Using estimate statement in proc surveyreg

[kukie]

Hi, I am trying to find the estimates related to the effects of  gender on the relationship between two variables. 

I used an estimate statement in the code as follows....

proc surveyreg data=nhanes4 order=formatted;

cluster SDMVPSU;

strata SDMVSTRA;

weight WTSH2YR;

class vaper riagendr age race income cigs bmi;

model loglead= vaper|riagendr ridageyr bmxbmI race income cigs/

solution clparm;

format vaper vaperf. riagendr genderf. race racef. income

incomef. cigs cigsf. ;

estimate 'comparing males and females' riagendr -1 1/exp;

title "Model with Gender Interaction Term";

run;

somehow, I am not able to get the estimates for males and the estimates for females. Rather, it gives me a single estimate with male as the reference. Is there another way I can code this to give me two separate estimates, one each for male and females?

thanks

[SAS_Rob]

Since gender is involved in an interaction you really can't look at a single parameter estimate to get the estimates for each of the two groups.  In this case it is probably easiest to use the LSMEANS statement.

lsmeans riagendr;

[SteveDenham]

I think what you are calling estimates are estimates of the parameters, which under the non-full rank parameterization used, sets the last category to zero.  Using the LSMEANS statement combines the necessary elements to calculate the expected population mean for each level of a categorical variable.

This is a case where using the LSMEANS and LSMESTIMATE statement is an advantage;  Try adding this to your code:

lsmeans vaper|riagender/e;
lsmestimate riagender "Males vs Females, averaged over vaper status' -1 1/exp;
lsmestimate vaper*riagender 'Males vs Females, vaper status=no'  -1 1 0 0,
                                                'Males vs Females, vaper status=yes' 0 0 -1 1/exp;

You may need to rearrange the coefficients in the second LSMESTIMATE statement to reflect the parameterization given in the LSMEANS statement by the /e option.

SteveDenham

[kukie]

Hi Steve,

Thanks for this. The challenge I have now is that I have three levels of vapers - never vapers, former vapers and current vapers and I am struggling with the parameterization. I am unsure how to account for the three levels.

Thank you

[SteveDenham]

That should not present a problem - once again it is why LSMESTIMATE statements are so useful.

lsmeans vaper|riagender/e;
lsmestimate riagender "Males vs Females, averaged over vaper status' -1 1/exp;
lsmestimate vaper*riagender 'Males vs Females, vaper status=never'  -1 1  0 0  0 0,
                            'Males vs Females, vaper status=former' 0 0  -1 1  0 0,
                            'Males vs Females, vaper status=current' 0 0  0 0  -1 1/exp;

This now gets trickier.  I just stuck these in, and the correct version depends on the ordering of vaper levels.  Since there is nothing in the CLASS statement and I assume that the levels are in fact  'Current', 'Former', and 'Never', the lsmeans will sort in alphabetical order.  That means the code should look like:

lsmeans vaper|riagender/e;
lsmestimate riagender "Males vs Females, averaged over vaper status' -1 1/exp;
lsmestimate vaper*riagender 'Males vs Females, vaper status=current'  -1 1  0 0  0 0,
                            'Males vs Females, vaper status=former' 0 0  -1 1  0 0,
                            'Males vs Females, vaper status=never' 0 0  0 0  -1 1/exp;

If there is another coding for the vaper levels, it can be handled once you know the order that things appear in the LSMEANS statement.

SteveDenham.

[kukie]

Thank you Steve,