and at least one tracking member from the household is over 15 years of age. If that is the case, the teams are required to interview the tracking target before leaving the original EA. Distance tracking occurs when the tracking target is not within one hour traveling distance from the original EA. In this case, the teams fill out the appropriate tracking form and send the information NBS headquarters. Once at NBS, the distance tracking case is given to the tracking team, who is then responsible for locating that household and conducting the interview.
The mobile tracking team consisted of one supervisor, two interviewers, one data entry technician, and one driver. In addition, there were two dedicated tracking enumerators that remained in Dar es Salaam. The tracking team began interviews three months after the beginning of fieldwork to allow enough time to accumulate a sufficient number of tracking targets. Tracking targets were grouped into geographic regions, and the team would visit the regions approximately every 2-3 months. Any tracking target not located was remained in the pool to be visited during the next trip, in addition to any new tracking cases that had accumulated in the intervening months. In addition, the regular field teams also sporadically would perform tracking within their interview regions if there was a backlog of cases. Finally, following the completion of the main fieldwork activities, four supervisors led dedicated tracking teams to interview the remaining cases.
Data entry was done concurrently with data collection by the data entry technician, using a laptop, known as first data entry. The data entry program was a CSPro-based system, developed by NBS with support from the World Bank. This facilitated the performance of internal crosschecks prior to departure from the enumeration area, allowing enumerators to return to households and clarify inconsistent information on the questionnaires. Data files from completed EAs were then e-mailed to headquarters using 3G modems. These files were concatenated and periodic checks were done to ensure the fieldwork was proceeding according to the calendar. The field teams also send the paper questionnaires back to the headquarters on a monthly basis.
Once the paper questionnaires and data files for completed EAs were received at NBS headquarters, a double entry procedure was implemented. Eight data entrants were hired by NBS to re-enter the data from the paper questionnaires into the CSPro-based data entry system for all households and questionnaires administered. A cross comparison between the entered values in the field based data entry and double entry was conducted and any differences in values between the two were flagged for manual inspection of the physical questionnaire. Corrections based on this inspection exercise were ultimately encoded in the dataset.
Additionally, an extensive review of data files was conducted, including interviewer errors such as missing values, ranges and outliers. Observations were returned for manual inspection of the physical questionnaires if continuous values fell outside five standard deviations of the mean, categorical values were not eligible responses, or there were internal inconsistencies within the dataset (for example, the age of an individual was not consistent with their educational status, there was more than one head of household listed, an individual was engaged in multiple primary activities, the quantity of crops and their byproducts produced, harvested, and sold not listed, the distance from the market and an individual’s plot was not listed, the number of weeks, days per week, and hours per day an individual engaged in fishery activity was not recorded, the species and quantity of fish caught, bought, sold, or traded was not listed, etc).
When it was determined that these values were the result of data-entry error, the values were corrected. In addition, cases deemed to reflect obvious enumerator error were also corrected in this cleaning process. The majority of such cases involved the use of incorrect measurement units, e.g. recording grams as kilograms or vice versa.
Data Collectors
| Name | Abbreviation | Affiliation |
|---|---|---|
| National Bureau of Statistics | NBS | Ministry of Finance, Tanzania |
Questionnaires
Questionnaires
The Household Questionnaire is comprised of thematic sections.This comprehensive questionnaire allows for the construction of a full consumption-based welfare measure, permitting distributional and incidence analysis. This project also recognizes the imperative to look beyond the household as a unit of analysis in order to improve the quality, relevance and sustainability of agricultural data systems. Although data collection is structured around a household panel survey, the data on labor, education, and health status were collected at the individual level. Moreover, in some household activities (like non-farm enterprise), the questionnaire records which specific members are engaged in the activity. A detailed description of the contents of the questionnaire can be found in the Basic Information Document report (Table 1).
The Agricultural Questionnaire collects information relative to a household’s agricultural activities. Information is collected at both the plot and crop level on inputs, production and sales. The Basic Information Document report (Table 2) provides a detailed description of the contents of the questionnaire. This questionnaire was administered to any household that engaged in any farming or livestock holding.
The Fisheries Questionnaire was developed in partnership with the World Fish Program to collect data on household fishery activities, fish processing, and fish trading. This includes data on the inputs, outputs, labour, and sales. All this data is divided into two reference periods, the high and low season. This data is collected at the household level. The Basic Information Document report (Table 3) provides a more comprehensive list of the sections found within the Fishery Questionnaire.
The Community Questionnaire collects information on physical and economic infrastructure and events in surveyed communities. In each selected survey community, key informants are interviewed by the field team supervisors. Information about the respondents for the community questionnaire is collected individually in section CI of community questionnaire.
The questionnaires were developed in collaboration with line ministries and donor partners, including the Technical Committee, over a period of several months. The NBS solicited feedback from various stakeholders in regards to survey content and design. The round two questionnaires were piloted in the Morogoro region in June 2010, in conjunction with supervisor training. After piloting, the questionnaires were further revised and finalized by August 2010. Questionnaire manuals were developed with detailed instructions for field staff during training and as the main survey reference guide over the course of the field work.
The Agricultural Questionnaire collects information relative to a household’s agricultural activities. Information is collected at both the plot and crop level on inputs, production and sales. The Basic Information Document report (Table 2) provides a detailed description of the contents of the questionnaire. This questionnaire was administered to any household that engaged in any farming or livestock holding.
The Fisheries Questionnaire was developed in partnership with the World Fish Program to collect data on household fishery activities, fish processing, and fish trading. This includes data on the inputs, outputs, labour, and sales. All this data is divided into two reference periods, the high and low season. This data is collected at the household level. The Basic Information Document report (Table 3) provides a more comprehensive list of the sections found within the Fishery Questionnaire.
The Community Questionnaire collects information on physical and economic infrastructure and events in surveyed communities. In each selected survey community, key informants are interviewed by the field team supervisors. Information about the respondents for the community questionnaire is collected individually in section CI of community questionnaire.
The questionnaires were developed in collaboration with line ministries and donor partners, including the Technical Committee, over a period of several months. The NBS solicited feedback from various stakeholders in regards to survey content and design. The round two questionnaires were piloted in the Morogoro region in June 2010, in conjunction with supervisor training. After piloting, the questionnaires were further revised and finalized by August 2010. Questionnaire manuals were developed with detailed instructions for field staff during training and as the main survey reference guide over the course of the field work.
Data Processing
Data Editing
CSPro-based data entry/editing system was used.
A cross comparison between the entered values in the field based data entry and double entry was conducted and any differences in values between the two were flagged for manual inspection of the physical questionnaire. Corrections based on this inspection exercise were ultimately encoded in the dataset.
Additionally, an extensive review of data files was conducted, including interviewer errors such as missing values, ranges and outliers. Observations were returned for manual inspection of the physical questionnaires if continuous values fell outside five standard deviations of the mean, categorical values were not eligible responses, or there were internal inconsistencies within the dataset (for example, the age of an individual was not consistent with their educational status, there was more than one head of household listed, an individual was engaged in multiple primary activities, the quantity of crops and their byproducts produced, harvested, and sold not listed, the distance from the market and an individual’s plot was not listed, the number of weeks, days per week, and hours per day an individual engaged in fishery activity was not recorded, the species and quantity of fish caught, bought, sold, or traded was not listed, etc). When it was determined that these values were the result of data-entry error, the values were corrected. In addition, cases deemed to reflect obvious enumerator error were also corrected in this cleaning process. The majority of such cases involved the use of incorrect measurement units, e.g. recording grams as kilograms or vice versa.
A cross comparison between the entered values in the field based data entry and double entry was conducted and any differences in values between the two were flagged for manual inspection of the physical questionnaire. Corrections based on this inspection exercise were ultimately encoded in the dataset.
Additionally, an extensive review of data files was conducted, including interviewer errors such as missing values, ranges and outliers. Observations were returned for manual inspection of the physical questionnaires if continuous values fell outside five standard deviations of the mean, categorical values were not eligible responses, or there were internal inconsistencies within the dataset (for example, the age of an individual was not consistent with their educational status, there was more than one head of household listed, an individual was engaged in multiple primary activities, the quantity of crops and their byproducts produced, harvested, and sold not listed, the distance from the market and an individual’s plot was not listed, the number of weeks, days per week, and hours per day an individual engaged in fishery activity was not recorded, the species and quantity of fish caught, bought, sold, or traded was not listed, etc). When it was determined that these values were the result of data-entry error, the values were corrected. In addition, cases deemed to reflect obvious enumerator error were also corrected in this cleaning process. The majority of such cases involved the use of incorrect measurement units, e.g. recording grams as kilograms or vice versa.
Other Processing
To maintain the confidentiality of our respondents, certain parts of the TZNPS database have not been made publicly available. The confidential variables pertain to (i) names of the respondents to the household and community questionnaires, (ii) village and constituency names, (iii) descriptions of household dwelling and agricultural plot locations, (iv) phone numbers of household members and their reference contacts, (v) GPS-based household and agricultural plot locations, (vi) names of the children of the head/spouse living elsewhere, (vii) names of the deceased household members, (viii) names of individuals listed in the network roster, and (ix) names of field staff.
To increase the use of the TZNPS data, a set of geospatial variables has been provided by using the georeferenced plot and household locations in conjunction with various geospatial databases that were available to the survey team. The table in Appendix A provides the name, type, source, reference period, resolution, description, and source of each variable.
The geovariables are stored in two data files, one at the household-plot-level, and the other at the household-level. The plot-level file, named Plot.Geovariables, contains one geospatial variable measuring plot distance to household and the observations are uniquely identified by the combination of y2_hhid plotnum. The observations included in this file are rainy season plots that are owned and/or cultivated by the household and that have been visited for GPS-based land area measurement.
The rest of the geovariables are stored in HH.Geovariables and the observations are uniquely identified by y2_hhid. To partially satisfy the demand for georeferenced household and community locations while preserving the confidentiality of sample household and communities, we have computed the average of household GPS coordinates in each EA, applied a random offset within a specified range to the average EA value (following the MeasureDHS methodology) and provided the off-set EA latitudes and longitudes are part of EA.Offsets.
More specifically, the coordinate modification strategy relies on random offset of cluster centerpoint coordinates (or average of household GPS locations by EA in TZNPS2) within a specified range determined by an urban/rural classification. For urban areas a range of 0-2 km is used. In rural areas, where communities are more dispersed and risk of disclosure may be higher, a range of 0-5 km offset is used. An additional 0-10 km offset for 1% of rural clusters effectively increases the known range for all rural points to 10 km while introducing only a small amount of noise. Offset points are constrained at the district level, so that they still fall within the correct district for spatial joins, or point-in-polygon overlays. The result is a set of coordinates, representative at the EA level, that fall within known limits of accuracy. Users should take into account the offset range when considering different types of spatial analysis or queries with the data. Analysis of the spatial relationships between locations in close proximity would not be reliable. However, spatial queries using medium or low resolution datasets should be minimally affected by the offsets.
All geospatial variables have been produced by using the unmodified GPS data. These include extensive measures of distance, climatology, soil and terrain and other environmental factors.
Time-series on rainfall and vegetation have also been used to describe the survey agricultural season relative to normal conditions. These variables are intended to provide some understanding of how geophysical characteristics vary at the landscape level.
To increase the use of the TZNPS data, a set of geospatial variables has been provided by using the georeferenced plot and household locations in conjunction with various geospatial databases that were available to the survey team. The table in Appendix A provides the name, type, source, reference period, resolution, description, and source of each variable.
The geovariables are stored in two data files, one at the household-plot-level, and the other at the household-level. The plot-level file, named Plot.Geovariables, contains one geospatial variable measuring plot distance to household and the observations are uniquely identified by the combination of y2_hhid plotnum. The observations included in this file are rainy season plots that are owned and/or cultivated by the household and that have been visited for GPS-based land area measurement.
The rest of the geovariables are stored in HH.Geovariables and the observations are uniquely identified by y2_hhid. To partially satisfy the demand for georeferenced household and community locations while preserving the confidentiality of sample household and communities, we have computed the average of household GPS coordinates in each EA, applied a random offset within a specified range to the average EA value (following the MeasureDHS methodology) and provided the off-set EA latitudes and longitudes are part of EA.Offsets.
More specifically, the coordinate modification strategy relies on random offset of cluster centerpoint coordinates (or average of household GPS locations by EA in TZNPS2) within a specified range determined by an urban/rural classification. For urban areas a range of 0-2 km is used. In rural areas, where communities are more dispersed and risk of disclosure may be higher, a range of 0-5 km offset is used. An additional 0-10 km offset for 1% of rural clusters effectively increases the known range for all rural points to 10 km while introducing only a small amount of noise. Offset points are constrained at the district level, so that they still fall within the correct district for spatial joins, or point-in-polygon overlays. The result is a set of coordinates, representative at the EA level, that fall within known limits of accuracy. Users should take into account the offset range when considering different types of spatial analysis or queries with the data. Analysis of the spatial relationships between locations in close proximity would not be reliable. However, spatial queries using medium or low resolution datasets should be minimally affected by the offsets.
All geospatial variables have been produced by using the unmodified GPS data. These include extensive measures of distance, climatology, soil and terrain and other environmental factors.
Time-series on rainfall and vegetation have also been used to describe the survey agricultural season relative to normal conditions. These variables are intended to provide some understanding of how geophysical characteristics vary at the landscape level.
Access policy
Contacts
| Name | Affiliation | URL | |
|---|---|---|---|
| Director General | dg@nbs.go.tz | Link | |
| Living Standards Measurement Study | World Bank | lsms@worldbank.org | www.worldbank.org/lsms |
Confidentiality
The Primary Data Investigator undertakes that no attempt will be made to identify any individual person, family, business, enterprise or organization. If such a unique disclosure is made inadvertently, no use will be made of the identity of any person or establishment discovered and full details will be reported to the NBS. The identification will not be revealed to any other person not included in the Data Access Agreement.
Access conditions
The dataset has been anonymized and is available as a Public Use Dataset. It is accessible to all for statistical and research purposes only, under the following terms and conditions:
1. The data and other materials will not be redistributed or sold to other individuals, institutions, or organizations without the written agreement of the Nationa Bureau of Statistics, Tanzania.
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 re-identify respondents, and no use will be made of the identity of any person or establishment discovered inadvertently. Any such discovery would immediately be reported to the National Bureau of Statistics.
4. No attempt will be made to produce links among datasets provided by the NBS, or among data from the National Bureau of Statistics and other datasets that could identify individuals or organizations.
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.
6. An electronic copy of all reports and publications based on the requested data will be sent to the National Bureau of Statistics
The original collector of the data, the National Bureau of Statistics, and the relevant funding agencies bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
1. The data and other materials will not be redistributed or sold to other individuals, institutions, or organizations without the written agreement of the Nationa Bureau of Statistics, Tanzania.
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 re-identify respondents, and no use will be made of the identity of any person or establishment discovered inadvertently. Any such discovery would immediately be reported to the National Bureau of Statistics.
4. No attempt will be made to produce links among datasets provided by the NBS, or among data from the National Bureau of Statistics and other datasets that could identify individuals or organizations.
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.
6. An electronic copy of all reports and publications based on the requested data will be sent to the National Bureau of Statistics
The original collector of the data, the National Bureau of Statistics, and the relevant funding agencies bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
Citation requirements
National Bureau of Statistics (NBS) [Tanzania]. 2011. Tanzania National Panel Survey Report (NPS) - Wave 2, 2010 - 2011. Dar es Salaam, Tanzania: NBS. (www.nbs.go.tz)
Access authority
| Name | Affiliation | URL | |
|---|---|---|---|
| National Bureau of Statistics | Ministry of Finance, Tanzania | dg@nbs.go.tz | www.nbs.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.
Metadata production
DDI Document ID
DDI_TZA_2010_NPS-R2_v03_M
Producers
| Name | Abbreviation | Role |
|---|---|---|
| National Bureau of Statistics | NBS | Survey Implementer |
Date of Metadata Production
2012-09-25
DDI Document version
Version 03 (Wave 2: Anonymous dataset for public distribution).