Don't need it done for me (and it's not homework, btw)... but if somebody could point me in the right direction conceptually, I'd appreciate it...
There have been 6 perfect games in baseball the past 3.5 seasons, and 13 in the 90 seasons prior to that. I may not use test it under exactly those parameters (I may use x in last 10 years, y in past 75, etc etc). But I just don't know what tool I would use to to be able to say that we can be 'x' confident that an actual change has occurred versus just being random variation. It's been a while since college stats, and even then I don't recall testing the significance of a frequency distribution on it's own.... more like a frequency associated with a particular variable.
You might look into using a Poisson distribution. The intervals each have a rate, which is the mean of the distribution. From the distribution of one statistic you can calculate the probability of the other statistic occurring.
Reply With Quote
Posting Permissions