Statistical Methods, Standards and Guidelines 73
Whi = basic weight for the sample households in the i-th sample EA in stratum h
Mh = total number of households in the sampling frame of EAs for stratum h
M'hi = total number of households listed in the i-th sample EA in stratum h nh = number of sample EAs selected in stratum h
Mhi = total number of households in the frame for the i-th sample EA in stratum h
mhi = number of sample households selected in the i-th sample EA in stratum h
If mhi is constant for each stratum (24, for example), the sample will be approximately self- weighting within each stratum. These weights will actually vary slightly based on the difference between the number of households listed in each sample EA and the corresponding number from the sampling frame.
Data Collection Labour force survey questionnaire consists of four modules. First, Labour Force module which consists of two forms namely; Labour Force Survey Form 1 (LFS1) and Labour Force Survey Form 2 (LFS2). The first form (LFS1) is administered to the head of the household or his/her representative intending to collect household particulars. The second form (LFS2) aims to collect the information of labour force details for individuals. Second, Informal Sector module (IS) and its data is being collected using LFS2. Third, Working Children module (WC) which aims to collect information of children age 5 to 17 years is also being collected using LFS2. The fourth module is Time Use Survey module (TUS), it is designed to collect the information on the routine activities of the respondents and administered on seven consecutive days to each member aged 5 years and above of the selected households.
Data collection is conducted in teams, each team consist of a supervisor, enumerators and a driver. Supervisors are responsible for the overall administrative work in the field including checking the quality of the questionnaires before departing from the cluster.
Field work The fieldwork is usually conducted on quarterly basis of three months intervals to capture seasonal variations of economic activities. Regular field visits for quality assurance is made by national and regional supervisors to ensure that the quality of work is maintained at all stages of
Statistical Methods, Standards and Guidelines 74
data production. This is intended to minimise errors made by enumerators who are instructed to make field edits at the household level as soon as they finish interviews.
Data Processing Data processing activities involve various stages which includes; reception of questionnaire from the field, questionnaire editing and coding, data entry using Census and Survey Processing system (CSPro), development of editing specifications lists, computer data editing using batch-edit application, data analysis and tabulation using Statistical Packages for Social Scientists (SPSS) or other packages.
4.11.3 Reference to applicable standard classifications Intergrated labour force survey follows the International reference classifications such as the Tanzania Standard Classification of Occupations (TASCO) and International Classification Activities for Time Use Statistics (ICATUS).
4.12 EMPLOYMENT AND EARNINGS SURVEY The Employment and Earnings Survey (EES) is an establishment-based survey conducted annually in Tanzania Mainland by the National Bureau of Statistics (NBS). The survey covers formal establishments with employees in both private and public sectors. The establishments are divided into three main categories which are all public sector establishments, all registered private establishments employing at least 50 persons and a sample of all registered private establishments whose number of employees are from 5 to 49 persons. The survey does not include domestic servants in Private households, non-salaried working proprietors and non-salaried family workers.
4.12.1 Objectives and uses of the EES The main objective of Employment and Earnings is to obtain a comprehensive data on the annual status of employment and earnings as well as data on socio-economic characteristics of the labour market.
Uses of the EES The findings of employment and earnings survey are used for estimating the labour market indicators that could be used for planning, policy formulation and examining the contribution to Gross Domestic Product (GDP) of different categories of employment.
Statistical Methods, Standards and Guidelines 75
4.12.2 Methodology of data production The Selection of Establishments The Employment and Earnings Survey uses the existing Statistical Business Register of Establishment (SBR) frame that was developed on the basis of International Standard Industrial Classification Revision 4 (ISIC Rev.4) and maintained by NBS. The selection of establishments from the SBR frame falls under the following groups: -
(i) All establishments of public sectors found in the current SBR frame are taken; (ii) All establishments of private sector with at least 50 employees found in the current SBR frame are taken; (iii) The list of surveyed establishments of private sector employing persons in the range of 5 to 49 is based on a sample.
The Sample Design The survey is covering all public sector establishments and private sector establishments with at least 50 employees. Furthermore, the survey covers a sample of private establishments employing 5 to 49 persons. The sampling for this group involves stratifying establishments into those with 5 to 9 employees and those with 10 to 49 persons. Establishments in these strata are further stratified on the basis of their economic activities and ultimately a single stage sampling technique is used to derive representative establishments from each activity using the probability proportion to size (PPS).
Survey instruments The most used survey instruments in EES are Questionnaire, instruction manual for data editors and coders.
Structure of the Questionnaire
Employment and Earnings Survey Questionnaire is divided into six main parts;
(a)
Identification
(i)
Name and address of establishment.
(ii)
Description of the main and secondary economic activities for the establishment.
(b)
Regular employees
(i) Employment and Earnings
§
Total regular employees by sex, citizenship, age group (adult and youth) and
disability.
§
Benefits for regular employees
Statistical Methods, Standards and Guidelines 76
§
Gross Earnings and Basic salary for Regular Employees by sex, age group and
citizenship.
(ii) Wage rates of citizens § Groups of wage rates with number of employees in each group by sex
(c)
Casual workers
(d)
Number of new workers recruited during the last 12 months.
(e)
Current Job Vacancies.
(f) Future Job vacancies in the next three years.
Training of Enumerators, data editors and data entrants. After completion preparations of survey instruments, training of enumerators and data coder follows. The minimum conditions in order for enumerators and data coders to qualify for the training is secondary education (O level) and have at least done one survey of Employment and Earnings.
Data collection Printed questionnaires accompanied with a list of selected establishments are usually sent to the Regional statistical offices in 26 regions of Tanzania Mainland. Each Regional Statistical Manager coordinates all the activities of distributing the questionnaires to the selected establishment, supervision of the fieldwork and mailing filled questionnaires back to NBS head office. Field visit for quality assurance are made by supervisors from head office. Data collection begins on 1st July up to 31st December of each year. The reference period for EES is at 30th June of each year.
Data are being collected by means of questionnaires delivered to the selected establishments through regional statistical offices. The data collected include; identification of establishments, regular employees, casual workers, number of new workers recruited and the current job vacancies. The Survey do not include the following:-
(i) Wage earners in seasonal small-holder agriculture
(ii) Employees in households
(iii) Members of the foreign diplomatic missions, corporation and international aid
organizations stationed in Tanzania
(iv) Members of armed forces
Statistical Methods, Standards and Guidelines 77
Data Processing report writing and dissemination Data processing for EES had several stages including; receiving and recording filled-in questionnaires from the regions, manual data cleaning, editing and validation, manual data coding, data entry using Census and Survey Processing system (CSPro), data cleaning, editing and validation using CSPro, table generation using SPSS or any other relevant software, and finally report writing and dissemination.
4.12.3 Reference to applicable standard classifications The Employment and Earnings Survey (EES) follow the International reference classifications such as the International Standard of Industrial Classifications (ISIC) and the Tanzania Standard Classification of Occupations (TASCO).
4.13 NATIONAL PANEL SURVEY The National Panel Survey (NPS) is a nationally representative household survey designed to collect information on the living standards of the population including socioeconomic characteristics, consumption, agricultural production, and non-farm income generating activities. The term “panel” means that the survey follows the original sampled population over time to track the evolution of its living conditions. The NPS is scheduled to have several rounds, since its inception 2008 there are four rounds that had been conducted. The first round of the survey (NPS 2008/09) was conducted from October 2008 to September 2009, the second round (NPS 2010/11) was carried out from October 2010 to September 2011, the third round (NPS 2012/13) took place from October 2012 to September 2013 and fourth round of the survey (NPS 2014/15) was conducted from October 2014 to September 2015.
4.13.1 Objectives and uses of the NPS The National Panel Survey (NPS) is intended to achieve multiple objectives. These objectives are:
The first objective is to track implementation progress across the three clusters of the National Strategy for Growth and Reduction of Poverty (commonly known by its Kiswahili acronym as MKUKUTA) which includes: Growth, reduction of poverty, improvement of quality of life and social wellbeing and governance and accountability. Assessing progress across the three clusters is possible because the NPS allows the estimation of many of these MKUKUTA II indicators by then although from 2016 poverty will be tracked by the indicators from SUSTAINABLE DEVELOPMENT GOALS (SDG 2030) and FIVE-YEAR DEVELOPMENT PLAN (FYDP
Statistical Methods, Standards and Guidelines 78
2016-2021).
The second objective is to provide a better understanding of the determinants of poverty reduction. The panel feature of the survey implies that information on the poverty status of households is available at different points in time, thus permitting the study of poverty dynamics at the household level. This is a key advantage with respect to the usual cross-sectional household surveys, which allow the monitoring of poverty at the aggregate level, say, by district or by region, but not at the household level given that they do not follow the same households over time.
The third objective of the NPS is to assess the impact of public policy initiatives. The NPS can be a powerful tool to evaluate the impact of development policies and programs implemented by the government or non-governmental institutions. If a person, household or community has been affected by a particular policy and has been sampled in the NPS, the survey may allow the estimation of indicators that capture that effect. Hence coordination with those who implemented these policies is crucial in order to determine both how the impact evaluation can be done and if complementary data are required.
Uses of NPS Apart from NPS to be a powerful tool to evaluate the impact of development policies and programs implemented by the government or non-governmental institutions, also the available data can be used for further analysis by researchers, students, higher learning institutions etc. Some analysis done through NPS data were: i. Child Poverty Analysis – NBS and UNICEF, ii. Tanzania Smallholder Livestock Sector – NBS and Ministry of Agriculture, Livestock and Fishery Development, iii. NPS data is being used in the Livestock Sector Analysis (LSA) in order to develop the Tanzanian Livestock Master Plan (TLMP), iv. Multidimensional Child Poverty Mapping - by NBS, REPOA and UNICEF
Statistical Methods, Standards and Guidelines 79
4.13.2 Methodology of data production
Frame of the Sample The sampling frame for NPS rounds is the recent available Population and Housing Census whereas, each time there is a new frame resulting from the Population and Housing Census, becomes an opportunity for refreshing the sample so as to utilize a new frame. For example, while the first three rounds of the NPS used the 2002 PHC frame, the fourth round’s sample (i.e. 2014/15) was refreshed and used the sampling frame of 2012 Population and Housing Census.
Sample Design The NPS is based on a stratified, multi-stage cluster sample design. The sample design of the NPS recognizes explicitly four analytical strata: Dar es Salaam, other urban areas in Mainland, rural areas in Mainland, and Zanzibar. Within each stratum, clusters are randomly selected as the primary sampling units, with the probability of selection proportional to size. In urban areas, clusters match census enumeration areas, while in rural areas, clusters match villages. In the last stage, 8 households are randomly chosen in each cluster.
Questionnaires The survey is made up of four questionnaires: Household questionnaire, Agricultural questionnaire, Livestock/Fisheries questionnaire and Community Questionnaire that is administered by the team supervisor capturing community level information.
Training of Field Staff:
The training is usually conducted in two stages: Training of Trainers (ToT) which involves quality
control personnel and supervisors, followed by training of interviewers which involve the
understanding of questionnaires in the classroom settings, mock interview, test for the
interviewers and field practice
Fieldwork The NPS fieldwork is implemented over a 12-month period to address concerns about intra-year seasonality since seasonal fluctuations can affect considerably the living standards of the population. The field team consists of a supervisor, data entry personnel, enumerators and a driver.