Help with 3:1 propensity score matching using macro

Jarot741 — Mon, 31 Dec 2018 02:06:21 GMT

Hi all,

I need help with the following:

PRE-Matching

My treatment cohort is 427 and the control 4079

POST-Matching

My treatment cohort is 1281 and the control 1281

I am wanting to do a 3:1 match, and not sure why I ended up with the last numbers.

I am using this macro by Marcelo Coca Perraillon Paper 185-2007:

%macro PSMatching(datatreatment=, datacontrol=,
method=, numberofcontrols=, caliper=,
replacement=, out=);

/* Create copies of the treated units if N > 1 */;
data _Treatment0(drop= i);
set &datatreatment;
do i= 1 to &numberofcontrols;
RandomNumber= ranuni(12345);
output;
end;
run;

/* Randomly sort both datasets */
proc sort data= _Treatment0 out= _Treatment(drop= RandomNumber);
by RandomNumber;
run;
data _Control0;
set &datacontrol;
RandomNumber= ranuni(45678);
run;
proc sort data= _Control0 out= _Control(drop= RandomNumber);
by RandomNumber;
run;

data Matched(keep = IdSelectedControl PScoreControl MatchedToTreatID PScoreTreat);
length pscoreC 8;
length idC 8;
/* Load Control dataset into the hash object */
if _N_= 1 then do;
declare hash h(dataset: "_Control", ordered: 'no');
declare hiter iter('h');
h.defineKey('idC');
h.defineData('pscoreC', 'idC');
h.defineDone();
call missing(idC, pscoreC);
end;
/* Open the treatment */
set _Treatment;
%if %upcase(&method) ~= RADIUS %then %do;
retain BestDistance 99;
%end;
/* Iterate over the hash */
rc= iter.first();
if (rc=0) then BestDistance= 99;
do while (rc = 0);

/* Caliper */
%if %upcase(&method) = CALIPER %then %do;
if (pscoreT - &caliper) <= pscoreC <= (pscoreT + &caliper) then do;
ScoreDistance = abs(pscoreT - pscoreC);
if ScoreDistance < BestDistance then do;
BestDistance = ScoreDistance;
IdSelectedControl = idC;
PScoreControl = pscoreC;
MatchedToTreatID = idT;
PScoreTreat = pscoreT;
end;
end;
%end;

/* NN */
%if %upcase(&method) = NN %then %do;
ScoreDistance = abs(pscoreT - pscoreC);
if ScoreDistance < BestDistance then do;
BestDistance = ScoreDistance;
IdSelectedControl = idC;
PScoreControl = pscoreC;
MatchedToTreatID = idT;
PScoreTreat = pscoreT;
end;
%end;

%if %upcase(&method) = NN or %upcase(&method) = CALIPER %then %do;
rc = iter.next();
/* Output the best control and remove it */
if (rc ~= 0) and BestDistance ~=99 then do;
output;
%if %upcase(&replacement) = NO %then %do;
rc1 = h.remove(key: IdSelectedControl);
%end;
end;
%end;
/* Radius */
%if %upcase(&method) = RADIUS %then %do;
if (pscoreT - &caliper) <= pscoreC <= (pscoreT + &caliper) then do;
IdSelectedControl = idC;
PScoreControl = pscoreC;
MatchedToTreatID = idT;
PScoreTreat = pscoreT;
output;
end;
rc = iter.next();
%end;
end;
run;
/* Delete temporary tables. Quote for debugging */
proc datasets;
delete _ : gennum=all);

run;
data &out;
set Matched;
run;
%mend PSMatching;

And I am invoking it :

%PSMatching(datatreatment=PNET._MIPD_YES, datacontrol=PNET._MIPD_NO,
method=NN, numberofcontrols=3, caliper=0.1, replacement=NO, out=MATCHES); RUN;

Any ideas?

Thanks,

Re: Help with 3:1 propensity score matching using macro

Reeza — Tue, 01 Jan 2019 00:27:02 GMT

You stared with: N=427, so if you want a 1:3 match, that becomes 1281 records.

Each treatment is matched with 3 controls. If you have a unique variable that identifies your rows, check your data and you should find that you have duplicates of your case data, triplicates and each control should be unique.

EDIT:

Please include code in a code block in the future and if you're using SAS 9.4 TSM5+ there is a PROC PSMATCH now available to do these types of matching as well.

Source of macro: http://www2.sas.com/proceedings/forum2007/185-2007.pdf

@Jarot741 wrote: