|
|
|
||||
|
|
|||||
Inputting the Death Penalty data, table 3.1.2, p. 54.
data death; input victim defendant deathp count; cards; 1 1 1 53 1 1 2 414 1 2 1 11 1 2 2 37 2 1 1 0 2 1 2 16 2 2 1 4 2 2 2 139 ; run; proc format; value defendant 1='white' 2='black'; value victim 1='white' 2='black'; value deathp 1='Yes' 2='No'; run; proc freq data = death; format defendant defendant. victim victim. deathp deathp.; weight count; by victim; table defendant*deathp/norow nocol ; exact or; run;
victim=white
The FREQ Procedure
Table of defendant by deathp
defendant deathp
Frequency|
Percent |Yes |No | Total
---------+--------+--------+
white | 53 | 414 | 467
| 10.29 | 80.39 | 90.68
---------+--------+--------+
black | 11 | 37 | 48
| 2.14 | 7.18 | 9.32
---------+--------+--------+
Total 64 451 515
12.43 87.57 100.00
Statistics for Table of defendant by deathp
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 0.4306 0.2072 0.8947
Cohort (Col1 Risk) 0.4952 0.2780 0.8822
Cohort (Col2 Risk) 1.1501 0.9824 1.3464
Odds Ratio (Case-Control Study)
-----------------------------------
Odds Ratio 0.4306
Asymptotic Conf Limits
95% Lower Conf Limit 0.2072
95% Upper Conf Limit 0.8947
Exact Conf Limits
95% Lower Conf Limit 0.2003
95% Upper Conf Limit 0.9956
Sample Size = 515
victim=black
The FREQ Procedure
Table of defendant by deathp
defendant deathp
Frequency|
Percent |Yes |No | Total
---------+--------+--------+
white | 0 | 16 | 16
| 0.00 | 10.06 | 10.06
---------+--------+--------+
black | 4 | 139 | 143
| 2.52 | 87.42 | 89.94
---------+--------+--------+
Total 4 155 159
2.52 97.48 100.0
Statistics for Table of defendant by deathp
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Cohort (Col2 Risk) 1.0288 1.0006 1.0578
One or more risk estimates not computed --- zero cell.
Sample Size = 159
Inputting the clinic data and obtaining table 3.2 and odds ratios, p. 58-59.
data temp; input clinic treat response count; cards; 1 1 1 18 1 1 2 12 1 2 1 12 1 2 2 8 2 1 1 2 2 1 2 8 2 2 1 8 2 2 2 32 ; run; proc format; value treat 1='A' 2='B'; value response 1='Success' 2='Failure'; run; proc freq data = temp; format treat treat. response response.; weight count; table clinic*treat*response/norow nocol nopercent; exact or; run;
The FREQ Procedure
Table 1 of treat by response
Controlling for clinic=1
treat response
Frequency|Success |Failure | Total
---------+--------+--------+
A | 18 | 12 | 30
---------+--------+--------+
B | 12 | 8 | 20
---------+--------+--------+
Total 30 20 50
Statistics for Table 1 of treat by response
Controlling for clinic=1
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 1.0000 0.3151 3.1738
Cohort (Col1 Risk) 1.0000 0.6300 1.5872
Cohort (Col2 Risk) 1.0000 0.5001 1.9996
Odds Ratio (Case-Control Study)
-----------------------------------
Odds Ratio 1.0000
Asymptotic Conf Limits
95% Lower Conf Limit 0.3151
95% Upper Conf Limit 3.1738
Exact Conf Limits
95% Lower Conf Limit 0.2669
95% Upper Conf Limit 3.6617
Sample Size = 50
The FREQ Procedure
Table 2 of treat by response
Controlling for clinic=2
treat response
Frequency|Success |Failure | Total
---------+--------+--------+
A | 2 | 8 | 10
---------+--------+--------+
B | 8 | 32 | 40
---------+--------+--------+
Total 10 40 50
Statistics for Table 2 of treat by response
Controlling for clinic=2
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 1.0000 0.1769 5.6541
Cohort (Col1 Risk) 1.0000 0.2501 3.9984
Cohort (Col2 Risk) 1.0000 0.7072 1.4141
Odds Ratio (Case-Control Study)
-----------------------------------
Odds Ratio 1.0000
Asymptotic Conf Limits
95% Lower Conf Limit 0.1769
95% Upper Conf Limit 5.6541
Exact Conf Limits
95% Lower Conf Limit 0.0872
95% Upper Conf Limit 6.5993
Sample Size = 50
Inputting the Chinese Smoking and Lung Cancer data, table 3.3, p. 60.
data cmh; input center smoke cancer count @@; cards; 1 1 1 126 1 1 2 100 1 2 1 35 1 2 2 61 2 1 1 908 2 1 2 688 2 2 1 497 2 2 2 807 3 1 1 913 3 1 2 747 3 2 1 336 3 2 2 598 4 1 1 235 4 1 2 172 4 2 1 58 4 2 2 121 5 1 1 402 5 1 2 308 5 2 1 121 5 2 2 215 6 1 1 182 6 1 2 156 6 2 1 72 6 2 2 98 7 1 1 60 7 1 2 99 7 2 1 11 7 2 2 43 8 1 1 104 8 1 2 89 8 2 1 21 8 2 2 36 ; run;
The Mantel-Haenszel odds ratio and the Breslow-Day statistic, p. 62-63.
proc freq data=cmh; weight count; table center*smoke*cancer/ relrisk cmh norow nocol nopercent ; ods output RelativeRisks=temp; run;
Table 1 of smoke by cancer
Controlling for center=1
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 126 | 100 | 226
---------+--------+--------+
2 | 35 | 61 | 96
---------+--------+--------+
Total 161 161 322
Statistics for Table 1 of smoke by cancer
Controlling for center=1
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.1960 1.3432 3.5902
Cohort (Col1 Risk) 1.5292 1.1460 2.0406
Cohort (Col2 Risk) 0.6964 0.5641 0.8596
Sample Size = 322
Table 2 of smoke by cancer
Controlling for center=2
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 908 | 688 | 1596
---------+--------+--------+
2 | 497 | 807 | 1304
---------+--------+--------+
Total 1405 1495 2900
Statistics for Table 2 of smoke by cancer
Controlling for center=2
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.1430 1.8457 2.4881
Cohort (Col1 Risk) 1.4927 1.3762 1.6191
Cohort (Col2 Risk) 0.6966 0.6491 0.7476
Sample Size = 2900
Table 3 of smoke by cancer
Controlling for center=3
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 913 | 747 | 1660
---------+--------+--------+
2 | 336 | 598 | 934
---------+--------+--------+
Total 1249 1345 2594
Statistics for Table 3 of smoke by cancer
Controlling for center=3
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.1753 1.8445 2.5654
Cohort (Col1 Risk) 1.5289 1.3889 1.6829
Cohort (Col2 Risk) 0.7028 0.6542 0.7551
Sample Size = 2594
Table 4 of smoke by cancer
Controlling for center=4
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 235 | 172 | 407
---------+--------+--------+
2 | 58 | 121 | 179
---------+--------+--------+
Total 293 293 586
Statistics for Table 4 of smoke by cancer
Controlling for center=4
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.8503 1.9695 4.1252
Cohort (Col1 Risk) 1.7820 1.4196 2.2368
Cohort (Col2 Risk) 0.6252 0.5369 0.7280
Sample Size = 586
Table 5 of smoke by cancer
Controlling for center=5
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 402 | 308 | 710
---------+--------+--------+
2 | 121 | 215 | 336
---------+--------+--------+
Total 523 523 1046
Statistics for Table 5 of smoke by cancer
Controlling for center=5
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.3191 1.7745 3.0309
Cohort (Col1 Risk) 1.5723 1.3446 1.8384
Cohort (Col2 Risk) 0.6779 0.6036 0.7615
Sample Size = 1046
Table 6 of smoke by cancer
Controlling for center=6
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 182 | 156 | 338
---------+--------+--------+
2 | 72 | 98 | 170
---------+--------+--------+
Total 254 254 508
Statistics for Table 6 of smoke by cancer
Controlling for center=6
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 1.5880 1.0948 2.3032
Cohort (Col1 Risk) 1.2714 1.0396 1.5548
Cohort (Col2 Risk) 0.8006 0.6736 0.9517
Sample Size = 508
Table 7 of smoke by cancer
Controlling for center=7
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 60 | 99 | 159
---------+--------+--------+
2 | 11 | 43 | 54
---------+--------+--------+
Total 71 142 213
Statistics for Table 7 of smoke by cancer
Controlling for center=7
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.3691 1.1351 4.9447
Cohort (Col1 Risk) 1.8525 1.0541 3.2557
Cohort (Col2 Risk) 0.7819 0.6523 0.9373
Sample Size = 213
Table 8 of smoke by cancer
Controlling for center=8
smoke cancer
Frequency| 1| 2| Total
---------+--------+--------+
1 | 104 | 89 | 193
---------+--------+--------+
2 | 21 | 36 | 57
---------+--------+--------+
Total 125 125 250
Statistics for Table 8 of smoke by cancer
Controlling for center=8
Estimates of the Relative Risk (Row1/Row2)
Type of Study Value 95% Confidence Limits
-----------------------------------------------------------------
Case-Control (Odds Ratio) 2.0032 1.0906 3.6796
Cohort (Col1 Risk) 1.4626 1.0163 2.1050
Cohort (Col2 Risk) 0.7301 0.5686 0.9377
Sample Size = 250
Summary Statistics for smoke by cancer
Controlling for center
Cochran-Mantel-Haenszel Statistics (Based on Table Scores)
Statistic Alternative Hypothesis DF Value Prob
---------------------------------------------------------------
1 Nonzero Correlation 1 280.1375 <.0001
2 Row Mean Scores Differ 1 280.1375 <.0001
3 General Association 1 280.1375 <.0001
Estimates of the Common Relative Risk (Row1/Row2)
Type of Study Method Value 95% Confidence Limits
-------------------------------------------------------------------------
Case-Control Mantel-Haenszel 2.1745 1.9840 2.3832
(Odds Ratio) Logit 2.1734 1.9829 2.3823
Cohort Mantel-Haenszel 1.5192 1.4417 1.6008
(Col1 Risk) Logit 1.5132 1.4362 1.5942
Cohort Mantel-Haenszel 0.6999 0.6721 0.7290
(Col2 Risk) Logit 0.7011 0.6734 0.7300
Breslow-Day Test for
Homogeneity of the Odds Ratios
------------------------------
Chi-Square 5.1997
DF 7
Pr > ChiSq 0.6356
Total Sample Size = 8419
proc print data=temp noobs; where studytype="Case-Control (Odds Ratio)"; var table value; title 'Odds Ratio by Center'; run;
Odds Ratio by Center
Table Value
Table 1 of smoke * cancer 2.1960
Table 2 of smoke * cancer 2.1430
Table 3 of smoke * cancer 2.1753
Table 4 of smoke * cancer 2.8503
Table 5 of smoke * cancer 2.3191
Table 6 of smoke * cancer 1.5880
Table 7 of smoke * cancer 2.3691
Table 8 of smoke * cancer 2.0032
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