Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars.

kmoonmurr — Fri, 06 Jul 2018 14:39:35 GMT

Hello first time posting so go easy on me. I have a list of 50 or so dependent variables that I want to run in 3 different scenarios using proc logistic, so 150 rows. I don’t want to enter any data manually. I am manipulating the data in SAS to get the output table I desire.

This macro should loop through all the dependent variables and append the data to my base table but I cannot get it to work. Macro is below after description of the problem.

If I run the macro one variable at a time, I get this table which IS what I want, but this is dumb and time consuming.

The table gives me the odds ratios, confidence intervals and p-values for values 0 and 2 of the dependent variable (1 = referent group). Dependent variable is "depvar"

%mylogit2(stress_echo3 );

%mylogit2(oth_imaging3 );

%mylogit2(cabg3);

%mylogit2(pci3 );

DEPVAR	OR_0	P_0	OR_2	P_2
anyevent3	1.05 (0.88-1.25)	0.107	0.83 (0.65-1.07)	0.082
stress_echo3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
oth_imaging3	0.99 (0.80-1.22)	0.495	0.85 (0.63-1.15)	0.271
cabg3	0.58 (0.25-1.36)	0.335	0.78 (0.25-2.41)	0.959
pci3	0.58 (0.25-1.36)	0.335	0.78 (0.25-2.41)	0.959
pci3	0.97 (0.62-1.51)	0.878	1.01 (0.55-1.84)	0.943

When I run the macro this way - which is how I want to do this, I get the following. It does not take any additional data after

stress_echo3, it just appends the same data over and over again.

%mylogit2(stress_echo3 oth_imaging3 cath3 cabg3 pci3);

DEPVAR	OR_0	P_0	OR_2	P_2
anyevent3	1.05 (0.88-1.25)	0.107	0.83 (0.65-1.07)	0.082
stress_echo3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
oth_imaging3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
cath3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
cabg3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
pci3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598
ami3	0.92 (0.50-1.69)	0.865	0.76 (0.30-1.91)	0.598

Here is the macro:

%macro mylogit2(all_deps);

ods output parameterestimates = pe (where=(variable ne "INTERCEPT"));

ods output oddsratios = or;

%let k=1;

%let dep = %scan(&all_deps, &k);

%do %while(&dep NE);

title 'Nuclear Cohort';

proc logistic data=logit ;

class accred_nuclear2 (ref='1');

model &dep (event=last) = accred_nuclear2 /lackfit;

where test = 2;

run;

*get the p-value;

data pe2;

set pe (keep=probchisq CLASSVAL0);

length depvar $20.;

depvar = "&dep";

accred=input(CLASSVAL0, 8.);

drop CLASSVAL0;

rename probchisq=p;

proc sort;

by accred;

run;

*Get the odds ratios and confidence intervals;

data or2;

set or;

length depvar $20.;

depvar = "&dep";

if effect = 'ACCRED_NUCLEAR2 0 vs 1' then accred = 0;

else if effect = 'ACCRED_NUCLEAR2 2 vs 1' then accred = 2;

depvar = "&dep";

drop effect;

Create a single variable that contains the string " oddsratio (lowerlimit CI - upperlimit CI) ';

o= strip(put(ODDSRATIOEST, 8.2));

u=strip(put(UPPERCL, 8.2));

l=strip(put(LOWERCL, 8.2));

ci = cats('(', l, '-', u, ')');

or = catx(' ' , o, ci);

keep or depvar accred;

proc sort;

by accred;

run;

*Create single file with p-value, ORs and CIs and flatten;

data f0 (keep=depvar or_0 p_0) f2 (keep=depvar or_2 p_2);

merge pe2 or2;

by accred;

if accred = 0 then do;

or_0 = or;

p_0 = round(p, 0.001);

output f0;

end;

if accred = 2 then do;

or_2 = or;

p_2= round(p, 0.001);

output f2;

end;

drop accred;

run;

*Create single row file with dependent variable, the OR, CI, and p-value variables for values 0 and 2 of the dependent variable.

data app_stats;

merge f0 f2;

by depvar;

run;

*Append to base table;

proc append base=stats

data=app_stats force;

run;

%let k = %eval(&k + 1);

%let dep = %scan(&all_deps, &k);

%end;

%mend;

/*this works*/

%mylogit2(stress_echo3 );

%mylogit2(oth_imaging3 );

%mylogit2(cabg3 pci3 );

%mylogit2(pci3 );

/*This does not work - all of the values are the same

it take the value of the first dependent variable only

and copies it all the way through. */

%mylogit2(stress_echo3 oth_imaging3 cath3 cabg3 pci3

ami3 cardiac_arrest3 hrt_failure3 h_angina3 h_other_hrt3 anycardiac_outcome);

Re: Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars

Rick_SAS — Fri, 06 Jul 2018 14:47:41 GMT

Try moving the ODS OUTPUT statements INSIDE the PROC LOGISTIC call. See this SAS Tip. I think only your first call is generating data sets.

Although this macro-centric approach is okay for small data sets and 50 variables, you might want to eventually learn how to use the BY statement to perform a more efficient style of regression.

Re: Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars

kmoonmurr — Fri, 06 Jul 2018 14:53:04 GMT

Thank you - that was it! And thanks for the tip - I will look into it.

topic Re: Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars in Statistical Procedures

Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars.

Re: Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars

Re: Output odds ratios, confidence intervals, p-value from proc logistic with list of dependent vars