DHS surveys collect a wealth of information on a wide range of topics from a representative sample of the population in the countries that participate in The DHS Program. For each country, the information collected is processed, tabulated, and presented in a report that describes the living conditions and the demographic and health situation in the country. Before producing the tables, many steps are necessary to ensure that the data properly reflect the situation they intend to describe. This involves editing the data for consistency, imputation of key dates of events, weighting the sample results, considering such factors as the sample design and response rates, calculating the wealth index, and constructing accurate summary variables.
Many of the procedures involved are straightforward and are familiar to demographic analysts. However, other procedures need special attention and have been developed on the basis of experience accumulated over many years regarding the preferred way of calculating certain indicators, what to guard against, and what not to forget.
This Guide to DHS Statistics is meant to be a tool for all data users. It can be an aid for those who are just starting out in data analysis, a tool for checking procedures for those whose skills are more advanced, and a reference document for all who deal with data generated by The DHS Program surveys. Even those who do not analyze data using a statistical software package can benefit from a deeper understanding of the definitions of these indicators and a closer examination of the numerators and denominators.
I hope that this valuable tool will significantly increase the capacity of many researchers to do their own tabulations and analyses. I trust that it will help make data users aware of the precautions to take and the procedures that need to be followed to ensure that indicators are calculated correctly. It should also ensure that the strengths and limitations of certain data and indicators are clear to all users.
Sunita Kishor
Project Director