Overview (HOMALS command)

HOMALS (homogeneity analysis by means of alternating least squares) estimates category quantifications, object scores, and other associated statistics that separate categories (levels) of nominal variables as much as possible and divide cases into homogeneous subgroups.

Options

Data and variable selection. You can use a subset of the variables in the analysis and restrict the analysis to the first n observations.

Number of dimensions. You can specify the number of dimensions HOMALS should compute.

Iterations and convergence. You can specify the maximum number of iterations and the value of a convergence criterion.

Display output. The output can include all available statistics; just the default frequencies, eigenvalues, discrimination measures and category quantifications; or just the specific statistics you request. You can also control which statistics are plotted and specify the number of characters used in plot labels.

Saving scores. You can save object scores in the working data file.

Writing matrices. You can write a matrix data file containing category quantifications for use in further analyses.

Basic Specification

  • The basic specification is HOMALS and the VARIABLES subcommand. By default, HOMALS analyzes all of the variables listed for all cases and computes two solutions. Frequencies, eigenvalues, discrimination measures, and category quantifications are displayed, and category quantifications and object scores are plotted.

Subcommand Order

  • Subcommands can appear in any order.

Syntax Rules

  • If ANALYSIS is specified more than once, HOMALS is not executed. For all other subcommands, if a subcommand is specified more than once, only the last occurrence is executed.

Operations

  • HOMALS treats every value in the range of 1 to the maximum value specified on VARIABLES as a valid category. If the data are not sequential, the empty categories (categories with no valid data) are assigned zeros for all statistics. You may want to use RECODE or AUTORECODE before HOMALS to get rid of these empty categories and avoid the unnecessary output (see RECODE and AUTORECODE for more information).

Limitations

  • String variables are not allowed; use AUTORECODE to recode string variables into numeric variables.
  • The data (category values) must be positive integers. Zeros and negative values are treated as system-missing, which means that they are excluded from the analysis. Fractional values are truncated after the decimal and are included in the analysis. If one of the levels of a variable has been coded 0 or a negative value and you want to treat it as a valid category, use the AUTORECODE or RECODE command to recode the values of that variable.
  • HOMALS ignores user-missing value specifications. Positive user-missing values less than the maximum value specified on the VARIABLES subcommand are treated as valid category values and are included in the analysis. If you do not want the category included, use COMPUTE or RECODE to change the value to something outside of the valid range. Values outside of the range (less than 1 or greater than the maximum value) are treated as system-missing and are excluded from the analysis.