GOHEAVY.COM Forums

We have made several changes to our policy here at GOHEAVY. Here they are:
  • POST WITH YOUR REAL NAME (FIRST & LAST!)
  • POST WITH YOUR REAL EMAIL ADDRESS
  • NO FLAMES
  • NO ADS
  • NO TROLLING
  • PLEASE KEEP BAD LANGUAGE TO A MINIMUM
The moderators of this forum reserve the right to delete any post that is deemed inappropriate for this forum.

GOHEAVY.COM Debates Forum

Re: My main hobby

Posted By: Brad Lehaus (74-131-136-14.dhcp.insightbb.com)
Date: Monday, September 15, 2008, @ 3:24 p.m.

In Response To: Re: My main hobby (Phil Mitchell)

a Poisson distribution is a bivariate discrete distribution similiar to the binomial but usually for small proportion rates (p =5 the binomail distribution approaches the normal distribution. this fact is whatis necessary to validate a chi-square hypothesis test for instance

normal distributions are found often in real life. in fact if you take a sample from a population that is Poisson, binomial or ANY distribution, then the distributions of the samples, or "the average of the averages" will be normally distributed. this is due to the Central limit theorem.

normal distributions are continous distributions but not all continual distributions are normal. for those that aren't (such exponential, Weibel, uniform, etc.) for hypothesis testing you have Wilcoxon sign test, Mann Whitney, Kruskal Wallis and Mood's Median....all of which test for the median vice the means which is what hypothesis testing for normal distributions (such as t -test, ANOVA) test for

so what do I win?

Messages In This Thread

GOHEAVY.COM Debates Forum is maintained by Administrator with WebBBS 5.12.