LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (July 2002, week 1)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Fri, 5 Jul 2002 09:57:52 -0700
Reply-To:   "Meg A." <napu1975@HOTMAIL.COM>
Sender:   "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:   "Meg A." <napu1975@HOTMAIL.COM>
Organization:   http://groups.google.com/
Subject:   proc rank problem
Content-Type:   text/plain; charset=ISO-8859-1

I am looking at the quintiles of a predicted outcome from many different models. When i use proc rank to divide into quintiles, one of the datasets from a model is only giving me four categories (leaving the 2nds quintile out). This is the data i get...as you can see it is excluding the second quintile (from model_1_1). Does anyone have an idea as to why this is happening? Thanks!!!

Meg

quintiles for yhat- model 1_1_98

The FREQ Procedure

Rank for Variable y1hat

Cumulative Cumulative rank_yhat Frequency Percent Frequency Percent &#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402; 1st Quintile 15248 29.07 15248 29.07 3rd Quintile 15286 29.14 30534 58.21 4th Quintile 13789 26.29 44323 84.49 5th Quintile 8136 15.51 52459 100.00

quintiles for yhat -model 2_1_98

The FREQ Procedure

Rank for Variable y1hat

Cumulative Cumulative rank_yhat Frequency Percent Frequency Percent &#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402;&#402; 1st Quintile 11234 21.41 11234 21.41 2nd Quintile 9743 18.57 20977 39.99 3rd Quintile 10498 20.01 31475 60.00 4th Quintile 10492 20.00 41967 80.00 5th Quintile 10492 20.00 52459 100.00

And Here is the Log:

2699 proc rank group=5 data=model_1_1_98 out=testing 2700 (keep=id y1hat rank_yhat); 2701 var y1hat; 2702 ranks rank_yhat ; 2703 format rank_yhat quintile.; WARNING: Variable RANK_YHAT not found in data set WORK.MODEL_1_1_98. 2704 run;

NOTE: There were 52459 observations read from the dataset WORK.MODEL_1_1_98. NOTE: The data set WORK.TESTING has 52459 observations and 3 variables. NOTE: PROCEDURE RANK used: real time 9.67 seconds cpu time 1.05 seconds

2705 2706 proc rank group=5 data=model_2_1_98 out=testing2 2707 (keep=id y1hat rank_yhat); 2708 var y1hat; 2709 ranks rank_yhat ; 2710 format rank_yhat quintile.; WARNING: Variable RANK_YHAT not found in data set WORK.MODEL_2_1_98. 2711 run;

NOTE: There were 52459 observations read from the dataset WORK.MODEL_2_1_98. NOTE: The data set WORK.TESTING2 has 52459 observations and 3 variables. NOTE: PROCEDURE RANK used: real time 11.15 seconds cpu time 1.18 seconds

2712 2713 2714 proc freq data=testing; 2715 tables rank_yhat; 2716 title; 2717 title2 'quintiles for yhat- model 1_1_98'; 2718 run;

NOTE: There were 52459 observations read from the dataset WORK.TESTING. NOTE: PROCEDURE FREQ used: real time 0.05 seconds cpu time 0.04 seconds

2719 2720 2721 proc freq data=testing2; 2722 tables rank_yhat; 2723 title; 2724 title2 'quintiles for yhat -model 2_1_98'; 2725 run;

NOTE: There were 52459 observations read from the dataset WORK.TESTING2. NOTE: PROCEDURE FREQ used: real time 0.08 seconds cpu time 0.05 seconds


Back to: Top of message | Previous page | Main SAS-L page