About goodness of fit in Weibull

[zhao.liang@usa.net]

[Originally Posted: 11/12/99-- Transferred by ReliaSoft Moderator]

The Distribution Wizard of Weibull++ can calculates some paraameters, such as Lkv, Avplot, k-s, chi-square. But in the reference book there are no background knowledge and theory which tell me how to get them . Is there anyone who would help me? Thanks.

[Jim Jauw]

[Originally Posted: 11/12/99-- Transferred by ReliaSoft Moderator]

I give you an answer and a comment I hope is helpful.

1) Answer - here are two sources that should start you out for fit testing theory:

D'Agostino, R.B. and Stephens, M.A. 1986. "Goodness-of-Fit Techniques." New York: Marcel Dekker.

Hoaglin, D.C., Mosteller, F., and Tukey, J.W., eds. 1991. "Fundamentals of Exploratory Analysis of Variance." New York: Wiley.

2) Comment - after reading a few of these papers and texts, you see that authors cite each other in their reference sections quite frequently. Some times, bad assumptions and errors are propagated. Once you have read the theory behind the techniques, please remember that they are tools that serve a specific purpose under specific circumstances, e.g., small data sets or time-dependent data.