Services Research Outcomes Study (SROS)

1. PREPARATION OF UNBIASED ESTIMATES OF TARGET POPULATION: SUDAAN

PREPARATION OF UNBIASED ESTIMATES OF TARGET POPULATION: SUDAAN

The estimates and analyses in this report were calculated using the Survey Data Analysis software package (SUDAAN). SUDAAN (Shah, Barnwell, Hunt, and LaVange, 1993) is a data analysis system that adjusts the standard errors for a set of data collected using complex sampling designs. This correction employs a Taylor Series algorithm to correct for the bias introduced by stratified, clustered sampling designs such as that employed in the SROS study. Under this type of probability sampling, the statistics one calculates are often more variable than those based on data from a simple random sample of the same size. Conventional statistical packages such as SAS and SPSS assume simple random sampling and may yield misleading statistical estimates when the data come from a more complex sampling design.

This page was last updated on June 03, 2008.

SAMHSA, an agency in the Department of Health and Human Services, is the Federal Government's lead agency for improving the quality and availability of substance abuse prevention, addiction treatment, and mental health services in the United States.