The user’s manual states that in order to compare estimates we need to use correct standard errors, which can be generated using replicate weights. What and where are the replicate weights and how do I use them?
To compute correct standard errors for comparing estimates, it is crucial to account in some manner for the complex survey design. Relying on methods that assume a simple random sample will typically underestimate the true sampling error associated with estimates from the NHTS. Replicate weights are provided to allow you to correctly compute estimates of standard errors using appropriate software such as WesVar, SUDAAN, and others. SuperTABLE is not able to provide standard error estimates using replicate weights. The comma-delimited ASCII files supplied on this CD-ROM contain the replicate weights. For more on how to use the ASCII files, see Appendix C of the User’s Guide. For more on standard errors, see the statistical primer and Chapter 7 of the User’s Guide.
Related Questions
- Why are the standard errors/confidence intervals in my AskCHIS estimates different compared to those I find using the Public Use Files?
- My user manual says that the EDH-29 dry-cell case comes standard with the radio DJV5. Why did mine not have one ?
- How does one obtain standard errors and t-ratios for the parameter estimates in an interactive model?
