Page 1 of 1

Help: What is lack of fit test for linear regression?

Posted: Sat May 13, 2006 4:43 am
by wxmwqr
When I submit a paper about HPLC method for quantitative analysis. The reviewer asked me to do the lack of fit test for the standard curve. I want to kanow what is Lack of fit test , and how to do it.
I had read some paper in which the author used ANOVA to evaluate the precision, what dose it mean? (quote the sentence from the paper: One-way analysis of variance (ANOVA)was carried out with grouping variable "day" to assess precision at 95% level. The result was non-significant when data for each day was compared with other days and within the same day)
Who have the electronic book about the statistics that was used in analysis method, please send it to me. Thank again!!!
my e-mail: wxmwqr@56.com

Posted: Sat May 13, 2006 2:50 pm
by james little
Could be as simple as the refit of the data to the calibration curve and the residual of any point in the curve..

see page 6 in the pdf document at

http://www.fda.gov/cder/guidance/4252fnl.htm