Multiple proc freq- proc report -order of categories

[Ronein]

Hello

The following code (macro) obtain multiple  chi-square test .

I want to ask please about the proc report.

I want that the order of categories will be as following:

Smoking Status- non smoker, light, moderate,heavy,very heavy

blood pressure status-optimal,normal,high

weight status-underweight ,normal,overweight

How can I change the order of the categories?

%macro mmacro1(pred,i); 
proc freq data=sashelp.heart;  
tables &pred*Status/chisq sparse outpct out=outfreq&i ;
output out=stats&i chisq;
run;

proc sort data = outfreq&i; 
by &pred; 
run;

/*calculate Totals for each category of predict var*/
proc means data=outfreq&i noprint; 
by &pred;  
var COUNT; 
output out=moutfreq&i(keep=&pred total rename=(&pred=variable)) sum=total;
run;

/*display  the  percentage  and  number  of  individuals  in  each  group*/
data routfreq&i(rename = (&pred = variable));   
set outfreq&i; 
length varname $20.; 
IF status='Dead' and &pred ne '';
rcount = put(count,8.);  
rcount = "(" || trim(left(rcount)) || ")"; 
pctnum = round(pct_row,0.1) || " " || (rcount);
index = &i; 
varname = vlabel(&pred); 
keep &pred pctnum index varname;
run;

/*We wish to present precise p-values with significant values indicated.*/
data rstats&i;  
set stats&i; 
length p_value $8.; 
if P_PCHI <= 0.05 then do;  
p_value = round(P_PCHI,0.0001) || "*"; 
if P_PCHI < 0.0001 then p_value = "<0.0001" || "*"; 
end;   else p_value = put(P_PCHI,8.4); 
keep p_value index;   index = &i;
run;


proc sort data = moutfreq&i;
by variable;
run;

proc sort data = routfreq&i; 
by variable; 
run;   

data temp&i;  
merge moutfreq&i routfreq&i; 
by variable; 
IF variable ne '' or variable ne . then output;
run; 

data final&i; 
merge temp&i rstats&i; 
by index;  
if not first.index then do; 
varname = " "; 
p_value = " "; 
end;     
run; 
%mend;
%mmacro1(sex,1);
%mmacro1(Chol_Status,2);
%mmacro1(Weight_Status,3);
%mmacro1(Smoking_Status,4);
%mmacro1(BP_Status,5);
%let number_Pred_Vars=5;

/*Combine data sets*/
%macro sset(j,k,dataname);
%do i=&j %to &k; 
&dataname&i   %end;
%mend; 



data categ_chdd; 
length variable $100;
set %sset(1,&number_Pred_Vars.,final);
label total="Freq" 
variable='Variable' 
p_value="p-value*(2 sided)" ;   
run; 



proc report data = categ_chdd nowd split = "*";
column index varname variable  total pctnum p_value;
define index /group noprint; 
compute before index; 
line ' '; 
endcomp; 
define varname / order = data style(column) = [just=left] width = 40; 
define variable / order = data style(column) = [just=left] width = 40; 
define total   / order = data style(column) = [just=center]; 
define pctnum  / order = data style(column) = [just=center]; 
define p_value / order = data style(column) = [just=center];  
title1 "TABLE 1A";  
title2 "CROSSTABS OF CATEGORICAL VARIABLES WITH CORONARY HEART DISEASE OUTCOME"; 
run; 

[andreas_lds]

---

@Ronein wrote:

Hello

The following code (macro) obtain multiple  chi-square test .

I want to ask please about the proc report.

I want that the order of categories will be as following:

Smoking Status- non smoker, light, moderate,heavy,very heavy

blood pressure status-optimal,normal,high

weight status-underweight ,normal,overweight

How can I change the order of the categories?

---

Please post an extract of the dataset used by proc report. Normally you don't have text in categorical variables, but an id and the text is displayed by applying a format. If you define a format in the required order and use "notsorted" option, see doc of proc format for details (https://documentation.sas.com/?docsetId=proc&docsetTarget=p1upn25lbfo6mkn1wncu4dyh9q91.htm&docsetVer...)

[Ronein]

In this example in column  "Variable" there are categories from multiple origin variables

[Ronein]

I want to perform multiple proc freq's and order the categories for each varaible by the proc format .

I get error

May anyone find the problem and provide a code 

proc format;
value $Fm1t ( notsorted)
'Male'='M'
'Female'='F';
Run;

proc format;
value $Fm2t ( notsorted)
'Desirable'='Desirable'
'Borderline'='Borderline'
'High'='High';
Run;

proc format;
value $Fm3t ( notsorted)
'Underweight'='Underweight'
'Normal'='Normal weight'
'Overweight'='Overweight';
Run;

proc format;
value $Fm4t ( notsorted)
'Non-smoker'='Non-smoker'
'Light (1-5)'='Light Smoker (1-5)'
'Moderate (6-15)'='Moderate Smoker(6-15)'
'Heavy (16-25)'='Heavy Smoker(16-25)'
'Very Heavy (> 25)'='Very Heavy Smoker(> 25)';
Run;

proc format;
value $Fm5t ( notsorted)
'Optimal'='Optimal Blood Pressure'
'Normal'='Normal Blood Pressure'
'High'='High Blood Pressure';
Run;

Data heart;
set sashelp.heart;
Format sex $Fm1t.
Chol_Status $Fm2t.
Weight_Status $Fm3t.
Smoking_Status $Fm4t.
BP_Status $Fm5t.;
Run;



%macro mmacro1(pred,i); 
proc freq data=heart order=formatted; 
tables &pred*Status/chisq sparse outpct out=outfreq&i ;
output out=stats&i chisq;
format &pred $Fm&i.t;
run;
%mend;
%mmacro1(sex,1);
%mmacro1(Chol_Status,2);
%mmacro1(Weight_Status,3);
%mmacro1(Smoking_Status,4);
%mmacro1(BP_Status,5);