# Why does FindDistributionParameters[] fail to converge for this distribution? [closed]

During testing my code for calculate parameters The following exception is thrown:

FindMaximum::eit: The algorithm does not converge to the tolerance of _4.806217383937354*^-6_ in _500_ iterations

• Welcome to Mathematica.SE! I suggest the following: 1) As you receive help, try to give it too, by answering questions in your area of expertise. 2) Take the tour! 3) When you see good questions and answers, vote them up by clicking the gray triangles, because the credibility of the system is based on the reputation gained by users sharing their knowledge. Also, please remember to accept the answer, if any, that solves your problem, by clicking the checkmark sign! Commented Feb 28, 2021 at 20:05
• People here generally like users to post code as Mathematica code instead of just images or TeX, so they can copy-paste it. It makes it convenient for them and more likely you will get someone to help you. You may find this meta Q&A helpful -- More description of the problem and what you want help with might be in order, too. Commented Feb 28, 2021 at 20:06
• I’m voting to close this question because the OP opened an identical question but with the requested information rather than editing the original question: mathematica.stackexchange.com/questions/240851/….
– JimB
Commented Mar 1, 2021 at 16:34

This is an extended comment about your pdf not integrating to 1.

I've typed in the code from the image you posted and I think it looks exactly like the image:

dist = ProbabilityDistribution[(1 - Exp[λ*(1 - Exp[1])])^(-1) *λ*β*(γ/α)*(x/α)^(γ - 1)*
(1 - Exp[-(x/α)^γ])^(β - 1)*Exp[λ*(1 - Exp[-(x/α)^γ])^β - (x/α)^γ + (1 - Exp[-(x/α)^γ])], {x, 1, ∞},
Assumptions -> {λ > 0, β > 0, α > 0, γ > 0}]


My result as an image:

Your image of the resulting distribution:

But if a set of parameters is tried, the pdf does not integrate to 1:

parms = {λ -> 2, α -> 1, β -> 1, γ -> 1};
Integrate[PDF[dist /. parms, x], {x, 1, ∞}] // N
(* 9.2468 *)


There is an option for ProbabilityDistribution to normalize the pdf (Method->"Normalize"`) but the proposed pdf seems too complicated for that to work on the symbolic distribution. (In other words, doing so does not return an answer in a reasonable or unreasonable amount of time.)