|
|
|
||||
|
|
|||||
Note: This chapter uses a suite of commands, called spost, written by J. Scott Long and Jeremy Freese. The commands must be downloaded prior to their use, and this can be done by typing findit spost in the Stata command line (see How can I use the findit command to search for programs and get additional help? for more information about using findit).
Table 4.1, page 97.
use http://www.ats.ucla.edu/stat/stata/examples/long/binlfp2.dta, clear
logit lfp k5 k618 age wc hc lwg inc
Iteration 0: log likelihood = -514.8732
Iteration 1: log likelihood = -454.32339
Iteration 2: log likelihood = -452.64187
Iteration 3: log likelihood = -452.63296
Iteration 4: log likelihood = -452.63296
Logit estimates Number of obs = 753
LR chi2(7) = 124.48
Prob > chi2 = 0.0000
Log likelihood = -452.63296 Pseudo R2 = 0.1209
------------------------------------------------------------------------------
lfp | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
k5 | -1.462913 .1970006 -7.43 0.000 -1.849027 -1.076799
k618 | -.0645707 .0680008 -0.95 0.342 -.1978499 .0687085
age | -.0628706 .0127831 -4.92 0.000 -.0879249 -.0378162
wc | .8072738 .2299799 3.51 0.000 .3565215 1.258026
hc | .1117336 .2060397 0.54 0.588 -.2920969 .515564
lwg | .6046931 .1508176 4.01 0.000 .3090961 .9002901
inc | -.0344464 .0082084 -4.20 0.000 -.0505346 -.0183583
_cons | 3.18214 .6443751 4.94 0.000 1.919188 4.445092
------------------------------------------------------------------------------
LR Tests, test k5 = 0.
quietly logit lfp k5 k618 age wc hc lwg inc
est store a
quietly logit lfp k618 age wc hc lwg inc
est store b
lrtest a b, stats
likelihood-ratio test LR chi2(1) = 66.48
(Assumption: b nested in a) Prob > chi2 = 0.0000
------------------------------------------------------------------------------
Model | nobs ll(null) ll(model) df AIC BIC
-------------+----------------------------------------------------------------
b | 753 -514.8732 -485.875 7 985.7501 1018.119
a | 753 -514.8732 -452.633 8 921.2659 958.2584
------------------------------------------------------------------------------
Test wc = hc = 0.
quietly logit lfp k5 k618 age lwg inc
est store c
lrtest a c, stats
likelihood-ratio test LR chi2(2) = 18.50
(Assumption: c nested in a) Prob > chi2 = 0.0001
------------------------------------------------------------------------------
Model | nobs ll(null) ll(model) df AIC BIC
-------------+----------------------------------------------------------------
c | 753 -514.8732 -461.8808 6 935.7617 963.5061
a | 753 -514.8732 -452.633 8 921.2659 958.2584
------------------------------------------------------------------------------
Test all slopes = 0.
quietly logit lfp
est store d
lrtest a d, stats
likelihood-ratio test LR chi2(7) = 124.48
(Assumption: d nested in a) Prob > chi2 = 0.0000
------------------------------------------------------------------------------
Model | nobs ll(null) ll(model) df AIC BIC
-------------+----------------------------------------------------------------
d | 753 -514.8732 -514.8732 1 1031.746 1036.37
a | 753 -514.8732 -452.633 8 921.2659 958.2584
------------------------------------------------------------------------------
Wald Tests.
logit lfp k5 k618 age wc hc lwg inc
Iteration 0: log likelihood = -514.8732
Iteration 1: log likelihood = -454.32339
Iteration 2: log likelihood = -452.64187
Iteration 3: log likelihood = -452.63296
Iteration 4: log likelihood = -452.63296
Logit estimates Number of obs = 753
LR chi2(7) = 124.48
Prob > chi2 = 0.0000
Log likelihood = -452.63296 Pseudo R2 = 0.1209
------------------------------------------------------------------------------
lfp | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
k5 | -1.462913 .1970006 -7.43 0.000 -1.849027 -1.076799
k618 | -.0645707 .0680008 -0.95 0.342 -.1978499 .0687085
age | -.0628706 .0127831 -4.92 0.000 -.0879249 -.0378162
wc | .8072738 .2299799 3.51 0.000 .3565215 1.258026
hc | .1117336 .2060397 0.54 0.588 -.2920969 .515564
lwg | .6046931 .1508176 4.01 0.000 .3090961 .9002901
inc | -.0344464 .0082084 -4.20 0.000 -.0505346 -.0183583
_cons | 3.18214 .6443751 4.94 0.000 1.919188 4.445092
------------------------------------------------------------------------------
test k5
( 1) k5 = 0
chi2( 1) = 55.14
Prob > chi2 = 0.0000
test wc hc
( 1) wc = 0
( 2) hc = 0
chi2( 2) = 17.66
Prob > chi2 = 0.0001
test k5 k618 age wc hc lwg inc
( 1) k5 = 0
( 2) k618 = 0
( 3) age = 0
( 4) wc = 0
( 5) hc = 0
( 6) lwg = 0
( 7) inc = 0
chi2( 7) = 94.98
Prob > chi2 = 0.0000
Figure 4.4, page 100.
Note: Figures 4.4 and 4.5 on pages 100 and 101 do not match the textbook.
logit lfp k5 k618 age wc hc lwg inc
Iteration 0: log likelihood = -514.8732
Iteration 1: log likelihood = -454.32339
Iteration 2: log likelihood = -452.64187
Iteration 3: log likelihood = -452.63296
Iteration 4: log likelihood = -452.63296
Logit estimates Number of obs = 753
LR chi2(7) = 124.48
Prob > chi2 = 0.0000
Log likelihood = -452.63296 Pseudo R2 = 0.1209
------------------------------------------------------------------------------
lfp | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
k5 | -1.462913 .1970006 -7.43 0.000 -1.849027 -1.076799
k618 | -.0645707 .0680008 -0.95 0.342 -.1978499 .0687085
age | -.0628706 .0127831 -4.92 0.000 -.0879249 -.0378162
wc | .8072738 .2299799 3.51 0.000 .3565215 1.258026
hc | .1117336 .2060397 0.54 0.588 -.2920969 .515564
lwg | .6046931 .1508176 4.01 0.000 .3090961 .9002901
inc | -.0344464 .0082084 -4.20 0.000 -.0505346 -.0183583
_cons | 3.18214 .6443751 4.94 0.000 1.919188 4.445092
------------------------------------------------------------------------------
predict rstd, rstandard
sort inc
gen index = _n
label var index "Observation Number"
graph twoway (scatter rstd index)
Figure 4.5, page 101. Index Plot of Cook's Influence Statistics
predict c, dbeta label var c "Cook's Influence Statistics" graph twoway (scatter c index, mlabel(index))
Table 4.2, page 106.
quietly reg lfp k5 k618 age wc hc lwg inc
fitstat
Measures of Fit for regress of lfp
Log-Lik Intercept Only: -539.410 Log-Lik Full Model: -478.086
D(745): 956.171 LR(7): 122.648
Prob > LR: 0.000
R2: 0.150 Adjusted R2: 0.142
AIC: 1.291 AIC*n: 972.171
BIC: -3978.757 BIC': -76.280
quietly reg lfp k5 age age2 wc inc
fitstat
Measures of Fit for regress of lfp
Log-Lik Intercept Only: -539.410 Log-Lik Full Model: -486.426
D(747): 972.851 LR(5): 105.968
Prob > LR: 0.000
R2: 0.131 Adjusted R2: 0.125
AIC: 1.308 AIC*n: 984.851
BIC: -3975.326 BIC': -72.848
Logit Model.
quietly logit lfp k5 k618 age wc hc lwg inc
fitstat
Measures of Fit for logit of lfp
Log-Lik Intercept Only: -514.873 Log-Lik Full Model: -452.633
D(745): 905.266 LR(7): 124.480
Prob > LR: 0.000
McFadden's R2: 0.121 McFadden's Adj R2: 0.105
Maximum Likelihood R2: 0.152 Cragg & Uhler's R2: 0.204
McKelvey and Zavoina's R2: 0.217 Efron's R2: 0.155
Variance of y*: 4.203 Variance of error: 3.290
Count R2: 0.693 Adj Count R2: 0.289
AIC: 1.223 AIC*n: 921.266
BIC: -4029.663 BIC': -78.112
gen age2 = age*age
quietly logit lfp k5 age age2 wc inc
fitstat
Measures of Fit for logit of lfp
Log-Lik Intercept Only: -514.873 Log-Lik Full Model: -461.653
D(747): 923.306 LR(5): 106.441
Prob > LR: 0.000
McFadden's R2: 0.103 McFadden's Adj R2: 0.092
Maximum Likelihood R2: 0.132 Cragg & Uhler's R2: 0.177
McKelvey and Zavoina's R2: 0.182 Efron's R2: 0.135
Variance of y*: 4.023 Variance of error: 3.290
Count R2: 0.677 Adj Count R2: 0.252
AIC: 1.242 AIC*n: 935.306
BIC: -4024.871 BIC': -73.321
Table 4.4, page 109.
quietly logit lfp k5 k618 age wc hc lwg inc
* Stata 8 code.
lstat
* Stata 9 code and output.
estat classification
Logistic model for lfp
-------- True --------
Classified | D ~D | Total
-----------+--------------------------+-----------
+ | 342 145 | 487
- | 86 180 | 266
-----------+--------------------------+-----------
Total | 428 325 | 753
Classified + if predicted Pr(D) >= .5
True D defined as lfp != 0
--------------------------------------------------
Sensitivity Pr( +| D) 79.91%
Specificity Pr( -|~D) 55.38%
Positive predictive value Pr( D| +) 70.23%
Negative predictive value Pr(~D| -) 67.67%
--------------------------------------------------
False + rate for true ~D Pr( +|~D) 44.62%
False - rate for true D Pr( -| D) 20.09%
False + rate for classified + Pr(~D| +) 29.77%
False - rate for classified - Pr( D| -) 32.33%
--------------------------------------------------
Correctly classified 69.32%
--------------------------------------------------
Table 4.6, page 113.
quietly logit lfp k5 k618 age wc hc lwg inc
fitstat
Measures of Fit for logit of lfp
Log-Lik Intercept Only: -514.873 Log-Lik Full Model: -452.633
D(745): 905.266 LR(7): 124.480
Prob > LR: 0.000
McFadden's R2: 0.121 McFadden's Adj R2: 0.105
Maximum Likelihood R2: 0.152 Cragg & Uhler's R2: 0.204
McKelvey and Zavoina's R2: 0.217 Efron's R2: 0.155
Variance of y*: 4.203 Variance of error: 3.290
Count R2: 0.693 Adj Count R2: 0.289
AIC: 1.223 AIC*n: 921.266
BIC: -4029.663 BIC': -78.112
quietly logit lfp k5 age age2 wc inc
fitstat
Measures of Fit for logit of lfp
Log-Lik Intercept Only: -514.873 Log-Lik Full Model: -461.653
D(747): 923.306 LR(5): 106.441
Prob > LR: 0.000
McFadden's R2: 0.103 McFadden's Adj R2: 0.092
Maximum Likelihood R2: 0.132 Cragg & Uhler's R2: 0.177
McKelvey and Zavoina's R2: 0.182 Efron's R2: 0.135
Variance of y*: 4.023 Variance of error: 3.290
Count R2: 0.677 Adj Count R2: 0.252
AIC: 1.242 AIC*n: 935.306
BIC: -4024.871 BIC': -73.321
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