Come again? Trend tests are NOT employed for a continuous predictor variable, only for ordinal categorical variables. If you were to take your continuous predictor variable and chop it into some finite number of levels (greater than two, but usually less than or equal to five), then we could discuss performing a trend test. At the risk of sounding offensive, let me just put in my plug for working directly with a statistician. I am concerned that you do not really know what you are doing. If this is for real data which you must analyze for some scientific objective, then consultation with a statistician is critical. Of course, this could be part of a homework assignment, in which case SAS-L is not the place to seek cheap answers.

Dale

--- SASKID <s4a3s2k1id@WEB.DE> wrote: > Hi, > Is PROC LOGISTIC capable to do a a test for trend for continous data? > Or > better choose FREQ's CA? > TIA, SASKID

===== --------------------------------------- Dale McLerran Fred Hutchinson Cancer Research Center mailto: dmclerra@fhcrc.org Ph: (206) 667-2926 Fax: (206) 667-5977 ---------------------------------------

__________________________________________________ Do you Yahoo!? Yahoo! Tax Center - File online, calculators, forms, and more http://tax.yahoo.com