Differences

This shows you the differences between two versions of the page.

--- logit_analysis [2019/09/15 02:41] – created hkimscil
+++ logit_analysis [2019/09/15 02:54] – hkimscil
@@ Line 1: / Line 1: @@
-====== logit analysis ======
+====== Logit Analysis ======
+https://stats.idre.ucla.edu/r/dae/logit-regression/
 <code>
 mydata <- read.csv("https://stats.idre.ucla.edu/stat/data/binary.csv")
@@ Line 43: / Line 44: @@
 <code>xtabs(~admit + rank, data = mydata)</code>
-<code> xtabs(~admit + rank, data = mydata)
+<code>> xtabs(~admit + rank, data = mydata)
      rank
 admit  1  2  3  4
@@ Line 49: / Line 50: @@
 33 54 28 12
 </code>
+<code>mydata$rank <- factor(mydata$rank)
+mylogit <- glm(admit ~ gre + gpa + rank, data = mydata, family = "binomial")
+summary(mylogit)
+</code>
+<code>
+Call:
+glm(formula = admit ~ gre + gpa + rank, family = "binomial",
+    data = mydata)
+Deviance Residuals:
+    Min       1Q   Median       3Q      Max
+-1.6268  -0.8662  -0.6388   1.1490   2.0790
+Coefficients:
+             Estimate Std. Error z value Pr(>|z|)
+(Intercept) -3.989979   1.139951  -3.500 0.000465 ***
+gre          0.002264   0.001094   2.070 0.038465 *
+gpa          0.804038   0.331819   2.423 0.015388 *
+rank2       -0.675443   0.316490  -2.134 0.032829 *
+rank3       -1.340204   0.345306  -3.881 0.000104 ***
+rank4       -1.551464   0.417832  -3.713 0.000205 ***
+---
+Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
+(Dispersion parameter for binomial family taken to be 1)
+    Null deviance: 499.98  on 399  degrees of freedom
+Residual deviance: 458.52  on 394  degrees of freedom
+AIC: 470.52
+Number of Fisher Scoring iterations: 4
+> </code>
+<code>
+> confint(mylogit)
+Waiting for profiling to be done...
+.5 %       97.5 %
+(Intercept) -6.2716202334 -1.792547080
+gre          0.0001375921  0.004435874
+gpa          0.1602959439  1.464142727
+rank2       -1.3008888002 -0.056745722
+rank3       -2.0276713127 -0.670372346
+rank4       -2.4000265384 -0.753542605
+>
+</code>
+<code>> ## CIs using standard errors
+> confint.default(mylogit)
+.5 %       97.5 %
+(Intercept) -6.2242418514 -1.755716295
+gre          0.0001202298  0.004408622
+gpa          0.1536836760  1.454391423
+rank2       -1.2957512650 -0.055134591
+rank3       -2.0169920597 -0.663415773
+rank4       -2.3703986294 -0.732528724
+</code>
+<code>wald.test(b = coef(mylogit), Sigma = vcov(mylogit), Terms = 4:6)</code>
+<code>l <- cbind(0, 0, 0, 1, -1, 0)
+wald.test(b = coef(mylogit), Sigma = vcov(mylogit), L = l)
+</code>
+{{tag> statistics r "logit statistics" "multiple regression"}}