Programming the statistical procedures from SAS

Survival Analysis, anova table of risk coefficients

Reply
Occasional Contributor
Posts: 17

Survival Analysis, anova table of risk coefficients

Hello Community,

I have a homework problem where a sample of bone marrow transplants for Hodgekin's and NON-Hodgekin's Lymphoma. All patients had either Hodgekin's disease (HOD) or non-Hodgekin's lymphoma (NHL) and were given an allogeneic (allo) transplant or autogeneic (auto) transplant. This information is non-identifiable and taken from a graduate text book.

So, total there are four types of groups of patients. the first variable graft is used as a dummy variable . The variable, Score, is the pretransplant Karnofsky, Z1 and the variable, Wait, is the waiting time to transplant. My question is that the parameter estimates for the Anova table are very close to the answer to the back of my textbook, but not exact. I was wondering if I'm missing an option in my syntax. For example, HOD Allo has parameter estimate 1.830 as the correct response, however, in my Anova table it's 1.82132.

Below is my code:

data transplant;

input graft type time status score wait;

if graft = 1 and type = 2 then allo_hod = 1; else allo_hod = 0;

if graft = 2 and type = 1 then auto_nhl = 1; else auto_nhl = 0;

if graft = 2 and type = 2 then auto_hod = 1; else auto_hod = 0;

cards;

1 1 28 1 90 24

1 1 32 1 30 7

1 1 49 1 40 8

1 1 84 1 60 10

1 1 357 1 70 42

1 1 933 0 90 9

1 1 1078 0 100 16

1 1 1183 0 90 16

1 1 1560 0 80 20

1 1 2114 0 80 27

1 1 2114 0 90 5

2 1 42 1 80 19

2 1 53 1 90 17

2 1 57 1 30 9

2 1 63 1 60 13

2 1 81 1 50 12

2 1 140 1 100 11

2 1 176 1 80 38

2 1 210 0 90 16

2 1 252 1 90 21

2 1 476 0 90 24

2 1 524 1 90 39

2 1 1037 0 90 84

1 2 2 1 20 34

1 2 4 1 50 28

1 2 72 1 80 59

1 2 77 1 60 102

1 2 79 1 70 71

2 2 30 1 90 73

2 2 36 1 80 61

2 2 41 1 70 34

2 2 52 1 60 18

2 2 62 1 90 40

2 2 108 1 70 65

2 2 132 1 60 17

2 2 180 0 100 61

2 2 307 0 100 24

2 2 406 0 100 48

2 2 446 0 100 52

2 2 484 0 90 84

2 2 784 0 90 171

2 2 1290 0 90 20

2 2 1345 0 80 98

;

run;

proc phreg data=transplant;

model time*status(0) = allo_hod auto_nhl auto_hod /ties=efron;

output out=diagnostic resdev=dev resmart=mart;

run;

Thank you Community!

Ask a Question
Discussion stats
  • 0 replies
  • 209 views
  • 0 likes
  • 1 in conversation