Stat Computing > SPSS > Textbook Examples > Applied Logistic Regression, 2nd, by Hosmer and Lemeshow

SPSS Textbook Examples
Applied Logistic Regression, Second Edition, by Hosmer and Lemeshow
Chapter 4: Model-building strategies and methods for logistic regression

page 105 Table 4.1 Univariable logistic regression models for the UIS  (n = 575).

NOTE: To obtain the values for G, subtract the log likelihoods (remember that the SPSS output gives the -2 log likelihoods, so you will need to divide the value given in the output by -2 before doing the subtraction).

Get file='d:\uis.sav'.

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER age
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER beck
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER ndrugtx
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER ivhx2 ivhx3
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER race
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER treat
  /PRINT=CI(95).

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER site
  /PRINT=CI(95).

page 106 Table 4.2 Results of fitting a multivariable model containing the covariates significant at the 0.25 level in Table 4.1.

NOTE: To get the values listed in the column labeled z, you need to take the square root of the Wald statistics given in the SPSS output.

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER age ndrugtx ivhx2 ivhx3 race treat site.

page 107 Figure 4.2 Univariable lowess smoothed logit versus age.

NOTE: We were unable to reproduce this graph.

page 107 Table 4.3 Results of the quartile analyses of age from the multivariable model containing the variable shown in the model in Table 4.2. 

#2 quartile regression.

SORT CASES BY age (A).

compute age1=($casenum<=148).
compute age2=($casenum>=149) and ($casenum<=292).
compute age3=($casenum>=293) and ($casenum<=458).
compute age4=($casenum>=459).
execute.

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER age2 age3 age4 ndrugtx ivhx2 ivhx3 race treat site
  /PRINT=CI(95).

page 108 Figure 4.3 Plot of estimated logistic regression coefficients versus approximate quartile midpoints of age.

data list list / age coeff.
begin data.
 24 0
30.5 -.165864
35.5 .4693399
47.5 .595771
end data.
execute.

IGRAPH
  /X1 = VAR(age)
  /Y = VAR(coeff)
  /LINE(MEAN) STYLE = DOTLINE INTERPOLATE = STRAIGHT.



 

page 109 Table 4.4 Summary of the use of the method of fractional polynomials for AGE.

NOTE: Deviance is the -2 log likelihood.

Get file='d:\uis.sav'.

NOTE: First row of table:

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER ndrugtx ivhx2 ivhx3 race treat site.
 

NOTE: Second row of table:

LOGISTIC REGRESSION VAR=dfree
  /METHOD=ENTER age ndrugtx ivhx2 ivhx3 race treat site.