How can I perform a linear Regression including censored data using the Maximum Likelihood?

3 次查看（过去 30 天）

Davide Leonetti 2016-4-13

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/278806-how-can-i-perform-a-linear-regression-including-censored-data-using-the-maximum-likelihood

Is there an already defined function to perform a linear regression including censored data using the Maximum Likelihood?

Assume that I have these vectors

X=[2.423 2.423 2.423 2.305 2.305 2.305 2.143 2.143 2.033 2.033 2.033 2.033 2.033 1.869 1.869]
Y=[4.623 4.845 4.898 5.029 5.274 5.310 5.730 5.776 5.903 6.032 6.699 6.716 6.732 6.699 6.716]
d=[0 0 0 0 0 0 0 0 0 0 1 1 1 1 1]

where the vector d describes the censoring (see mle command). Moreover, for a fixed value of X, Y follows a Normal distribution. How can I derive the curve related to the 0.05 percentile?