Providing software solutions since 1976

• Log in
• Create profile
• Welcome
  [Log out]
• Edit profile

• Print  |
• Feedback  |
• Share

  • E-mail

  
  
  

  E-mail This Page

  Your Name:*
  Your E-mail:*
  Recipient E-mail:*
  Send a copy to me
  Personal Message:
  
  

  * indicates a required field

The STAT/STAT survey procedures (SURVEYMEANS, SURVEYFREQ, SURVEYREG, and SURVEYLOGISTIC) provide analyses based on the sample design. These procedures can be used to analyze data from multistage designs or from single-stage designs, with or without stratification, with or without clustering, and with equal or unequal weighting.

To analyze your survey data with these survey procedures, you need to specify information about the sample design. This information includes design strata, clusters, and sampling weights. You provide sample design information with the STRATA, CLUSTER, and WEIGHT statements (see "Introduction to Survey Procedures" in the SAS/STAT User's Guide).

These procedures use the Taylor expansion method for estimating sampling errors of estimators based on complex survey designs. This method is appropriate for all designs where the first-stage sample is selected with replacement, or where the first-stage sampling fraction is small, as is often the case.

You can use the survey procedures to analyze survey data from any sample design of the following types:

If the first-stage selection is with replacement or without replacement but with a small sampling fraction, then you do not need any extra options to specify this because it is the default for the survey procedures. If the first-stage selection is without replacement (with a small to moderate sampling fraction), use either the TOTAL= option or RATE= option to specify the first-stage sampling fraction which will incorporate the finite population correction factor in the variance estimation. For more details, see the "Specification of Population Totals" and "Sampling Rates" sections in the documentation for the survey procedures.

¹ For a multistage sample design, when the first-stage sampling fraction is small, as is often the case, it is approximately valid to assume that the sample selection is performed with replacement, even when it is not. As a result, it is sufficient to estimate the variance using only the variance component for the first-stage sampling units (PSUs), ignoring the relatively insignificant components due to second-stage or higher sampling units (Kalton 1983, Korn and Graubard 1999).

The following survey designs are not currently supported by the survey procedures:

When first-stage selection (or single-stage sampling) is carried out without replacement and the sampling fraction is large, the "with replacement" approximation is no longer appropriate and the variance components among second-stage or higher sampling units cannot be ignored.

For more information about variance estimation for sample survey data, see Lohr (1999), Särndal, Swensson, and Wretman (1992), Lee, Forthofer, and Lorimor (1989), Wolter (1985), Cochran (1977), Kish (1965), and Hansen, Hurwitz, and Madow (1953).

References

Cochran, W. G. 1977. Sampling Techniques. 3d ed. New York: John Wiley & Sons.

Hansen, M. H., W. N. Hurwitz, and W. G. Madow. 1953. Sample Survey Methods and Theory. 2 vols. New York: John Wiley & Sons.

Kalton, Graham. 1983. Introduction to Survey Sampling. Sage University Paper Series on Quantitative Applications in the Social Sciences, series no. 07-035. Beverly Hills, CA, and London: Sage Publications.

Kish, L. 1965. Survey Sampling. New York: John Wiley & Sons.

Korn, Edward L., and Barry I. Graubard. 1999. Analysis of Health Surveys. New York: John Wiley & Sons.

Lee, E. S., R. N. Forthofer, and R. J. Lorimor. 1989. Analyzing Complex Survey Data. Sage University Paper Series on Quantitative Applications in the Social Sciences, series no. 07-071. Beverly Hills, CA, and London: Sage Publications.

Lohr, S. L. 1999. Sampling: Design and Analysis. Pacific Grove, CA: Duxbury Press.

Särndal, C. E., B. Swensson, and J. Wretman. 1992. Model Assisted Survey Sampling. New York: Springer-Verlag.

Wolter, Kirk M. 1985. Introduction to Variance Estimation. Berlin: Springer-Verlag.

Operating System and Release Information