Stat Computing > Statistica > Textbook Examples > Computer-Aided Multivariate Analysis

Statistica Textbook Examples
Computer-Aided Multivariate Analysis, Afifi and Clark
Chapter 11

Page 245 Table 11.1  Means and standard deviations for nondepressed and depressed adults in Los Angeles County

File
  Open - open the depression data set

Statistics
  Basic statistics
    Descriptives
      Variables - select sex, age, education, income, health, beddays, acuteill and chronill
        "Advanced" tab - uncheck "Valid N" and "Minimum and maximum"
          Select cases (middle of the right-hand side of the dialogue box)
            Check the "Enable selection conditions" box to active the 
            "Include cases" and "Exclude cases" dialogue box
            In the "Include cases" box, change the radio button to "Specific, selected by"
            In the "By expression" box in the "Include cases" box, type "cases = 0" (without the quotation marks)
              OK

NOTE:  Change the selection condition to cases = 1.

Page 248 Figure 11.2  Distribution of income for depressed and nondepressed individuals showing effects of a dividing point at an income of $18440

We were unable to reproduce this graph.

Page 249 Table 11.2  Classification of individuals as depressed or not depressed on the basis of income alone

Statistics
  Multivariate exploratory techniques
    Discriminant analysis
      Variables - select cases as the grouping variable and income as the independent variable
        OK
          OK
RESULTS
  "Classification" tab - change the radio button under "A priori classification probabilities" 
  to "same for all groups"
    Classification matrix

Page 252 Figure 11.5  Classification of individuals as depressed or not depressed on the basis of income and age

We were unable to reproduce this graph.

Page 253 Table 11.3  Classification of individuals as depressed or not depressed on the basis of income and age

Statistics
  Multivariate exploratory techniques
    Discriminant analysis
      Variables - select cases as the grouping variable and income and age as the independent variables
        OK
          OK
RESULTS
  "Classification" tab - change the radio button under "A priori classification probabilities" 
  to "same for all groups"
    Classification matrix

Page 257 Table 11.4  Classification function and discriminant coefficients for age and income from BMDP 7M

From the results from Table 11.3, click on the "classification functions" button.

Page 258 Covariances in the middle of the page

NOTE:  We reduced the number of decimals shown by highlighting those cells and clicking on the ".00 -> .0" button at the top.  We also deleted some unnecessary columns and rows from the output.

Statistics
  Advanced linear/non-linear models
    General regression models
      Multiple regression
        OK
          "Quick" tab
            Variables - select cases as the dependent variable and age and income 
            as the independent variables
              OK
RESULTS
  "Matrix" tab
    Covariance

Page 268 Table 11.5  Partial printout from BMDP 7M for classification into more than two groups, using the depression data with K = 3 groups

Before you can do this, you need to add a new variable to the data set and use the variable cesd to recode the new variable.  To add the new variable, highlight the variable that you would like to have come immediately after the new variable and click on "Insert" (part of the main menu at the top) and click on "Add variable".  This will open a dialogue box in which you can name the variable, etc.  (We named our new variable cases3.)  Click on "OK" to create the variable.  Next, click on "Data" (from the main menu at the top) and click on "Recode".  Follow the coding scheme given on page 267 in the middle of the text. 

Statistics
  Multivariate exploratory techniques
    Discriminant analysis
      Variables - select cases3 as the grouping variable and sex, age, educat, income, health and beddays 
      as the independent variables
        OK
          OK
RESULTS
  "Classification" tab - change the radio button under "A priori classification probabilities" 
  to "same for all groups"
    Classification functions

 Number of variables in the model: 6

 Wilks' Lambda: .8398356   approx. F (12,572) = 4.347020 p <  .0000

NOTE:  We could only find the standardized coefficients for the canonical variables in Statistica, not the raw coefficients as shown in the text.

Page 271 Figure 11.6  Plot of the canonical variables for the depression data set with k = 3 groups

We were unable to reproduce this graph.

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