Comparing survival between matched cases and controls - proc phreg?

SarahW13 — Wed, 13 Jun 2018 05:34:50 GMT

Hello all! I have a question about how to do Cox regression for matched cases and controls. In my example, I have 2 controls matched to each case. I used the code from this article to generate my dataset of matched cases and controls: http://www2.sas.com/proceedings/sugi29/173-29.pdf

However, now I am stuck at figuring out how to actually run the analysis. I have my original dataset that has all of the covariates that I need, and I have the new dataset that has the id's of the controls, id's of the matched cases, and the variables that I used to match the cases & controls (in this case, age).

In my original dataset, this is what I have:

id age treatment survival survival_censor

1 57.1 0 3.41 1

2 38.1 0 2.05 1

3 42.5 0 1.95 0

100 57.4 1 3.10 1

101 57.0 1 5.38 0

120 38.2 1 0.95 0

125 38.9 1 4.41 0

105 43.9 1 3.41 0

132 41.3 1 2.37 0

Below is an example of what I have in the new dataset that has case:control matches (1:2):

case_id control_id case_age control_age rand_num num

1 100 57.1 57.4 0.56778 1

1 101 57.1 57.0 0.56778 2

2 120 38.1 38.2 0.23116 1

2 125 38.1 38.9 0.23116 2

3 105 42.5 43.9 0.95096 1

3 132 42.5 41.3 0.95096 2

I would like to run a Cox regression comparing the survival between the matched cases and controls, but I have the actual case-control pairings in one dataset and the survival info (plus other covariates that I need to adjust for) in a separate dataset.

Does anyone have any advice on the next steps I need to do?

Thanks!

Re: Comparing survival between matched cases and controls - proc phreg?

SarahW13 — Wed, 13 Jun 2018 21:39:00 GMT

I thought I would check again to see if anyone has thoughts on this. Would cox regression even be appropriate in this case, or would I need other methods (eg, conditional logistic regression) to compare survival between the matched cases and controls? Any guidance would be much appreciated.

topic Re: Comparing survival between matched cases and controls - proc phreg? in Statistical Procedures

Comparing survival between matched cases and controls - proc phreg?

Re: Comparing survival between matched cases and controls - proc phreg?