Service Delivery Indicators Education Survey 2016 - Harmonized Public Use Data
This survey is part of the Service Delivery Indicators (SDI) project, an initiative led by the World Bank. SDI surveys track the quality of service delivery in primary schools and frontline health facilities across Africa and other regions of the world. The indicators can be used to track progress within and across countries over time and aim to enhance the active monitoring of service delivery to increase public accountability and good governance. Ultimately, the goal of the program is to support policymakers, citizens, service providers, donors, and other stakeholders in enhancing the quality of service delivery and improve development outcomes.
Since the inception of the initiative in 2010, twenty-six surveys have been completed in twelve countries in Africa, capturing the health and primary education service delivery experience of over 500 million people. The surveys have been extended in Africa (with SDIs in the pipeline or envisioned in Benin, DRC, Cameron, Madagascar, Ethiopia, Cote D’Ivoire, Gambia, Guinea Bissau, Malawi, and Mali) and beyond: data collection for the first SDI surveys in Latin America (Guatemala), East Asia/Pacific (Indonesia), Europe and Central Asia (Armenia, Moldova and Ukraine), Middle East and North Africa (Iraq), and South Asia (Bhutan) are underway or being considered.
With the exception of Module 3 (school finances), the datasets distributed here were harmonized to a common standard to facilitate comparisons across countries and over time. The data was also anonymized to preserve the confidentiality of the data of respondents. The harmonization and anonymization work were conducted by the SDI team at the World Bank.
SDI surveys are documented in the Microdata Library as Service Delivery Indicators Health Surveys and Service Delivery Indicators Education Surveys.
The Service Delivery Indicators (SDI) are a set of health and education indicators that examine the effort and ability of staff and the availability of key inputs and resources that contribute to a functioning school or health facility. The indicators are standardized allowing comparison between and within countries over time.
The Education SDIs include teacher effort, teacher knowledge and ability, and the availability of key inputs (for example, textbooks, basic teaching equipment, and infrastructure such as blackboards and toilets). The indicators provide a snapshot of the learning environment and the key resources necessary for students to learn.
Madagascar Service Delivery Indicators Education Survey was implemented from April 2016 (for enumerator training and pre-testing of the instruments) to May and June 2016 (for fieldwork and data collection) by CAETIC Development, a strong local think-tank and survey firm. The sampling strategy was done by INSTAT the national institute for statistics. Information was collected from 473 primary schools, 2,130 teachers (for skills assessment), 2,475 teachers (for absence rate), and 3,960 pupils across Madagascar. The survey also collected basic information on all the 3,049 teachers or staff that teach in the 473 primary schools visited or are non-teaching directors.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Schools, teachers, students.
v01, harmonized and anonymized data for public distribution.
The core Education Service Delivery Indicators are:
1) Teacher Effort:
- School absence rate
- Classroom absence rate
- Time spent teaching per day
2) Teacher Knowledge and Ability:
- Minimum knowledge among teachers
3) Availability of Inputs:
- Infrastructure availability
- Equipment availability
- Share of pupils with textbooks
- Observed pupil-teacher ratio
The survey also tests grade 4 pupils on mathematics, linguistics and non-verbal reasoning. Additionally, direct observations are made to assess firsthand classroom conditions as well as school inputs and infrastructure that teachers and students have readily available.
SDI instruments also include modules on school's finances and staff/teacher rosters that include their qualifications and demographic information.
Producers and sponsors
The World Bank
The World Bank
Madagascar SDI focal point
The World Bank
William and Flora Hewlett Foundation
The World Bank
A two-stage sampling method was adopted. First, in each stratum schools were chosen within the selected councils. Once at a selected school, the enumerator selected teachers and pupils depending on the structure of the classrooms.
The schools were chosen using probability proportional to size (PPS), where size was the number of standard two pupils as provided by the 2014 EMIS database. As for the selection of the cluster, the use of PPS implied that each standard four pupil within a stratum had an equal probability for her school to be selected.
Finally, within each school, up to 10 standard four pupils and 10 teachers were selected. Pupils were randomly selected among the grade-four pupil body, whereas for teachers, there were two different procedures for measuring absence rate and assessing knowledge. For absence rate, 10 teachers were randomly selected from the teachers’ roster and the whereabouts of those teachers was ascertained in a return surprise visit. For the knowledge assessment, however, all teachers who were currently teaching in primary four or taught primary three the previous school year were included in the sample. Then a random number of teachers in upper grades were included to top up the sample. These procedures implied that pupils across strata, as well as teachers across strata and within a school (for the knowledge assessment) did not all have the same probability of selection. It was, therefore, warranted to compute weights for reporting the survey results.
The sampling strategy for the SDI in Madagascar was done by INSTAT the national statistics office.
SDI survey estimates must be properly weighted using a sampling weight or expansion factor to estimate representativeness of the population of interest.
School, teacher, and pupil-level sampling weights are stored in the "MDG_2016_EDU_Weights.dta" file.
Dates of Data Collection
Data Collection Mode
The SDI Education Survey Questionnaire consists of six modules:
Module 1: School Information - Administered to the head of the school to collect information about school type, facilities, school governance, pupil numbers, and school hours. Includes direct observations of school infrastructure by enumerators.
Module 2a: Teacher Absence and Information - Administered to headteacher and individual teachers to obtain a list of all school teachers, to measure teacher absence, and to collect information about teacher characteristics.
Module 2b: Teacher Absence and Information - Unannounced visit to the school to assess absence rate.
Module 3: School Finances - Administered to the headteacher to collect information about school finances (this data is unharmonized).
Module 4: Classroom Observation - An observation module to assess teaching activities and classroom conditions.
Module 5: Pupil Assessment - A test of pupils to have a measure of pupil learning outcomes in mathematics and language in grade four.
Module 6: Teacher Assessment - A test of teachers covering mathematics and language subject knowledge and teaching skills.
Data quality control was performed in Stata.
Datasets have been cleaned, anonymized, and harmonized using Stata.
For some variables, missing observations were recoded and/or distinctly labeled as:
Skips: "-999", or ".a"
Don't Know: "999", "99", or ".b"
Confidential Information (Anonymized): "Confidential", or ".c "
Not Available: ".n"
HD Practice Group, The World Bank
HD Practice Group, The World Bank
Details about the anonymization process can be found in the documentation provided with these datasets.
The harmonized, anonymized datasets are available as public files (for use under a License).
Researchers who feel that they need non-anonymized data should contact firstname.lastname@example.org with a statement of research objectives and a rationale for why they require such data. That will start the Research Use File discussion.
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
Waly Wane, The World Bank. Madagascar Service Delivery Indicators Education Survey (SDI-E) 2016 - Harmonized Public Use Data, Ref. MDG_2016_SDI-E_v01_M_v01_A_PUF. Dataset downloaded from [URL] on [date].
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
Development Data Group
Documentation of the Study
Date of Metadata Production
DDI Document version