Descriptive Analysis for Continuous Variables
Estimation of totals, means, variances, and other distributional statistics for survey variables may be the primary objective of an analysis plan or possibly an exploratory step on a path to a more multivariate treatment of the survey data. Major reports of survey results can be filled with detailed tabulations of descriptive estimates. This chapter describes techniques for generating population estimates of descriptive parameters for continuous survey variables. It examines features that distinguish descriptive analysis of complex sample survey data from more standard descriptive analyses of simple random samples or convenience samples. The chapter also describes basic methods and examples of estimating important descriptive parameters for univariate, continuous distributions and methods for studying simple bivariate relationships between two continuous survey variables. It concludes with coverage of methods for descriptive estimation for subpopulations and estimation of simple linear functions of distributional statistics such as differences of means.