0

I am looking for help to calculate a CDF for a multinominal distribution function. (I'm strictly using Excel)

I have figured out, how to calculate the bivariate distribution, but seems to be a lot more complicated adding more dimensions.

I have 5 variables.

Lasse Mikkel Nawths
  • 1
  • 1
  • Welcome to SE. What do you mean by CDF? The probability density for the parameters of the multinomial distirbution, given data? That would be handeled by Dirichlet Distirbution. Or the probability mass function for the multinomial itslef, given data? That would be handeled by Dirichlet-Multinomial. Perhaps if you showed what was a good result for you in case of binomial distribution, it would be easier to give you a good answer – Cryo Mar 30 '24 at 00:48
  • Or the multivariate normal? (The multinominal would be, I suppose, a multivariate nominal distribution, but I wouldn't expect to see meaningful tables there, if only because the order of cumulation would be totally arbitrary.) – Nick Cox Mar 30 '24 at 00:55
  • You can find references to solutions at https://stats.stackexchange.com/questions/32156/how-to-evaluate-a-multivariate-gaussian-condition/91035#91035. Unless you are a true expert at VBA in Excel as well as in numerical algorithms, please don't even attempt this in Excel: use software, such as R, where knowledgeable programmers have already implemented and tested solutions. – whuber Mar 30 '24 at 13:23
  • What I mean by CDF is the Cumulative Distribution Function for a given probability density function. That is, a function that provides the volume / area under the given function (i.e., the integral from 0 to X,Y,Z of the joint distribution function) – Lasse Mikkel Nawths Mar 31 '24 at 09:36

0 Answers0