Students t-distribution Derivation

  • Context: Graduate 
  • Thread starter Thread starter taper100
  • Start date Start date
  • Tags Tags
    Derivation students
Click For Summary
SUMMARY

The discussion focuses on the derivation of the Students t-distribution probability distribution function, specifically the expression T = Z/sqrt(W/v), where Z follows a standard normal distribution and W follows a chi-squared distribution with v degrees of freedom. The participant acknowledges the necessity of independence between Z and W but questions whether this independence was implicitly assumed in their derivation. The key point raised is the assumption in the probability statement P(T ≤ t | W = w) = P(Z/c ≤ t), which indicates that the probability of Z being less than a certain value is independent of W.

PREREQUISITES
  • Understanding of probability distributions, specifically the standard normal distribution and chi-squared distribution.
  • Familiarity with the concept of independence in probability theory.
  • Knowledge of the derivation process for statistical distributions.
  • Basic mathematical skills for manipulating probability expressions.
NEXT STEPS
  • Study the properties of the Students t-distribution and its derivation process.
  • Learn about the independence of random variables in probability theory.
  • Explore the implications of conditional probability in statistical derivations.
  • Review examples of derivations involving the chi-squared distribution and standard normal distribution.
USEFUL FOR

Statisticians, mathematics students, and researchers involved in probability theory and statistical analysis who seek to understand the derivation of the Students t-distribution.

taper100
Messages
7
Reaction score
0
I have attempted a derivation of the Students t-distribution probability distribution function in the attached pdf. I defined T to be Z/sqrt(W/v) where Z has standard normal distrubution and W has chi squared distribution with v degrees of freedom. I know that Z and W need to be independent, but I did not use this fact in my derivation. Can someone tell me where I went wrong in the derivation or where I unknowing used this fact in my derivation?
 

Attachments

Physics news on Phys.org
On the first line,
P(T\leq t | W = w) = P(\frac{Z}{c} \leq t )
assumes that Z and W are independent already, since you're saying that the probability that Z is smaller than some number is independent of what our measurement of W is.
 

Similar threads

  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 4 ·
Replies
4
Views
2K
Replies
8
Views
3K
Replies
20
Views
3K
  • · Replies 4 ·
Replies
4
Views
4K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 24 ·
Replies
24
Views
4K
  • · Replies 2 ·
Replies
2
Views
2K