Proc Rank

[newguy1580]

The histogram is highly left-skewed, basically the same as the one after running proc univariate for hisugbev. Do you think then what I suggested would still be a reasonable idea?

[PGStats]

I would simply make sure I have a fair share of uncensored events in each category.

Good luck!

PG

[newguy1580]

Does anyone know by any chance how to create quantiles with a certain portion of data? I told my professor that creating tertiles would be one way to work with the data I have for hisugbev but another way she suggested was have all the people who have 0 for this variable go in one group and then with the remaining people put them into tertiles. I have never done this before. Thanks!

[Reeza]

Why categorize them anyways, why not use the continuous variable?

Making some very broad assumptions here:

hisugbev is probably high sugar beverage consumption, I'll assume weekly.

I would categorize as

0 - no consumption

<7 - less than 1 a day

<14 -less than 2 a day

>=14 2 or more a day

This gives you intuitive data. 

[newguy1580]

The thing about using the continuous form is that you are assuming linearity which may or may not be true in the actual dataset. I modeled hisugbev in tertiles and I see that the difference in parameter estimates shows there is some non-linearity here which you wouldn't see if you modeled hisugbev as a continuous variable. I actually didn't try the categorization you suggested but I will give that a try! You are correct hisugbev is high sugared beverage consumption (servings/week)

[Tom]

What is the cross tab of censor and your new 4 level ranking?

[Reeza]

Did you want to include referential coding?

You may also want to point explicitly to data=temp4

proc phreg data=temp4;

class hisugbev4 (ref='0')/param=REF;

model tpyrs*c5_1(0)= age hisugbev4/rl ties=efron;

run;

what happens when you run a proc freq, none of the cells are 0?

proc freq data =temp4;

table hisugbev4*c5_1;

run;

[newguy1580]

I tried putting in data=temp4 next to the proc phreg statement and ran the model again but nothing different..i get the same output.