The derivation of the formula for variance for a Pareto Distribution

I need help with the step-by-step process of how to derive the formula for variance. 
First I need to see how to calculate E[X^2] and then how to get variance using Vax[X] = E[X^2] - (E[X])^2.

I'm pretty sure I'm doing something wrong with the integration of x^2*ab/(b+x)^a+1 and the algebra that follows. 

I've been trying this for 2 days now and I cannot seem to get it.

I've posted a picture of my attempt so you can see what I'm expecting. 

Answer

Answers can be viewed only if
  1. The questioner was satisfied and accepted the answer, or
  2. The answer was disputed, but the judge evaluated it as 100% correct.
View the answer
  • Leave a comment if you need any clarifications.

  • How did you know to multiply and divide by(a-k) lambda^(a-k)????

  • We would like the function inside the integral to be a Pareto distribution, since we know it integrates to 1. So you try to create a Pareto distribution algebraic manipulations.

  • Shouldnt the end of be negative?? for when we integrate and then plug in infinity, that part goes to 0 as infinity is in the denominator but then it's minus a minus one?? To be more specific what is the step between a*lambda^a/(a-k)/((a-k)lambda^(a-k) multiplied by the integration of (a-k)lambda*^(a-k)/x^(a-k+1) dx and the last step. Because I get (a*lambda^a)/(a-k)lambda^(a-k) multiplied by 0 - 1

  • OOOO are you using the fact that the density integrates to 1 therefore in that last step for E[X^k] a is (a-k)? then since it is the integral of the density it's just equal to 1!!

  • Yes, I revised my solution and added some more details.

The answer is accepted.