geometric mean with SE, STD and CLM

[Claus_Stenberg]

Trying to get the geometric mean with  SE, STD and CLM on some clinical data and want the outputs stats to be saved as a SAS datafile for further processing. 

Was thinking of using proc surveymeans as I want the variance of the geometric mean to be estimated using the Taylor series. 

How do I get the relevant stats in the output dataset ?  

Below code only gives me the SE, STD and CLM to the arithmetic mean - NOT the geometric mean. 

Somebody that can help a newbie  to surveymeans ?   

A small example: 

proc sort data=sashelp.class out=test;
 by sex;
run;

proc surveymeans data=test alpha=0.05 geomean std stderr clm ;
 by sex;
 var age;
 ods output
   Statistics = stats_ds;
run;

[PaigeMiller · Accepted solution]

You can use ODS output to get any calculated statistics from any procedure into a SAS data set. Example:

proc surveymeans data=sashelp.class allgeo;
    ods output geometricmeans=geometricmeans;
    var height;
run;

[Claus_Stenberg]

Thanks. Simple and straight forward 🙂

[SteveDenham]

@PaigeMiller shows that you can get what you want using PROC SURVEYMEAN, but you can also get the CLM with a DATA step by exponentiating the confidence bounds of the log transformed data.  STD and SE are a different matter.  Read through Alex Kritchevsky's webpage.  It has formulas for calculating the variability estimates, and lots of cautionary items about the use of these measures.  See http://alexkritchevsky.com/2018/06/15/geometric-mean.html 

Alternatively, you could use PROC FMM to fit a non-mixture distribution of a lognormal distribution.  Use the OUTPUT statement to get a dataset with means and variances, and from those calculate standard deviations and standard errors.

In the end, though, @PaigeMiller  has the answer you requested.

SteveDenham