Accession Number:

ADA089411

Title:

Alternative Computational Methods for Estimation in Multinomial Logit Response Models. Revision.

Descriptive Note:

Technical rept.,

Corporate Author:

MINNESOTA UNIV ST PAUL DEPT OF APPLIED STATISTICS

Personal Author(s):

• Fienberg,Stephen E.
• Meyer,Michael M.
• Stewart,G. W.

Report Date:

1979-11-01

Pagination or Media Count:

13.0

Abstract:

Several algorithms have been proposed for the computation of maximum likelihood estimates for contingency tables. Since multinomial logit response models can be treated as special versions of log-linear models, many of these techniques can be used for logit models as well. In this paper we compare, in a qualitative fashion, the relative merits of 1 two variants of Newtons method developed by Fienberg and Stewart 2 GLIM, as developed by Nelder and Wedderburn 3 the BMDP program for stepwise logistic regression and 4 the widely used method of iterative proportional fitting. Author

Descriptors:

• *STATISTICAL DATA
• *FITTING FUNCTIONS(MATHEMATICS)
• ALGORITHMS
• COMPUTATIONS
• LEAST SQUARES METHOD
• TABLES(DATA)
• LOGARITHM FUNCTIONS
• ITERATIONS

Subject Categories:

• Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE