# What features can be extracted from a probability distribution? [closed]

I have been looking online regarding feature extraction and I am looking at extracting features from probability distribution by getting the characteristics of the distribution. I know that most common are the following:

• Mean
• Variance
• Standard Deviation
• Skewness
• Kurtosis

I used some links to get these features which can be found below:

So, I have been wondering if there are other types of features that explain the probability distribution?

Side question:

Regarding the Goodness-of-fit tests, I know that they are used to find a suitable distribution that fits the dataset that you are using. I want to know if there is a link or article that looks into the type of tests and if there were a review on them and what could be the better goodness of fit test to use to get the distribution for your dataset?

New contributor
WDpad159 is a new contributor to this site. Take care in asking for clarification, commenting, and answering. Check out our Code of Conduct.
• I think you might be misusing feature extraction. Suppose you had a variable with a mean of 0 and variance of 1. How would you use that information? – Dave Apr 5 at 11:21
• @Dave Well, in my case it's not exactly zero and variance is not close to 1, so, I was thinking of using them as features to classify the cases that I have. Is there different type of features I can extract from a probability distribution? – WDpad159 Apr 5 at 11:57
• How would you use your mean of $\bar{x}$ and variance of $s^2$, whatever the values are, to do the classification? – Dave Apr 5 at 12:05