track changes over time

[axescot78]

I have long data and wrote code to track changes in 2 variables over time. However, the second entry for each userID is wrong. My data, code, and screenshot of results below. What is wrong with the code?

data fake_data;
input userID $ event_date date9. response $ code $;
format event_date date9.;
datalines;
1693 01Dec2014 Y V
1693 01Jan2015 Y V
1693 01Feb2015 Y V
1693 01Mar2015 M G
1693 01Apr2015 M G
1693 01May2015 M G
1129 01Feb2018 Y V
1129 01Mar2018 Y V
1129 01Apr2018 N R
1129 01May2018 N R
1129 01Jun2018 M R
1129 01Jul2018 M R 
1345 01Aug2016 N R
1345 01Sep2016 N R
1345 01Oct2016 N R
1345 01Nov2016 N R
1345 01Dec2016 M R
1345 01Jan2017 M G
1345 01Feb2017 Y G
1345 01Mar2017 Y G
1345 01Apr2017 Y G
1345 01May2017 Y G
;

proc sort data = fake_data out=fake_data_nodupkey nodupkey; by userID event_date; run;
data flag_vars;
set fake_data_nodupkey;
by userID event_date;
if first.userID then do;
	prev_response = response;
	prev_code = code;
	end;
else do;
	prev_response = lag(response);
	prev_code = lag(code);
	end;

response_change = 0;
if response ne prev_response then response_change = 1;

code_change = 0;
if code ne prev_code then code_change = 1;

run;

proc print data=flag_vars;
run;

[axescot78 · Accepted solution]

data flag_vars;
set fake_data_nodupkey;
by userID ;

prev_response = lag(response);
prev_code = lag(code);

if first.userID then do;
	prev_response = response;
	prev_code = code;
	end;

response_change = 0;
if response ne prev_response then response_change = 1;

code_change = 0;
if code ne prev_code then code_change = 1;

 
run;