sleck
07-30-2008, 11:49 AM
I'm trying to compare one data point to a distribution to see if that one data point fits into the distribution. The distribution is not a normal continuous distribution. Which test should I use? Chi square? how do you make a matrix for the Chi square test in R for this case?
Thank you!
Dragan
07-30-2008, 01:05 PM
I'm trying to compare one data point to a distribution to see if that one data point fits into the distribution. The distribution is not a normal continuous distribution. Which test should I use? Chi square? how do you make a matrix for the Chi square test in R for this case?
Thank you!
A chi-square goodness-of-fit test isn't going to do you any good if your working with ONE data point.
In short, you should provide more background and detail associated with your question. For example, are you attempting to detect an outlier in a data set from a regression analysis? If this is the case you might consider using Cook's D or studentized residual t-statistics.
Andy McKenzie
08-05-2008, 12:28 AM
Yes, it seems like a simple t-test would be adequate here, but you're going to have to give more information.