The types of datasets generated for each survey vary by survey design however there are seven common types of recode data files associated with the core questionnaires. DHS questionnaires allow different units of analysis (i.e., households, household members, women, children etc.) and they are ultimately translated into datasets. Work is currently under way for a recode definition for SPA surveys. Recode definitions are available for the DHS, AIS and MIS surveys. However, variables that are common across phases keep their names and the names of variables that are removed from a phase are not reused unless reinstated in another phase. Because of changes in questionnaires between DHS phases, there is a different recode definition for each phase. Recode files have standard data definitions across countries and across DHS phases. In order to facilitate the analysis of data, DHS has developed the concept of recode files. Geographic data are distributed in a format designed for use with GIS software packages. A recode data file uses a standardized data definition in order to facilitate comparisons across surveys, and is distributed in several different file formats for use with statistical software packages. A raw data file includes the data as they were collected, without any structural changes. Survey Data and HIV Data from DHS surveys are generally distributed in recode format, but may occasionally be distributed in raw format. It is important to note that there is an additional requirement for GPS/HIV dataset requests. HIV Test Results and Geographic Data are available for most surveys conducted in recent years. Survey Data can comprise many different types of data depending on individual survey design. Dataset types are organized into three distribution categories: Survey Data, HIV Test Results, and Geographic data. These types vary by individual survey, but are based upon the types of data collected and the file formats used for dataset distribution. The DHS Program produces many different types of datasets.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |