Introduction to Survey Sampling and Analysis Procedures


The SURVEYMEANS procedure produces estimates of population means and totals from sample survey data. The procedure also computes estimates of proportions for categorical variables, estimates of quantiles for continuous variables, estimates of geometric means for positive continuous variables, and ratio estimates of means and proportions. For all these statistics, PROC SURVEYMEANS provides standard errors, confidence limits, and t tests when appropriate.

PROC SURVEYMEANS provides domain analysis, which computes estimates for domains (subpopulations), in addition to analysis for the entire study population. Formation of subpopulations can be unrelated to the sample design, and so the domain sample sizes can actually be random variables. Domain analysis takes this variability into account by using the entire sample to estimate the variance of domain estimates. Domain analysis is also known as subgroup analysis, subpopulation analysis, and subdomain analysis.

PROC SURVEYMEANS also performs poststratification, which adjusts the sampling weights so that their distribution matches known auxiliary information. Poststratification is often used to improve the efficiency of the analysis and adjust for nonresponse. PROC SURVEYMEANS provides poststratified analyses and also produces poststratified weights that can be used in the other survey analysis procedures. For more information about poststratification, see Fuller (2009); Lohr (2010); Wolter (2007); Rao, Yung, and Hidiroglou (2002).

PROC SURVEYMEANS uses ODS Graphics to create graphs as part of its output. Available statistical graphics include histograms and summary panel plots for continuous variables, box plots, and domain box plots.

For more information, see ChapterĀ 99: The SURVEYMEANS Procedure.