Need help solving CDF (Cumulative distribution function)

Click For Summary

Discussion Overview

The discussion revolves around calculating the cumulative distribution function (CDF) by hand, specifically through the integration of a Gaussian function. Participants explore methods to express the result in terms of the error function and discuss the relationship between the CDF and the probability density function (PDF).

Discussion Character

  • Exploratory, Technical explanation, Homework-related, Mathematical reasoning

Main Points Raised

  • One participant seeks guidance on calculating the CDF using integration, presenting a specific integral to solve.
  • Another participant introduces the error function, suggesting that the result can be expressed as erf(1/sqrt(2)).
  • A subsequent post questions what the associated probability density function (PDF) is once the CDF is expressed in terms of the error function.
  • It is noted that the density function related to the error function is the normal density function, which aligns with the original integrand.
  • A final post indicates that the original poster has understood the explanation provided.

Areas of Agreement / Disagreement

Participants appear to agree on the use of the error function in expressing the CDF, but there is no explicit consensus on the step-by-step integration process itself, as the original poster was seeking detailed guidance.

Contextual Notes

The discussion includes assumptions about familiarity with integration techniques and the properties of the error function, which may not be universally understood by all participants.

Who May Find This Useful

This discussion may be useful for individuals learning about cumulative distribution functions, integration of Gaussian functions, and the relationship between CDFs and PDFs in probability theory.

invictor
Messages
6
Reaction score
0
Hello, I am new. I been looking on the net for a guide how to solve the CDF by hand, i know the answer and I am about to crack this baby but I got stuck...

Im trying to calculate Cumulative distribution function by hand:
[itex]\int^{1}_{-1}\frac{1}{2\pi} e^{\frac{-z^{2}}{2}} dz[/itex] or wolfram alpha: integrate 1/sqrt(2*pi) * e^(-z^2 /2) dz from -1 to 1

Anyway, this is the tricky part, how do this? (I left out the lefthand part above part for easier readability):

[itex]\int e^{\frac{-z^{2}}{2}} dz =[/itex]

[itex]u = \frac{-z^{2}}{2}[/itex]

[itex]du = -z dz[/itex]

[itex]\frac{du}{-z} = dz[/itex]

[itex]\int e^{u} \frac{du}{-z} =[/itex]

then? How do i need to do?. Can any friendly soul here show me step by step how to solve this?

best regrads
invictor
 
Physics news on Phys.org
You can define
[tex]\operatorname{erf}(x) = \frac{2}{\sqrt{\pi}} \int_0^x e^{-t^2} dt[/tex]
and express the result in terms of that, getting [itex]\operatorname{erf}(1/\sqrt{2})[/itex] as the answer.

You cannot give a (more) exact answer than that (otherwise we wouldn't be needing erf in the first place).
 
Ok so now you have the CDF in terms of the error function erf(/frac{1}{/sqrt{2}}) what is the associating PDF?
 
The density function for the error function is the normal density function, which is the integrand you started with.
 
Thanks i got it now :)
 

Similar threads

  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 36 ·
2
Replies
36
Views
5K
  • · Replies 6 ·
Replies
6
Views
5K
Replies
1
Views
4K
  • · Replies 2 ·
Replies
2
Views
3K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 16 ·
Replies
16
Views
3K
  • · Replies 10 ·
Replies
10
Views
2K
  • · Replies 10 ·
Replies
10
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K