SAS Output

The SAS System

Directory
Libref	LIBRARY
Engine	V9
Physical Name	C:\MyGithub\N736Fall2017_HELPdataset
Filename	C:\MyGithub\N736Fall2017_HELPdataset

#	Name	Member Type	File Size	Last Modified
1	FORMATS	CATALOG	33792	12/14/2018 10:54:49
2	HELP	DATA	175104	09/17/2017 06:30:26
3	HELPMKH	DATA	361472	12/14/2018 10:12:25

The SAS System

The FREQ Procedure

Number of times in past 6 months entered a detox program - Baseline
e2b	Frequency	Percent	Cumulative Frequency	Cumulative Percent
1	90	42.06	90	42.06
2	57	26.64	147	68.69
3	29	13.55	176	82.24
4	16	7.48	192	89.72
5	6	2.80	198	92.52
6	4	1.87	202	94.39
7	3	1.40	205	95.79
8	4	1.87	209	97.66
11	2	0.93	211	98.60
14	1	0.47	212	99.07
17	1	0.47	213	99.53
21	1	0.47	214	100.00
Frequency Missing = 239

nodetox	Frequency	Percent	Cumulative Frequency	Cumulative Percent
0	214	47.24	214	47.24
1	239	52.76	453	100.00

The SAS System

The FREQ Procedure

Frequency
Percent
Row Pct
Col Pct

.

0

0.00

239

52.76

100.00

239

52.76

1

90

19.87

100.00

42.06

0

0.00

90

19.87

2

57

12.58

100.00

26.64

0

0.00

57

12.58

3

29

6.40

100.00

13.55

0

0.00

29

6.40

4

16

3.53

100.00

7.48

0

0.00

16

3.53

5

6

1.32

100.00

2.80

0

0.00

6

1.32

6

4

0.88

100.00

1.87

0

0.00

4

0.88

7

3

0.66

100.00

1.40

0

0.00

3

0.66

8

4

0.88

100.00

1.87

0

0.00

4

0.88

11

2

0.44

100.00

0.93

0

0.00

2

0.44

14

1

0.22

100.00

0.47

0

0.00

1

0.22

17

1

0.22

100.00

0.47

0

0.00

1

0.22

21

1

0.22

100.00

0.47

0

0.00

1

0.22

Total

214

47.24

239

52.76

453

100.00

The SAS System

The LOGISTIC Procedure

Model Information
Data Set	WORK.HELP2
Response Variable	nodetox
Number of Response Levels	2
Model	binary logit
Optimization Technique	Fisher's scoring

Number of Observations Read	453
Number of Observations Used	453

Response Profile
Ordered Value	nodetox	Total Frequency
1	0	214
2	1	239

Probability modeled is nodetox=0.

Model Convergence Status
Convergence criterion (GCONV=1E-8) satisfied.

Model Fit Statistics
Criterion	Intercept Only	Intercept and Covariates
AIC	628.611	605.646
SC	632.727	613.878
-2 Log L	626.611	601.646

Testing Global Null Hypothesis: BETA=0
Test	Chi-Square	DF	Pr > ChiSq
Likelihood Ratio	24.9650	1	<.0001
Score	24.3243	1	<.0001
Wald	23.2743	1	<.0001

Analysis of Maximum Likelihood Estimates
Parameter	DF	Estimate	Standard Error	Wald Chi-Square	Pr > ChiSq
Intercept	1	1.0846	0.2632	16.9808	<.0001
mcs	1	-0.0381	0.00789	23.2743	<.0001

Odds Ratio Estimates
Effect	Point Estimate	95% Wald Confidence Limits
mcs	0.963	0.948	0.978

Association of Predicted Probabilities and Observed Responses
Percent Concordant	61.9	Somers' D	0.238
Percent Discordant	38.1	Gamma	0.238
Percent Tied	0.0	Tau-a	0.119
Pairs	51146	c	0.619

Classification Table
Prob Level	Correct		Incorrect		Percentages
Prob Level	Event	Non- Event	Event	Non- Event	Correct	Sensi- tivity	Speci- ficity	False POS	False NEG
0.200	214	0	239	0	47.2	100.0	0.0	52.8	.
0.300	205	39	200	9	53.9	95.8	16.3	49.4	18.8
0.400	176	91	148	38	58.9	82.2	38.1	45.7	29.5
0.500	120	138	101	94	57.0	56.1	57.7	45.7	40.5
0.600	27	210	29	187	52.3	12.6	87.9	51.8	47.1
0.700	0	238	1	214	52.5	0.0	99.6	100.0	47.3
0.800	0	239	0	214	52.8	0.0	100.0	.	47.2

The SAS System

The LOGISTIC Procedure

Model Information
Data Set	WORK.HELP2
Response Variable	nodetox
Number of Response Levels	2
Model	binary logit
Optimization Technique	Fisher's scoring

Number of Observations Read	453
Number of Observations Used	453

Response Profile
Ordered Value	nodetox	Total Frequency
1	0	214
2	1	239

Probability modeled is nodetox=1.

Model Convergence Status
Convergence criterion (GCONV=1E-8) satisfied.

Model Fit Statistics
Criterion	Intercept Only	Intercept and Covariates
AIC	628.611	605.646
SC	632.727	613.878
-2 Log L	626.611	601.646

Testing Global Null Hypothesis: BETA=0
Test	Chi-Square	DF	Pr > ChiSq
Likelihood Ratio	24.9650	1	<.0001
Score	24.3243	1	<.0001
Wald	23.2743	1	<.0001

Analysis of Maximum Likelihood Estimates
Parameter	DF	Estimate	Standard Error	Wald Chi-Square	Pr > ChiSq
Intercept	1	-1.0846	0.2632	16.9808	<.0001
mcs	1	0.0381	0.00789	23.2743	<.0001

Odds Ratio Estimates
Effect	Point Estimate	95% Wald Confidence Limits
mcs	1.039	1.023	1.055

Association of Predicted Probabilities and Observed Responses
Percent Concordant	61.9	Somers' D	0.238
Percent Discordant	38.1	Gamma	0.238
Percent Tied	0.0	Tau-a	0.119
Pairs	51146	c	0.619

Classification Table
Prob Level	Correct		Incorrect		Percentages
Prob Level	Event	Non- Event	Event	Non- Event	Correct	Sensi- tivity	Speci- ficity	False POS	False NEG
0.200	239	0	214	0	52.8	100.0	0.0	47.2	.
0.300	238	0	214	1	52.5	99.6	0.0	47.3	100.0
0.400	210	27	187	29	52.3	87.9	12.6	47.1	51.8
0.500	138	120	94	101	57.0	57.7	56.1	40.5	45.7
0.600	91	176	38	148	58.9	38.1	82.2	29.5	45.7
0.700	39	205	9	200	53.9	16.3	95.8	18.8	49.4
0.800	0	214	0	239	47.2	0.0	100.0	.	52.8

The SAS System

The LOGISTIC Procedure

Model Information
Data Set	WORK.HELP2
Response Variable	nodetox
Number of Response Levels	2
Model	binary logit
Optimization Technique	Fisher's scoring

Number of Observations Read	453
Number of Observations Used	453

Response Profile
Ordered Value	nodetox	Total Frequency
1	0	214
2	1	239

Probability modeled is nodetox=0.

Model Convergence Status
Convergence criterion (GCONV=1E-8) satisfied.

Model Fit Statistics
Criterion	Intercept Only	Intercept and Covariates
AIC	628.611	596.726
SC	632.727	625.538
-2 Log L	626.611	582.726

Testing Global Null Hypothesis: BETA=0
Test	Chi-Square	DF	Pr > ChiSq
Likelihood Ratio	43.8846	6	<.0001
Score	41.8722	6	<.0001
Wald	38.6514	6	<.0001

Analysis of Maximum Likelihood Estimates
Parameter	DF	Estimate	Standard Error	Wald Chi-Square	Pr > ChiSq
Intercept	1	2.1148	1.0779	3.8493	0.0498
age	1	0.00182	0.0134	0.0187	0.8913
female	1	-0.6645	0.2449	7.3613	0.0067
pss_fr	1	-0.0368	0.0255	2.0797	0.1493
pcs	1	-0.0258	0.00997	6.7020	0.0096
mcs	1	-0.0316	0.0108	8.5648	0.0034
cesd	1	0.0102	0.0115	0.7756	0.3785

Odds Ratio Estimates
Effect	Point Estimate	95% Wald Confidence Limits
age	1.002	0.976	1.028
female	0.515	0.318	0.832
pss_fr	0.964	0.917	1.013
pcs	0.975	0.956	0.994
mcs	0.969	0.949	0.990
cesd	1.010	0.988	1.033

Association of Predicted Probabilities and Observed Responses
Percent Concordant	67.0	Somers' D	0.340
Percent Discordant	33.0	Gamma	0.340
Percent Tied	0.0	Tau-a	0.170
Pairs	51146	c	0.670

The SAS System

The LOGISTIC Procedure

Model Information
Data Set	WORK.HELP2
Response Variable	nodetox
Number of Response Levels	2
Model	binary logit
Optimization Technique	Fisher's scoring

Number of Observations Read	453
Number of Observations Used	453

Response Profile
Ordered Value	nodetox	Total Frequency
1	0	214
2	1	239

Probability modeled is nodetox=1.

Model Convergence Status
Convergence criterion (GCONV=1E-8) satisfied.

Model Fit Statistics
Criterion	Intercept Only	Intercept and Covariates
AIC	628.611	596.726
SC	632.727	625.538
-2 Log L	626.611	582.726

Testing Global Null Hypothesis: BETA=0
Test	Chi-Square	DF	Pr > ChiSq
Likelihood Ratio	43.8846	6	<.0001
Score	41.8722	6	<.0001
Wald	38.6514	6	<.0001

Analysis of Maximum Likelihood Estimates
Parameter	DF	Estimate	Standard Error	Wald Chi-Square	Pr > ChiSq
Intercept	1	-2.1148	1.0779	3.8493	0.0498
age	1	-0.00182	0.0134	0.0187	0.8913
female	1	0.6645	0.2449	7.3613	0.0067
pss_fr	1	0.0368	0.0255	2.0797	0.1493
pcs	1	0.0258	0.00997	6.7020	0.0096
mcs	1	0.0316	0.0108	8.5648	0.0034
cesd	1	-0.0102	0.0115	0.7756	0.3785

Odds Ratio Estimates
Effect	Point Estimate	95% Wald Confidence Limits
age	0.998	0.972	1.025
female	1.944	1.203	3.141
pss_fr	1.037	0.987	1.091
pcs	1.026	1.006	1.046
mcs	1.032	1.010	1.054
cesd	0.990	0.968	1.013

Association of Predicted Probabilities and Observed Responses
Percent Concordant	67.0	Somers' D	0.340
Percent Discordant	33.0	Gamma	0.340
Percent Tied	0.0	Tau-a	0.170
Pairs	51146	c	0.670