|
Abstract:
|
This workshop will cover using Stata for survey data analysis, i.e. data arising from designed samples from a fixed population. We will briefly introduce the sampling methods used to collect survey data, demonstrate how to tell Stata about these methods, and discuss how they affect common estimators, such as totals, ratios, and regression coeffcients. We will then show how variance estimates incorporating the sampling design can be computed simply by using the svy prefix command. Finally, we will talk about poststratification, calibration, subpopulation estimation, and visualizing models in some detail, including how to work with certainty sampling units and strata with a single sampling unit. Each topic will be illustrated with an example in a Stata session. Knowledge of Stata is not required, but basic statistical knowledge, such as topics covered in an introductory statistics course, is assumed.
|
