Is there a way to calculate the p-values from Cochran-Armitage Trend Test when I am only given frequencies like so:  data have; input dose $ response $ count; cards; 10ug yes 3 20ug yes 1 30ug yes 1 Plac yes 2 10ug no 1 20ug no 3 30ug no 4 Plac no 1 ; run; Or do I need the combinations repeating for proc freq data = have; tables dose*response / trend; run; ... View more

I see no errors in my SAS log, but the output is just a blank document that is "Read Only"?? I am not sure where the Read Only part comes from since I am the one who created this document and have had zero problem with other table documents. The latter may be a different problem. My main issue is that no results are being displayed. Below is a snippet of my log file.   362 /* ------------------------------------------------------------- Table 19 362! ------------------------------------------------------------- */ 363 data tab19; 364 set stresults; 365 where SPECTYPE = 'BREAST MILK'; 366 if PER_1 ^= . | PER_2 ^= . then output; 367 run; NOTE: There were 30 observations read from the data set WORK.STRESULTS. WHERE SPECTYPE='BREAST MILK'; NOTE: The data set WORK.TAB19 has 18 observations and 10 variables. NOTE: DATA statement used (Total process time): real time 0.01 seconds cpu time 0.03 seconds 368 369 %let w = 0.6in; 370 371 title; footnote; 372 373 ods listing close; ods html close; 374 options orientation = portrait; 375 ods escapechar = '^'; 376 ods rtf file = 'G:\VID\ANTIMICROBIALS\STAT\160076\24_Final 376! Reports\Tables\Tab_summ_stat_azi_breastmilk.rtf' bodytitle; NOTE: Writing RTF Body file: G:\VID\ANTIMICROBIALS\STAT\160076\24_Final Reports\Tables\Tab_summ_stat_azi_breastmilk.rtf 377 title1 h = 12pt f = 'Times New Roman' j = left bold "Summary Statistics for Azithromycin 377! Concentrations in Breast Milk by Obesity Status"; 378 379 proc report data = tab19 nowd split = '*' 380 %reportStyle; MPRINT(REPORTSTYLE): style(report)=[just=center cellspacing=1 font_face="times new roman" font_size=9pt outputwidth=100%] style(header)=[just=center font_size=2 background=white foreground=black font_face="times new roman" font_size=9pt] style(column)=[just=center font_size=2 background=white just=center font_face="times new roman" font_size=9pt] style(lines)=[font_size=2 background=white just=left font_face="times new roman" font_size=9pt]; MPRINT(REPORTSTYLE): footnote j=c h=12pt color=red bold "CONFIDENTIAL"; 381 382 column BMI STAT PER_1 PER_2 PER_4; 383 384 define BMI / order display 'BMI' format = BMI. style(column) = [just = left cellwidth = 384! 0.75in]; 385 define STAT / display 'Statistic' format = STAT. style(column) = [just = left cellwidth = 385! 0.75in]; 386 define PER_1 / display '0-<12 hours Post Start of Infusion' style(column) = [just = left 386! cellwidth = &w]; 387 define PER_2 / display '12-<24 hours Post Start of Infusion' style(column) = [just = left 387! cellwidth = &w]; 388 define PER_4 / display 'Any Time Post Start of Infusion' style(column) = [just = left 388! cellwidth = &w]; 389 390 compute after _page_/left; 391 line "Note: If more than one sample collected per time period, the mean breast milk 391! concentration by subject was summarized. The p-value is for a [insert test type] comparing 391! concentrations by obesity status and is only 392 computed if > 3subjects have a concentration within the time period for each group."; NOTE: The quoted string currently being processed has become more than 262 characters long. You might have unbalanced quotation marks. 393 endcomp; 394 395 run; NOTE: The quoted string currently being processed has become more than 262 characters long. You might have unbalanced quotation marks. NOTE: There were 18 observations read from the data set WORK.TAB19. NOTE: PROCEDURE REPORT used (Total process time): real time 0.10 seconds cpu time 0.07 seconds ... View more

I have two datasets that look like the following: I want to perform ANOVA only if there are more than 3 subjects in each BMI category for each time period (STPER, ENDPER). In my head it would be something along the lines of %if have.STPER > 3 (where BMI = 'Not Obese' and STAT = 'N') and have.STPER > 3 (where BMI = 'Not Obese' and STAT = 'N') and have.STPER > 3 (where BMI = 'Not Obese' and STAT = 'N') %then %do; proc glm data = have2; class BMI; model log(CONCEN) = BMI; means BMI / hovtest = levene welch; ods output welch = welch diff = pairs; run; /*repeat for ENDPER*/ I have very little experience with macros, so I'm not sure if what I am asking is possible. ... View more

I am not super familiar with Welch's ANOVA nor geometric means, so a detailed response is appreciated. I am interested in comparing concentrations among BMI groups (not obese, obese, severely obese) within two different time points (after start of treatment, after end of treatment). Since we are assuming unequal variances, I thought Welch's ANOVA would work well to check if at least one group is different. However, since geometric mean and geometric cv are what's being reported, I thought I should compare geometric means rather than arithmetic means. (1) Is there a way to compare geometric means using ANOVA? I know the geometric mean is the exponentiated mean of the log-transformed data, but I am unsure how to apply that to ANOVA. (2) Is it even necessary to use the geometric mean if I use Welch's ANOVA? (3) Is there a simple way to store the p-value from the output table, so I can add it to a summary table later on? My plan was to use PROC SQL to add a row to the bottom of my "Data Have" with a p-value. Generally, I want a table like this (will use PROC REPORT):   My datasets are organized like this:   xx represents some numerical value.   Thank you in advance!   ... View more

I am trying to use PROC MEANS to calculate arithmetic CV. However, it is only outputting the default statistics. I had this issue earlier with the median, where I had to do median independently then merge to other statistics. Does anyone have any insight on the possible reasoning?   Code:  proc means data = have n mean std cv max min noprint; class BMI PERIOD TRT; var CONCEN LN_CONCEN; output out = stats; run;  Thank you in advance. ... View more

Is there a simple way to average the repeated measures for a given measurement type during a certain time period for a specific subject? I think the simplest thing to do is to create a second concentration column ("CONCEN_AVG"). However, I am not sure how to implement this idea. Is there a simpler way than making multiple subsets? I would want the average of all the white blood cell counts during period 1 for subject 1, and so on.      Note: Measurements are arbitrary.   Thank you in advance!   ... View more

If I want to use PROC SQL to join to datasets, what is a quick way to reference a sequence of columns? That is, if dataset 1 has columns: ID, NAME, X1, X2, X3, X4, X5 and dataset 2 has columns:  ID, NAME, Y1, Y2, Y3, Y4, Y5, then how can I join data1.* with columns Y1 to Y5 on ID and NAME using PROC SQL? Is there a way similar to data steps Y1--Y5? Or would I need to write out every column? ... View more