Revision as of 15:49, 3 May 2014 by Kim1449 (Talk | contribs)

Questions and Comments for: Generation of normally distributed random numbers from two categories with different priors

A slecture by Jonghoon Jin


Please leave me comment below if you have any questions, if you notice any errors or if you would like to discuss a topic further.


Questions and Comments

This slecture was reviewed by Khalid Tahboub:

Great job! few minor remarks:

1) I think the first equation should be

$ F^{-1}(u)=inf\{ x|F(x)\geq u, \quad u\in [0, 1] \} $

instead of

$ F^{-1}(u)=inf\{ x|F(x)\leq u, \quad u\in [0, 1] \} $
2) How we reach
$ X <- F^{-1}(U)\quad $
from
$ F^{-1}(u)=inf\{ x|F(x)\geq u, \quad u\in [0, 1] \} $
is not very clear to me


3)I think the equation

$ F(x) = \int_{-\infty}^x \lambda exp(-\lambda x') dx' = \int_0^x \lambda exp(-\lambda x') dx' = [-exp(-\lambda x')]_0^x = 1-exp(-\lambda x) \leq u $

should be instead

$ F(x) = \int_{-\infty}^x \lambda exp(-\lambda x') dx' = \int_0^x \lambda exp(-\lambda x') dx' = [-exp(-\lambda x')]_0^x = 1-exp(-\lambda x) \geq u $

4) I think it might give a nice demonstration if you plot the histogram of U and X to show that this method really functions in the desired way.



Back to Generation of normally distributed random numbers from two categories with different priors

Alumni Liaison

Basic linear algebra uncovers and clarifies very important geometry and algebra.

Dr. Paul Garrett