When the dependent variable is censored, values in a certain range are all transformed to a single value. For example, the standard tobit model can be defined as


where . The loglikelihood function of the standard censored regression model is

where is the cumulative density function of the standard normal distribution and is the probability density function of the standard normal distribution.
The tobit model can be generalized to handle observationbyobservation censoring. The censored model on both of the lower and upper limits can be defined as

The loglikelihood function can be written as






Loglikelihood functions of the lower or upperlimit censored model are easily derived from the twolimit censored model. The loglikelihood function of the lowerlimit censored model is

The loglikelihood function of the upperlimit censored model is

Amemiya (1984) classified Tobit models into five types based on characteristics of the likelihood function. For notational convenience, let denote a distribution or density function, is assumed to be normally distributed with mean and variance .
Type 1 Tobit
The Type 1 Tobit model was already discussed in the preceding section.









The likelihood function is characterized as .
Type 2 Tobit
The Type 2 Tobit model is defined as


















where . The likelihood function is described as .
Type 3 Tobit
The Type 3 Tobit model is different from the Type 2 Tobit in that of the Type 3 Tobit is observed when .


















where .
The likelihood function is characterized as .
Type 4 Tobit
The Type 4 Tobit model consists of three equations:



























where . The likelihood function of the Type 4 Tobit model is characterized as .
Type 5 Tobit
The Type 5 Tobit model is defined as follows:



























where are from iid trivariate normal distribution. The likelihood function of the Type 5 Tobit model is characterized as .
Code examples for these models can be found in Types of Tobit Models.
In a truncated model, the observed sample is a subset of the population where the dependent variable falls in a certain range. For example, when neither a dependent variable nor exogenous variables are observed for , the truncated regression model can be specified.

Twolimit truncation model is defined as

The loglikelihood function of the twolimit truncated regression model is

The loglikelihood functions of the lower and upperlimit truncation model are





