Title: Tables for the Maximum Likelihood Estimate of the Logistic Function
Abstract:where Pi is the probability of an event at xi, Li is the logit of Pi, a and A are parameters. It has a special relation to maximum likelihood estimation, stemming basically from the fact that the logi...where Pi is the probability of an event at xi, Li is the logit of Pi, a and A are parameters. It has a special relation to maximum likelihood estimation, stemming basically from the fact that the logistic function has simple sufficient statistics for the estimate of the parameters. These are E nipi = E ri and E nipixi = E rixi for a and 3 respectively, where ni is the total number exposed at xi, ri is the observed number of events, pi = 1 qi = r/ni . It is known that where sufficient statistics exist, the maximum likelihood estimates are functions of the sufficient statistics [8].* The estimating equations for the maximum likelihood estimate can be writtenRead More
Publication Year: 1957
Publication Date: 1957-03-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 45
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot