|
|
|
||||
|
|
|||||
Table 13.2, page 477
NOTE: The code below gives columns 1 through 4 and 8 through 9 of the table. Also note that the labels used in the text are very different from those used in the SPSS output. The table below matches the labels.
Column label in text Column label in SPSS output n at risk Number entrng this intrvl n events Number of termnl events n censored Number wdrawn during intrvl Actuarial estimates (survival) Cumul propn surv at end Actuarial estimates (hazard) Hazard rate
get file 'c:\alda\honking.sav'. survival table = seconds /interval = thru 8 by 1 /status=censor(0) /print=table.
This subfile contains: 57 observations
Life Table
Survival Variable SECONDS
Number Number Number Number Cumul
Intrvl Entrng Wdrawn Exposd of Propn Propn Propn Proba-
Start this During to Termnl Termi- Sur- Surv bility Hazard
Time Intrvl Intrvl Risk Events nating viving at End Densty Rate
------ ------ ------ ------ ------ ------ ------ ------ ------ ------
.0 57.0 .0 57.0 .0 .0000 1.0000 1.0000 .0000 .0000
1.0 57.0 1.0 56.5 5.0 .0885 .9115 .9115 .0885 .0926
2.0 51.0 3.0 49.5 14.0 .2828 .7172 .6537 .2578 .3294
3.0 34.0 2.0 33.0 9.0 .2727 .7273 .4754 .1783 .3158
4.0 23.0 4.0 21.0 6.0 .2857 .7143 .3396 .1358 .3333
5.0 13.0 2.0 12.0 2.0 .1667 .8333 .2830 .0566 .1818
6.0 9.0 2.0 8.0 2.0 .2500 .7500 .2122 .0707 .2857
7.0 5.0 .0 5.0 1.0 .2000 .8000 .1698 .0424 .2222
8.0+ 4.0 1.0 3.5 3.0 .8571 .1429 .0243 ** **
** These calculations for the last interval are meaningless.
The median survival time for these data is 3.86
SE of SE of
Intrvl Cumul Proba- SE of
Start Sur- bility Hazard
Time viving Densty Rate
------- ------ ------ ------
.0 .0000 .0000 .0000
1.0 .0378 .0378 .0414
2.0 .0643 .0593 .0868
3.0 .0690 .0536 .1039
4.0 .0680 .0508 .1342
5.0 .0674 .0383 .1280
6.0 .0666 .0465 .2000
7.0 .0654 .0402 .2208
8.0+ .0331 ** **
Table 13.3, page 484
NOTE: The code below gives columns 4, 8 and 11 of the table. Also note that SPSS "number remaining" column is the "n at risk" column in the text, except the values are shifted by one line. We use the /save survival subcommand to save the survival estimates to our data set for use in the next figure.
km seconds /status=censor(0) /print table /save survival.
Survival Analysis for SECONDS
Time Status Cumulative Standard Cumulative Number
Survival Error Events Remaining
1.41 .00 .9825 .0174 1 56
1.41 1.00 1 55
1.51 .00 .9646 .0246 2 54
1.67 .00 .9467 .0299 3 53
1.68 .00 .9289 .0343 4 52
1.86 .00 .9110 .0380 5 51
2.12 .00 .8931 .0412 6 50
2.19 .00 .8753 .0441 7 49
2.36 1.00 7 48
2.48 .00 .8570 .0468 8 47
2.50 .00 .8388 .0492 9 46
2.53 .00 .8206 .0514 10 45
2.54 .00 .8023 .0534 11 44
2.56 .00 .7841 .0552 12 43
2.62 .00 .7659 .0569 13 42
2.68 .00 .7476 .0584 14 41
2.76 1.00 14 40
2.78 1.00 14 39
2.83 .00 .7285 .0599 15 38
2.88 .00 .7093 .0614 16 37
2.89 .00 .6901 .0626 17 36
2.92 .00 .6710 .0637 18 35
2.98 .00 .6518 .0647 19 34
3.05 1.00 19 33
3.14 .00 .6320 .0657 20 32
3.17 .00 .6123 .0666 21 31
3.21 .00 .5925 .0673 22 30
3.22 .00 .5728 .0679 23 29
3.24 .00 .5530 .0684 24 28
3.46 1.00 24 27
3.56 .00 .5325 .0688 25 26
3.57 .00 .5121 .0692 26 25
3.58 .00 .4916 .0694 27 24
3.78 .00 .4711 .0694 28 23
4.01 1.00 28 22
4.10 .00 .4497 .0695 29 21
4.18 .00 .4283 .0694 30 20
4.30 1.00 30 19
4.44 .00 .4057 .0693 31 18
4.51 .00 .3832 .0690 32 17
4.52 .00 .3606 .0686 33 16
4.63 1.00 33 15
4.71 1.00 33 14
4.96 .00 .3349 .0683 34 13
5.12 1.00 34 12
5.39 .00 .3070 .0681 35 11
5.73 .00 .2791 .0674 36 10
5.88 1.00 36 9
6.03 .00 .2481 .0666 37 8
6.21 1.00 37 7
6.30 .00 .2126 .0659 38 6
6.60 1.00 38 5
7.20 .00 .1701 .0650 39 4
9.59 .00 .1276 .0611 40 3
12.29 .00 .0851 .0535 41 2
13.18 .00 .0425 .0403 42 1
17.15 1.00 42 0
Number of Cases: 57 Censored: 15 ( 26.32%) Events: 42
Figure 13.2, page 485
Top panel:
Note that we modified the graph produced by the code below by double clicking on the graph to open the Chart Editor and then double clicking on the elements that we wanted to change, such as the labeling of the axes. We used the "Interpolation" button at the top of the Chart Editor to delete the symbols and use a step function to connect the points.
sort cases by sur_1. graph scatterplot(bivar)= seconds with sur_1.
Bottom panel:
We do not know how to overlay the different survival functions onto a single graph in SPSS.
Figure 13.4, page 493
We do not know how to do these graphs in SPSS.
Figure 13.5, page 496
We do not know how to do smoothing in SPSS.
Figure 13.6, page 499
NOTE: We do not know how to do smoothed graphs in SPSS, so the third graph in each column has been omitted.
get file 'c:\alda\alcohol_relapse.sav'. km weeks /status=censor(0) /print none /plot survival hazard.get file 'c:\alda\judges.sav'. km tenure /status=leave(1) /print none /plot survival hazard.get file 'c:\alda\firstdepression.sav'. km age /status=censor(0) /print none /plot survival hazard.get file 'c:\alda\healthworkers.sav'. km weeks /status=censor(0) /print none /plot survival hazard.
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services
