A chi-squared test for power generalized Weibull family for the head-and-neck cancer censored data. (Russian, English) Zbl 1085.62125

Haghighi, F.; Nikulin, M.

Zap. Nauchn. Semin. POMI 311, 222-236, 301-302 (2004); translation in J. Math. Sci., New York 133, No. 3, 1333-1341 (2006).

From the paper: In survival analysis, the data are often not completely observed. For example, single right censoring occurs commonly in response time data. Here each lifetime \(X\) may be observed exactly or, alternatively, may be known only to be exact up to a certain value. In this case determining the exact value of the number of observations falling into the cell (Pearson statistic) is not possible. Goodness-of-fit analysis is substantially complicated by the presence of censoring.
We propose a chi-squared-type statistic to test the validity of the power generalized Weibull family based on head and neck cancer censored data.

MSC:

62P10	Applications of statistics to biology and medical sciences; meta analysis
62N01	Censored data models
62N03	Testing in survival analysis and censored data
62G10	Nonparametric hypothesis testing

Keywords:

maximum likelihood estimators; randomly censored data