Stat Computing > SPSS > Textbook Examples > Regression Analysis by Example, by Chatterjee, Hadi and Price

SPSS Textbook Examples
Regression Analysis by Example, Third Edition
Chapter 12:  Logistic Regression

Table 12.1, page 323. Financial Ratios of Solvent and Bankrupt Firms (First 10 observations).

get file 'd:\p323.sav'.
compute index = $casenum.
exe.
list
 /cases = 10.

       y        x1        x2        x3    index

       0    -62.80    -89.50      1.70     1.00
       0      3.30     -3.50      1.10     2.00
       0   -120.80   -103.20      2.50     3.00
       0    -18.10    -28.80      1.10     4.00
       0     -3.80    -50.60       .90     5.00
       0    -61.20    -56.20      1.70     6.00
       0    -20.30    -17.40      1.00     7.00
       0   -194.50    -25.80       .50     8.00
       0     20.80     -4.30      1.00     9.00
       0   -106.10    -22.90      1.50    10.00

Number of cases read:  10    Number of cases listed:  10

Table 12.2, page 324.

logistic regression y
 /method = enter x1 x2 x3
 /print = summary ci(.95)
 /save dev(dr) cook(c).

Block 0: Beginning Block

Block 1: Method = Enter

Figure 12.2, page 326.
NOTE: Figure is different than what is presented in the book.

graph
 /scatterplot = index with dr.

Figure 12.3, page 326.
NOTE: Figure is different than what is presented in the book.

graph
 /scatterplot = index with c.

Figure 12.4, page 327.
NOTE: SPSS does not have the influential measurement DG, change in the chi-squared test statistics G when the i^th observation is deleted.

Table 12.3, page 328. Output From the Logistic Regression Using x1 and x2.

logistic regression y
 /method = enter x1 x2 
 /print = summary ci(.95).

Block 0: Beginning Block

Block 1: Method = Enter

Table 12.4, page 328. Output from the logistic regression using x1.

logistic regression y
 /method = enter x1 
 /print = summary ci(.95).

Block 0: Beginning Block

Block 1: Method = Enter

Table 12.5, page 331. Results from OLS Regression of Y on x1, x2 and x3.

regression
 /dependent = y
 /method enter = x1 x2 x3 
 /save pred(p).

Table 12.6, page 332. Classification of Observations by Fitted Values.

compute assign = (p >= .5).
exe.
list y p assign
 /cases =10.

       y           p   assign

       0     -.00170      .00
       0      .48066      .00
       0     -.12212      .00
       0      .30644      .00
       0      .22883      .00
       0      .14467      .00
       0      .33313      .00
       0     -.32057      .00
       0      .51704     1.00
       0      .11620      .00

Number of cases read:  10    Number of cases listed:  10

crosstabs 
 /tables = y by assign.

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