1406.0.55.002 - User Manual: ABS Remote Access Data Laboratory (RADL), Mar 2006
Latest ISSUE Released at 11:30 AM (CANBERRA TIME) 22/02/2012  Reissue
Page tools: Print All RSS Search this Product
Contents >> Frequently asked questions >> Survey and replicate weights

SURVEY AND REPLICATE WEIGHTS

How should I use survey weights in my model?
How do I use normalization with SAS, SPSS and Stata?
How can I use the replicate weights in analysis or estimation of sampling error?
What parameters do I use with the svr suite of commands in Stata?
Where can I find useful references on the use of survey weights in modelling?

How should I use survey weights in my model?
Survey weights are most commonly used to produce estimates of aggregates, means, and quantiles for a population. The use of weights for more complex survey analysis is less clear-cut. There is no one unified view by statisticians on if, and how, weights should be used when undertaking a modelling exercise.

The decision whether to use weights or not could have an effect on point estimates produced from the model, not only in terms of magnitude but possibly also in terms of sign and significance. Standard errors of these estimates will also differ in magnitude depending on whether weights are used. In general, use of survey weights in the model should lead to accurate point estimates. However, the standard errors of these estimates will not tend to be as accurate.

One approach that may help in partially addressing the issue of less accurate standard errors is to first normalize the weights. Normalizing of weights involves multiplying the weight of each person by a constant factor so that they add up to a desired value. For the purposes of survey analysis, it is common to normalize the weights to add up to the sample total. It is suggested that normalized weights be calculated at state level where possible due to the different sampling fractions that are used in each state.

State-level normalized weights can be calculated by multiplying the person weight of an individual within state h by the proportion of people in the state that were in the sample:

How do I use normalization with SAS, SPSS and Stata?
Support for normalized weights in modelling varies for each of the different software packages available in the RADL.

SAS
When using the LOGISTIC or PHREG procedures, users may specify an option /NORMALIZE when using the 'weight' statement. This will cause the weights specified by the 'weight' statement to add to the total sample size. Note that this option does not necessarily produce normalized weights at state level.

SPSS
Minimal support for normalized weights.

Stata
When producing some models, Stata will rescale the specified weights to add to the total sample size.

How can I use the replicate weights in analysis or estimation of sampling error?
While SAS v9.1 provides the PROC SURVEYMEANS procedure and Stata v10 provides the svy suite of commands, these facilities do not use replicate weights. Rather than using replicate weights these facilities require identification of both stratification and clustering. To help protect against disclosure of individuals, these details have not been included on the CURF. The user written svr suite of procedures is available for RADL Stata users. These procedures are made available but are not supported by the ABS.

What parameters do I use with the svr suite of commands in Stata?
The methodology used should be set to jk1:
svrset set meth jk1
The ABS uses the delete 1 group jackknife method rather than the unstratified delete 1 jackknife method that jk1 specifies. However this setting, when used in conjunction with the other parameters below, produces suitable estimates of variance of estimates.

The other parameters will vary depending on the variable names for the primary and the replicate weights and the number of replicate weights. For example, if the primary weight on the CURF was ‘PRSNWGHT’, and if there were 30 replicates groups and the replicate weights were named RW1 to RW30, then the remaining parameters would be set using:
svrset set pw PRSNWGHT
svrset set rw RW*
svrset set dof 29
Note that the dof parameter should be set to the number of replicate groups minus one.

Refer to the technical information for further information about the weights on your CURF, via the 'CURF reference documentation' link in the navigator of the RADL.

A useful summary of replicate weights is available in the Stata help documentation: http://www.ats.ucla.edu/stat/stata/Library/replicate_weights.htm

Where can I find useful references on the use of survey weights in modelling?
The following references may assist your decision on whether or not to use survey weights for your particular purpose. They have been selected as a cross-section of discussion on the issue of using weights in models.

Chambers, R.L. and C.J. Skinner (eds.) (2003), Analysis of Survey Data, Chichester: Wiley.

DuMouchel, W.H. and G.J. Duncan, (1983) "Using Sample Survey Weights in Multiple Regression Analyses of Stratified Samples", Journal of the American Statistical Association, Vol. 78, No. 383. (September), pp. 535-543.

Magee, L., Robb, A.L., and J. B. Burbidge, (1998), "On the use of sampling weights when estimating regression models with survey data", Journal of Econometrics, Volume 84, Issue 2 (June), Pages 251-27.1

Pfeffermann, D. (1993), "The Role of Sampling Weights When Modeling Survey Data", International Statistical Review, Vol. 61, No. 2. (August), pp. 317-337.

Pfeffermann, D (1996), "The Use of Sampling Weights for Survey Data Analysis", Statistical Methods in Medical Research, 5, pp. 239-261.

Skinner, C.J., Holt, D., and T.M.F Smith (1989), Analysis of Complex Surveys, Chichester: Wiley.

Winship, C., and L. Radbill (1994), "Sampling Weights and Regression Analysis." Sociological Methods and Research 23(2):230-257.

 Previous Page Next Page