Skewness and Kurtosis of Bernoulli Distributions

  • #1

Main Question or Discussion Point

Suppose you have multiple independent Bernoulli random variables, [tex]X_1,X_2,...,X_n[/tex], with respective probabilities of success [tex]p_1,p_2,...,p_n[/tex].

So [tex]E(X_i)=p_i[/tex], and [tex]E(X_i+X_j)=E(X_i)+E(X_j)[/tex]. Also, [tex]\text{var}(X_i)=p\cdot (1-p)[/tex], and [tex]\text{var}(X_i+X_j)=\text{var}(X_i)+\text{var}(X_j)[/tex]. (Though correct me if any of that is wrong.)

I'm trying to figure out the similar formulae for skewness and kurtosis. Since skewness of [tex]X_i[/tex] is given by [tex]\tfrac{(1-p_i)-p_i}{\sqrt{p_i\cdot(1-p_i)}}[/tex], how would you calculate the skewness of [tex]X_i+X_j[/tex]? And for kurtosis of [tex]X_i+X_j[/tex]?
 

Answers and Replies

  • #2
mathman
Science Advisor
7,798
430
Skewness is a factor using the (centered) second and third moments, while kurtosis uses the (centered) second and fourth moments. You should be able to calculate the third and fourth moments and thus the quantities you want. You already have the centered second moment (variance).
 

Related Threads on Skewness and Kurtosis of Bernoulli Distributions

  • Last Post
Replies
3
Views
2K
Replies
2
Views
3K
  • Last Post
Replies
3
Views
3K
  • Last Post
Replies
1
Views
7K
Replies
3
Views
5K
Replies
11
Views
4K
  • Last Post
Replies
1
Views
2K
Replies
20
Views
3K
Replies
2
Views
1K
Replies
3
Views
8K
Top