| Summary: | Logistic regression is an analytical tool generally applied in health studies
and researchs whom the response variable have two values �success/yes� and
�failure/no�. This paper intends to study polychotomous logistic regression
models where the response variable has more than two categories and the
covariates have missing values.
In many medical data sets, we may face some missingness in some
covariates such as denying to respond, lack of information in files, and
incompleteness of study frame. In such case we deal with missing values. In this
study, it is assumed that the missingness is at random and independent of deal
with missing values.
To obtain the estimator of parameters of the polychotomous logistic
regression models it can use some method. In this thesis we use a Maximum
Likelihood Estimation (MLE) of the parameter β from an polychotomous
logistic regression models. It has been seen that the estimators obtained are not
available in nice closed form, so they can be easily evaluated by using Newton-
Raphson solution method.
|
|---|