The performance evaluation of the COSDEC subactivity integrated a qualitative analysis and a quantitative outcomes analysis. The qualitative analysis explored implementation of the subactivity, how it evolved after the compact, and its sustainability. It relied on two rounds of qualitative data: one conducted close to the end of the Namibia compact, and a second conducted about a year later. The qualitative data drew on focus groups with COSDEC trainees and interviews with COSDEC managers, the COSDEF (the body that oversees the COSDECs), implementers, employers, and other stakeholders. The outcomes analysis sought to describe the characteristics and outcomes of enrollees in the seven new or renovated COSDECs. It relied on a survey of COSDEC enrollees that collected information about their training and labor market outcomes about one year after the end of COSDEC training. The COSDEC enrollee survey and the second round of qualitative data informed the final COSDEC evaluation report. (The findings from the first round of qualitative data were provided in an interim evaluation report covering all three subactivities.) The data from the COSDEC enrollee survey are available for public use, but the qualitative data are not because of the risks to confidentiality.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Anonymized dataset for public distribution
Version 02 is the edited version produced by Development Data Group (The World Bank) based on Version 01 (DDI-MCC-NAM-MPR-COSDEC-2017-v1) that was done by Millennium Challenge Corporation. Data was downloaded from https://data.mcc.gov/evaluations/index.php/catalog/199/
The survey covered the following topics:
- Confirm respondent
- Employment and earnings
- Income and household demographics
- Demographic information
- Health behaviors
Vocational education and training
Vocational education and training
COSDEC providers throughout Namibia.
All enrollees in the 36 national courses that started in the seven new and renovated COSDECs between July and December 2014.
Producers and sponsors
Mathematica Policy Research
Millennium Challenge Corporation
The targeted sample for the COSDEC evaluation consists of all 934 enrollees in the national courses that started in the seven new and renovated COSDECs between July and December 2014. Of these enrollees, 642 completed a survey, and constitute the analytic sample used for the analysis.
Deviations from the Sample Design
Based on a request from COSDEF, we also administered the survey to enrollees in COSDEC Benguela (Lüderitz)--the only COSDEC not affected by the subactivity. COSDEF funded this additional data collection because they wanted comparable data and summary statistics for all the COSDECs in Namibia for their internal purposes, but our evaluation only covered the seven new and renovated COSDECs. Because data for COSDEC Benguela were entirely outside the evaluation, we have excluded this COSDEC from the public use dataset. The appendix to the COSDEC final report contains additional information about the data for COSDEC Benguela.
The response rate to the follow-up survey in the seven new or rennovated COSDECs was 68.7 percent.
No weights were used in the main analysis.
However, as a robustness check, we estimated results using non-response weights. These weights were designed to make the weighted sample reflect the applicant sample in terms of its distribution across trainings. To create these weights, we weighted each respondent by the inverse of the response rate in the training in which they enrolled. We then top-coded these weights at 3 standard deviations above the mean for the full sample to account for outliers and normalized the sum of the weights to equal the number of observations. The non-response weight variable is called t1_weight. The results applying these weights were very similar to the unweighted results.
Dates of Data Collection
Data Collection Mode
Computer Assisted Telephone Interview [cati]
The data were collected by a handful of interviewers who worked from Survey Warehouse( SW) office in Windhoek. These were supervised by a senior on-site SW staff member. Mathematica staff provided support as required.
Data Collection Notes
The COSDEC survey was conducted by Survey Warehouse from January to June 2016, with oversight from Mathematica. Interviews were conducted in English, Afrikaans, Oshiwambo, Otjiherero, or Rukwangali using a computer-assisted telephone interview system. Although the plan was for the survey to occur roughly one year after the scheduled end of each training, in practice the timing varied somewhat (between 12 and 16 months). However, the median was one year after the end of training (12 months).
The COSDEC survey was developed by Mathematica, and was a computer-assisted survey that was conducted by telephone. The survey was developed in English and was translated into Afrikaans, Oshiwambo, Otjiherero, and Rukwangali; the translated versions were used for respondents who were not comfortable in English. The survey included the following modules: (1) education and vocational training; (2) employment and earnings; (3) income and household demographics; and (4) health behaviors (related to HIV/AIDS and pregnancy).
Mathematica conducted cleaning of the raw data file in Stata, which included checking the validity of variable values and ranges; verifying skip patterns; cleaning and back-coding common "other-specify" responses; creating binaries of categorical variables; and recoding skips, missing data, and other non-response values to standardized lettered indicators. Mathematica then merged these data with sample information related to the COSDEC training in which each individual was enrolled (for example, provider, course name, and course duration).
Survey Warehouse enumerators directly entered survey responses into the web based system, allowing for real time logic and consistency checks. SW placed a strong emphasis on gathering high quality data from respondents. To this end, multiple supervision and quality control measures took place:
1. The supervisors regularly reviewed cases to ensure surveys were properly completed, consistent, and that the respondent was correctly identified.
2. During data collection supervisors back-checked 15 percent of the sample, spread out evenly across all the enumerators. For the back-checks, supervisors called the survey respondents to ask them key survey questions using a validation form. This validation form includes information such as confirmation that the interview took place; the approximate time taken by the interview; and checking critical variables for completeness. The responses obtained during validation were data entered by SW staff for comparison to responses obtained during the interview itself.
3. Supervisors observed (involving listening in on) 5 percent of interviews to ensure the proper execution of the survey and provide constructive feedback to enumerators.
4. While conducting interviews, enumerators used a paper-based form to track issues such as item non-response or system/computer errors during the interview, and entered the data directly into a comment section once the interview was complete.
Estimates of Sampling Error
The survey data were intended to cover the universe of applicants to the included trainings, and did not involve any sampling. The only source of error in the estimated means is survey non-response. Users can therefore rely on standard formulae to calculate the sampling error for the estimated means.
Monitoring & Evaluation Division of the Millennium Challenge Corporation
Public use files, accessible to all.
Use of the dataset must be acknowledged using a citation which would include:
- the Identification of the Primary Investigator
- the title of the survey (including country, acronym and year of implementation)
- the survey reference number
- the source and date of download
Borkum, Evan, Arif Mamun, and Malik Mubeen."Evaluation of the Community Skills Development Centres (COSDEC) Subactivity Outcomes Survey, 2016". Data submitted to the Millennium Challenge Corporation. Washington, DC: Mathematica Policy Research, September 2017.
Disclaimer and copyrights
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.
DDI Document ID
Mathematica Policy Research
Development Data Group
The World Bank
Date of Metadata Production
DDI Document version
Version 02 (April 2018) Edited version based on Version 01 (DDI-MCC-NAM-MPR-COSDEC-2017-v1) that was done by Millennium Challenge Corporation.
- Datasets provided and literal questions added
- External resources provided
Version 1 (September 2017)