A data archive for demography and population sciences

# Analyze & Subset--Study No. 4157

Title: National Survey of Family Growth, Cycle VI, 2002

## Online Analysis Using SDA

The online analysis system allows you to run both simple and complex analyses, recode and compute new variables, and subset variables or cases for downloading. The software powering the system, named Survey Documentation and Analysis (SDA), was developed by the Computer-assisted Survey Methods Program (CSM) at the University of California, Berkeley.

Click on the link(s) below to begin using SDA.

## Weight

Please note that weights may affect analysis results.

A simple random sample in which response rates and coverage were the same in every sub-group would be a "scale model" of the population. However a survey sample is almost never a scale model in that sense. Groups are often selected at different rates and often have different response rates. For example, in the NSFG, non-Hispanic black men and women account for 19.6 percent of all respondents in the sample but only 12.9 percent of the population 15-44 years of age. "Sampling weights" adjust for these different sampling rates, response rates, and coverage rates so that accurate national estimates can be made from the sample. A respondent's sampling weight can be interpreted as the number of persons in the population that he or she represents. For example, if a woman's sampling weight is 8,000, then she represents 8,000 women in the population. For the NSFG, the fully adjusted sampling weights were assigned to each respondent and consisted of 4 factors. The first factor is the inverse of the probability that the case was selected. For example, if the probability of selection is 1 in 6,000, then the initial sampling weight is 6,000. The second factor is an adjustment for nonresponse, which was calculated separately based on the probability of completing a screener, and the probability that a completed screener would result in a completed interview. The third factor is an adjustment to control totals of the number of persons by age, sex, race and Hispanic origin, provided by the US Census Bureau. This process is called post-stratification. The fourth factor is trimming, which reduces the values of a few extremely large weights.

If you're having trouble with SDA utilities, you may wish to consult the online help files for SDA users provided by the Computer-assisted Survey Methods Program (CSM) at the University of California, Berkeley.