libname herc 'S:\Courses\stat-renaes\Stat404';

* Creating variables;

data sales;
	set herc.sales;
	drop Gender Salary Job_Title
	     Country Birth_Date Hire_Date;
	Bonus=500;
	Compensation=sum(Salary,Bonus);
	BonusMonth=month(Hire_Date);
	AnnivBonus=mdy(month(Hire_Date),15,2008);
run;

proc print data=sales;
run;


* an example from stat 431 (basic ANOVA with transformation);

data gulfwaters;
*infile 'S:\Courses\stat-renaes\Data\gulf.csv' dsd missover firstobs=2;
input o2 Distance $;
cards;
1	1KM
5	1KM
2	1KM
1	1KM
2	1KM
2	1KM
4	1KM
3	1KM
0	1KM
2	1KM
4	5KM
8	5KM
2	5KM
3	5KM
8	5KM
5	5KM
6	5KM
4	5KM
3	5KM
3	5KM
20	10KM
26	10KM
24	10KM
11	10KM
28	10KM
20	10KM
19	10KM
19	10KM
21	10KM
24	10KM
37	20KM
30	20KM
26	20KM
24	20KM
41	20KM
25	20KM
36	20KM
31	20KM
31	20KM
33	20KM
;
run;
proc print data=gulfwaters;
run;


* natural log function is log() with base e;
data gulf2;
set gulfwaters;
lno2=log(o2+1);
sqrto2=sqrt(o2);
run;
proc print data=gulf2;
run;
* original data;
proc glm data=gulfwaters plots=(diagnostics residuals);
class distance;
model o2=distance;
run;
* square-root transformation;
proc glm data=gulf2 plots=(diagnostics residuals);
class distance;
model sqrtO2=distance;
run;
* natural log (+1) transformation;
proc glm data=gulf2 plots=(diagnostics residuals);
class distance;
model lno2=distance;
run;