STATA-- How to convert exponential parameters to normal distribution parameters

[jiahui Liu]

Hi everyone,

I have a exponential parameters of mean and std. However, I would like to have these 2 parameters in normal distribution form. Is there a function in STATA that could help me to convert from exponential mean and std to normal mean and std? Thank you!

[Sven-Kristjan Bormann]

Hi,
what do you mean exactly with "exponential parameters" and "normal distribution form". Do you mean "exp(mean) exp(std)"? Parameters don't have a distributional form but can be part of a distribution. Without further explanation, it will be difficult to help you.

[Nick Cox]

Your mean and SD are what they are. If you're changing your mind about the distribution they come from, that need not mean changing the inputs. That said, in an exponential distribution, mean and SD must be equal, but there is no such rule for the normal.

[William Lisowski]

Is this perhaps a restatement of the topic you started earlier?

https://www.statalist.org/forums/for...esian-analysis

Did you perhaps solve that problem by choosing from Stata's menus

Statistics>Bayesian Analysis>General estimation and regression>Syntax>Univariate Distributions>Exponential Distribution

and you are now trying to transform the result to what you originally were seeking?

If so, there were two pieces of good advice in that original topic, and what you have done is inappropriate and not of use to you.

My guess as to what you want to do in the original topic is

• you have prior distribution for the parameter(s) (mean, or perhaps mean and standard deviation) of a normally distributed random variable
• you have data drawn from that distribution
• you wish to use the data to to update your prior distribution, prodicing your posterior distribution for the parameter(s).

Joseph Coveney's post #3 advises you how to use Stata's Bayes commands to do that, and as he said, those commands are not geared toward what you apparently hope to do but can be made to do it in the way he suggests. When you regress a variable on the constant term alone, the parameter estimate for the constant will be the estimate for the mean of the variable; in a Bayesian framework it will be the posterior estimate of the mean of the variable.

Nick Cox's post #2 there advises you, as do I as well, to review the Statalist FAQ linked to from the top of the page, as well as from the Advice on Posting link on the page you used to create your post.

Note especially sections 9-12 on how to best pose your question. The more information you provide to help others understand your problem, the more likely others are to be able to help you solve your problem.

After two topics, we still have very little idea of what you are trying to do. At this point, I think the current topic is a dead end, if indeed you have used the Bayes commands to generate an exponential posterior from your normal prior. Perhaps you should return to the earlier topic and explain what you want in greater detail, and explain why the advice in post #3 there does not solve your problem.