Samples & SAS Notes > Analytics
>
Survey Sampling and Analysis
| Date | Title | Type | ||
|---|---|---|---|---|
| 11/20/09 |
37910 - Some samples cannot be reproduced with METHOD=PPS_SYS When using METHOD=PPS_SYS in PROC SURVEYSELECT and one of more numeric variables having a length less than 8 are specified on the CONTROL statement, then the output sample cannot be reproduced even when using the same ... http://support.sas.com/kb/37/910.html, 18KB |
Problem Note | ||
| 10/13/09 |
37377 - How can I sample from some of the strata in my data while ignoring others? In order to select a valid probability sample, every unit in the frame or input data set must have a positive selection probability. For PROC SURVEYSELECT, this means zero is not a statistically valid value for the ... http://support.sas.com/kb/37/377.html, 23KB |
Usage Note | ||
| 7/20/09 |
36569 - How do I run a Domain or Subgroup analysis in PROC SURVEYFREQ? PROC SURVEYFREQ does not have a DOMAIN statement, so in order to do a domain analysis you must add the subgroup variable to the TABLES statement. http://support.sas.com/kb/36/569.html, 19KB |
Usage Note | ||
| 7/10/09 |
36068 - Incorrect standard errors when format reorders CLASS levels in PROC SURVEYREG If a format is specified that changes the internal order of levels of a CLASS variable in PROC SURVEYREG and either METHOD=JK or METHOD=BRR is specified, then the standard errors for estimated regression coefficients ... http://support.sas.com/kb/36/068.html, 19KB |
Problem Note | ||
| 7/8/09 |
36478 - Why does an odds ratio confidence interval disagree with the parameter p-value or confidence interval? Under the default effects coding used the CLASS statement, a parameter for a CLASS predictor does not compare the effects of two predictor levels. Instead, it compares the effect of the associated predictor level with ... http://support.sas.com/kb/36/478.html, 21KB |
Usage Note | ||
| 6/23/09 |
36236 - With the REPS= option in PROC SURVEYSELECT, some units appear in more than one sample. How can I select several mutually exclusive samples? The REPS= (or REP=) option in PROC SURVEYSELECT takes independent samples using the same sample design, so by definition each sample is selected from the same original frame or input data set. This means duplication is ... http://support.sas.com/kb/36/236.html, 35KB |
Usage Note | ||
| 1/29/09 |
34607 - How can I compare means in PROC SURVEYMEANS? PROC SURVEYMEANS does a univariate analysis, and so it does not provide any tests for comparing means of different variables or domains. You can use PROC SURVEYREG to compare means instead. Example The following DATA ... http://support.sas.com/kb/34/607.html, 67KB |
Usage Note | ||
| 10/16/08 |
23087 - Why are the reported odds ratios not equal to exp(beta)? If the variable in question is listed in the CLASS statement, and you do not select reference (also called indicator or dummy) coding for it by specifying the PARAM=GLM or PARAM=REF option, then the default effects ... http://support.sas.com/kb/23/087.html, 18KB |
Usage Note | ||
| 9/29/08 |
33288 - PROC SURVEYMEANS computes incorrect degrees of freedom if the same variable is used on both the STRATA and DOMAIN statements If the same variable is specified on both the STRATA and DOMAIN statements in PROC SURVEYMEANS, the degrees of freedom and related statistics will be incorrect for any domain analysis involving that variable. The ... http://support.sas.com/kb/33/288.html, 20KB |
Problem Note | ||
| 9/16/08 |
33317 - How can I get stratum-level estimates in PROC SURVEYMEANS? If you have a stratified survey design and wish to compute summary statistics within each stratum, you can specify the strata variable(s) on a BY statement in PROC SURVEYMEANS. Since the strata are a part of the survey ... http://support.sas.com/kb/33/317.html, 21KB |
Usage Note | ||
