NCJ Number
249476
Date Published
December 2015
Length
58 pages
Annotation
This Appendix D from the "User's Guide to National Crime Victimization Survey (NCVS) Direct Variance Estimation" presents examples in SUDAAN (survey data analysis), which is a proprietary statistical software package for the analysis of correlated data, including correlated data encountered in complex sample surveys.
Abstract
In SUDAAN, the NCVS sample design must be appropriately specified for all SUDAAN procedures, using the "design" and "nest" statements. The "nest" statement is provided, since it must be included for the stratification and PSU variables. Weight statements are also required, but they vary depending on the type of estimate. Victimization rates also use the adjustment factor (ADJINC_WT), as outlined in the examples provided. Before interpreting results produced by SUDAAN, the design summary should always be examined to ensure that it matches with the input dataset and the specified design. Examples 1 and 2 demonstrate how to estimate the total number of victimizations. Examples 3 and 4 demonstrate how to calculate the proportion of victimizations with given characteristics. Examples are included for both single- and pooled-year estimates. Example 8 demonstrates how to identify low-quality estimates and implement the rounding recommended in "Section 4" of the user's guide.