Sampling Distribution Question

Click For Summary
SUMMARY

The discussion focuses on deriving the sampling distribution of a normally distributed random variable and formulating a test statistic for hypothesis testing. Specifically, it addresses the sampling distribution Z = (sqrt(N)) ((x-bar - mu)/(sigma)) and the implications of known versus unknown population variance sigma^2. The conversation emphasizes the importance of understanding the properties of the Normal distribution and the formulation of tests with a specified type I error rate alpha. Additionally, it highlights the necessity of consulting textbooks or established resources for foundational knowledge.

PREREQUISITES
  • Understanding of Normal distribution properties
  • Knowledge of hypothesis testing and test statistics
  • Familiarity with type I error concepts
  • Basic statistical notation and terminology
NEXT STEPS
  • Study the derivation of the Central Limit Theorem
  • Learn about hypothesis testing with known and unknown variances
  • Explore the use of t-distribution in statistical inference
  • Review the concept of type I and type II errors in hypothesis testing
USEFUL FOR

Statisticians, data analysts, students in statistics courses, and anyone involved in hypothesis testing and statistical inference will benefit from this discussion.

hsd
Messages
6
Reaction score
0
I've added a screenshot (https://imgur.com/a/isQXZ) and the text below for your convenience.

Please show steps if possible to help my understanding. Thank you.

Consider a random variable that is Normally distributed, with population mean mu = E [X] and population variance sigma^2 = var [X]. Assume that we have a random sample of size N from this distribution. Let x-bar be the usual sample average.

(a) Using the properties of the Normal distribution, derive explicitly the sampling distribution of the random variable: Z = (sqrt(N)) ((x-bar - mu)/(sigma))

(b) Assume that we know sigma^2, but not mu. For the Null hypothesis H0 : mu = mu0, derive a test statistic, characterize its distribution under H0, and describe a test with the property that the probability of committing a type I error is alpha.

(c) How do you need to modify the results in (b) if sigma^2 is unknown.
 
Physics news on Phys.org
hsd said:
I've added a screenshot (https://imgur.com/a/isQXZ) and the text below for your convenience.

Please show steps if possible to help my understanding. Thank you.

Consider a random variable that is Normally distributed, with population mean mu = E [X] and population variance sigma^2 = var [X]. Assume that we have a random sample of size N from this distribution. Let x-bar be the usual sample average.

(a) Using the properties of the Normal distribution, derive explicitly the sampling distribution of the random variable: Z = (sqrt(N)) ((x-bar - mu)/(sigma))

(b) Assume that we know sigma^2, but not mu. For the Null hypothesis H0 : mu = mu0, derive a test statistic, characterize its distribution under H0, and describe a test with the property that the probability of committing a type I error is alpha.

(c) How do you need to modify the results in (b) if sigma^2 is unknown.

Are you using a textbook? If so, all you need should be in there.

You are asking us to take the time to write things out and explain them to you, but many other people have already done that and put it into books and on web pages. So: I suggest you start looking elsewhere first, and if you have made a genuine effort---and are still confused about very specific issues---then come back here. General questions like yours will never be well received by most helpers..
 

Similar threads

  • · Replies 1 ·
Replies
1
Views
1K
  • · Replies 7 ·
Replies
7
Views
2K
Replies
7
Views
2K
  • · Replies 8 ·
Replies
8
Views
2K
Replies
4
Views
2K
Replies
12
Views
2K
  • · Replies 5 ·
Replies
5
Views
3K
  • · Replies 8 ·
Replies
8
Views
3K
Replies
5
Views
6K
  • · Replies 20 ·
Replies
20
Views
3K