|
|
|
||||
|
|
|||||
Table 10.1, page 327.
Note: The noadjust option suppresses the actuarial adjustment.
use http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers, clear
generate event = ~censor
ltable t event, noadjust
Beg. Std.
Interval Total Deaths Lost Survival Error [95% Conf. Int.]
-------------------------------------------------------------------------------
1 2 3941 456 0 0.8843 0.0051 0.8739 0.8939
2 3 3485 384 0 0.7869 0.0065 0.7737 0.7993
3 4 3101 359 0 0.6958 0.0073 0.6811 0.7099
4 5 2742 295 0 0.6209 0.0077 0.6056 0.6359
5 6 2447 218 0 0.5656 0.0079 0.5500 0.5809
6 7 2229 184 0 0.5189 0.0080 0.5032 0.5344
7 8 2045 123 280 0.4877 0.0080 0.4720 0.5032
8 9 1642 79 307 0.4642 0.0080 0.4485 0.4798
9 10 1256 53 255 0.4446 0.0081 0.4287 0.4605
10 11 948 35 265 0.4282 0.0083 0.4120 0.4444
11 12 648 16 241 0.4177 0.0085 0.4010 0.4342
12 13 391 5 386 0.4123 0.0087 0.3952 0.4293
-------------------------------------------------------------------------------
ltable t event, hazard noadjust
Beg. Cum. Std. Std.
Interval Total Failure Error Hazard Error [95% Conf. Int.]
-------------------------------------------------------------------------------
1 2 3941 0.1157 0.0051 0.1157 0.0054 0.1053 0.1266
2 3 3485 0.2131 0.0065 0.1102 0.0056 0.0994 0.1215
3 4 3101 0.3042 0.0073 0.1158 0.0061 0.1041 0.1280
4 5 2742 0.3791 0.0077 0.1076 0.0063 0.0957 0.1202
5 6 2447 0.4344 0.0079 0.0891 0.0060 0.0777 0.1013
6 7 2229 0.4811 0.0080 0.0825 0.0061 0.0711 0.0949
7 8 2045 0.5123 0.0080 0.0601 0.0054 0.0500 0.0712
8 9 1642 0.5358 0.0080 0.0481 0.0054 0.0381 0.0593
9 10 1256 0.5554 0.0081 0.0422 0.0058 0.0316 0.0543
10 11 948 0.5718 0.0083 0.0369 0.0062 0.0257 0.0501
11 12 648 0.5823 0.0085 0.0247 0.0062 0.0141 0.0382
12 13 391 0.5877 0.0087 0.0128 0.0057 0.0042 0.0262
-------------------------------------------------------------------------------
Figure 10.1, page 333.
Note: The notab option suppresses tabular display, noconf option suppresses confidence intervals on graph, xlabel specifies the values displayed on the x-axis, ylabel specifies the values displayed on the y-axis, msymbol(i) indicates that no symbol is to be used at the plotted points, yline places a horizontal line, xline places a vertical line.
Note: In the second panel the median is shifted up 1 point from the book because Stata plots the survival probabilities at the end of the time intervals.
stset t, failure(event) sts gen h=h graph twoway scatter h t, msymbol(i) connect(l) ylabel(0(.05).15) xlabe(0(1)13) sort
ltable t event, noadjust notab graph noconf xlabel(0(1)13) ylabel(0(.5)1) msymbol(i) yline(.5) xline(7.6)
Figure 10.2, page 340.
/* Panel A */ use http://www.ats.ucla.edu/stat/stata/examples/alda/data/relapse_days, clear generate weeks = int(days/7) + 1 generate event = ~censor stset weeks, failure(event) sts generate h = h graph twoway scatter h weeks, connect(l) msymbol(i) xlabel(0(1)12)
ltable weeks event, notable graph noconf msymbol(i) ylabel(0(.25)1) xlabel(0(1)12) yline(0.5)
/* Panel B */ use http://www.ats.ucla.edu/stat/stata/examples/alda/data/firstsex, clear generate event = ~censor stset time, failure(event) sts generate h = h graph twoway scatter h time, connect(l) msymbol(i) xlabel(6(1)12) ylabel(0(.1).3) sort
ltable time event, notable graph noconf msymbol(i) ylabel(0(.25)1) xlabel(6(1)12) yline(0.5) xline(11.6)
/* Panel C */ use http://www.ats.ucla.edu/stat/stata/examples/alda/data/suicide_orig, clear generate event = ~censor stset time, failure(event) sts generate h = h graph twoway scatter h time, connect(l) msymbol(i) xlabel(5(2)21) ylabel(0(.05).15) sort
ltable time event, noadjust notab graph noconf msymbol(i) ylabel(0(.25)1) xlabel(5(2)21) yline(.5) xline(15.8)
/* Panel D */ use http://www.ats.ucla.edu/stat/stata/examples/alda/data/congress_orig, clear generate event = ~censor stset time, failure(event) sts generate h = h graph twoway scatter h time, connect(l) msymbol(i) xlabel(0(1)8) ylabel(0(.10).3) sort
ltable time event, noadjust notab graph noconf msymbol(i) ylabel(0(.25)1) xlabel(0(1)8) yline(.5) xline(4.5)
Table 10.2, page 349.
Please see table 10.1 above. The Stata commands for producing table 10.1 include standard errors that are found in table 10.2.
Figure 10.4, page 353.
use http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers, clear list id t censor if id==20 | id==126 | id==129, noobs +-------------------+ | id t censor | |-------------------| | 20 3 0 | | 126 12 0 | | 129 12 1 | +-------------------+ use http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers_pp, clear list id period event if id==20 | id==126 | id==129, noobs +----------------------+ | id period event | |----------------------| | 20 1 0 | | 20 2 0 | | 20 3 1 | | 126 1 0 | | 126 2 0 | |----------------------| | 126 3 0 | | 126 4 0 | | 126 5 0 | | 126 6 0 | | 126 7 0 | |----------------------| | 126 8 0 | | 126 9 0 | | 126 10 0 | | 126 11 0 | | 126 12 1 | |----------------------| | 129 1 0 | | 129 2 0 | | 129 3 0 | | 129 4 0 | | 129 5 0 | |----------------------| | 129 6 0 | | 129 7 0 | | 129 8 0 | | 129 9 0 | | 129 10 0 | |----------------------| | 129 11 0 | | 129 12 0 | +----------------------+
Note: There is a user written procedure, prsnperd.ado, that will convert a "person" data file to a "person-period" data file. You can locate the procedure by entering the command, findit prsnperd, and following the installation instructions (see How can I use the findit command to search for programs and get additional help? for more information about using findit). The prsnperd.ado automatically generates a response variable for the event, called _Y, a period variable, _period, and dummy variables for each of the time periods.
use http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers, clear
prsnperd id t censor
describe
Contains data from http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers.dta
obs: 24,875
vars: 18
size: 1,890,500 (63.9% of memory free)
-------------------------------------------------------------------------------
storage display value
variable name type format label variable label
-------------------------------------------------------------------------------
id float %9.0g
t float %9.0g
censor float %9.0g
_period float %9.0g
_d1 float %9.0g
_d2 float %9.0g
_d3 float %9.0g
_d4 float %9.0g
_d5 float %9.0g
_d6 float %9.0g
_d7 float %9.0g
_d8 float %9.0g
_d9 float %9.0g
_d10 float %9.0g
_d11 float %9.0g
_d12 float %9.0g
_Y float %9.0g 0: Event did not happen; 1:
Event happened
_status float %9.0g 1: Left; 2: Stayed; 3: Censored
-------------------------------------------------------------------------------
Sorted by: id
Note: dataset has changed since last saved
list id _period _Y if id==20 | id==126 | id==129, noobs sepby(id)
+--------------------+
| id _period _Y |
|--------------------|
| 20 1 0 |
| 20 2 0 |
| 20 3 1 |
|--------------------|
| 126 1 0 |
| 126 2 0 |
| 126 3 0 |
| 126 4 0 |
| 126 5 0 |
| 126 6 0 |
| 126 7 0 |
| 126 8 0 |
| 126 9 0 |
| 126 10 0 |
| 126 11 0 |
| 126 12 1 |
|--------------------|
| 129 1 0 |
| 129 2 0 |
| 129 3 0 |
| 129 4 0 |
| 129 5 0 |
| 129 6 0 |
| 129 7 0 |
| 129 8 0 |
| 129 9 0 |
| 129 10 0 |
| 129 11 0 |
| 129 12 0 |
+--------------------+
Table 10.3, page 355.
use http://www.ats.ucla.edu/stat/stata/examples/alda/data/teachers_pp, clear
tabulate period event, row
+----------------+
| Key |
|----------------|
| frequency |
| row percentage |
+----------------+
| event
period | 0 1 | Total
-----------+----------------------+----------
1 | 3,485 456 | 3,941
| 88.43 11.57 | 100.00
-----------+----------------------+----------
2 | 3,101 384 | 3,485
| 88.98 11.02 | 100.00
-----------+----------------------+----------
3 | 2,742 359 | 3,101
| 88.42 11.58 | 100.00
-----------+----------------------+----------
4 | 2,447 295 | 2,742
| 89.24 10.76 | 100.00
-----------+----------------------+----------
5 | 2,229 218 | 2,447
| 91.09 8.91 | 100.00
-----------+----------------------+----------
6 | 2,045 184 | 2,229
| 91.75 8.25 | 100.00
-----------+----------------------+----------
7 | 1,922 123 | 2,045
| 93.99 6.01 | 100.00
-----------+----------------------+----------
8 | 1,563 79 | 1,642
| 95.19 4.81 | 100.00
-----------+----------------------+----------
9 | 1,203 53 | 1,256
| 95.78 4.22 | 100.00
-----------+----------------------+----------
10 | 913 35 | 948
| 96.31 3.69 | 100.00
-----------+----------------------+----------
11 | 632 16 | 648
| 97.53 2.47 | 100.00
-----------+----------------------+----------
12 | 386 5 | 391
| 98.72 1.28 | 100.00
-----------+----------------------+----------
Total | 22,668 2,207 | 24,875
| 91.13 8.87 | 100.00
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