*Program to Determine Women's Labor Force Participation Rate
*Sara Gieseke
*November 2004
*Program name:  workforce_part1;

/*variables used in the model 
data set for 1980 and 1990 for 50 states
wlfp = participation rate (%) of all women over 16
yf = median earnings (in thousands of dollars) by females
ym = median earnings (in thousands of dollars) by males
educ = percent of female high school graduates over 24 years of age
ue = unemployment rate (%)
mr = marriage rate (%) of women at least 16 years of age
dr = divorce rate (%)
urb = percentage of urban population in state
wh = percentage of females over 16 years who are 
d90 = dummy variable 0=1980 1=1990
*/

/*This is a continuation of the first women in labor participation rate, but
using two decades rather than one.  Therefore dummy variables must used to see if 
there is differences between the 1980s and 1990s.*/

/*TEST FOR CORRELATION*/
proc corr data=women2;
	var wlfp yf ym educ ue mr dr urb wh
run;


/*REGRESSION*/
/*ym left out of model because it is highly correlated with yf
will run regression until all of the variables are significant
the model produces the highest r square
*/
 proc reg data=women2;
 	model wlfp = yf d90yf educ d90educ ue d90ue mr d90mr dr d90dr urb d90urb wh d90wh;
run;
/*r-square for model 1 =.8613
drop least significant variable d90educ (.8813)
*/
proc reg data=women2;
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr d90dr urb d90urb wh d90wh;
run;
/*r-square for model 2 =.8612
drop least significant variable d90wh (.5573)
*/
proc reg data=women2;
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr d90dr urb d90urb wh;
run;
/* r-square for model 3 = .8607
drop least significant variable d90urb (.3391)
*/
proc reg data=women2;
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr d90dr urb wh;
run;
/* r-square for model 4 = .8592
drop least significant variable d90dr (.4350)
*/
proc reg data=women2;
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr urb wh;
run;
/*r-square for model 5 = .8582
all variables are significant at the .10 level
so this will be our final model, just like on p317
*/


/*final model re-run*/
proc reg data=women2;
/*print out predicted values and residuals*/
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr urb wh / p r;
/*plot residuals to check model assumptions*/
	plot residual.*predicted. ='o';
run;
quit;









/*best model (all variables significant at a p-value of .1 or lower)*/
proc reg data=women2;
	title 'Women in the Labor Force 1980 and 1990';
	model wlfp = yf d90yf educ ue d90ue mr d90mr dr urb wh;
	run;