This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: TA session 4 Econ. 103, winter 2010 Wed., Jan. 27, 2010, 10:00 a.m. and 1:00 p.m. in PP2400E. 3 The equivalence of three hypothesis tests Suppose we want to test the hypothesis H : μ = 1 against the two-sided alternative H 1 : μ 6 = 1 The sample mean ˆ μ = 1 n ∑ X i and sample variance ˆ s 2 = 1 n- 1 ∑ ( X i- ˆ μ ) 2 will be used to test this hypothesis. There are three tools available to test any hypothesis. These are the “t-test,” the “p-value” and the confidence interval. It is the mission of this sheet of paper to illustrate how they are equivalent. 3.1 Estimates Let’s say n = 30, ˆ μ = 1 . 2 and ˆ s 2 = 0 . 5. The question is whether the deviation of μ from our hypothesized value of “1” can be chalked up just to randomness. Such a judgment requires some statistical standard of “randomness.” 3.2 T ratio One standard is the t-ratio, which is a number that expresses the likelihood of drawing ˆ μ from a random variable distributed with mean of μ = 1 and whose standard deviation is estimated by ˆ s ....
View Full Document
This note was uploaded on 03/15/2010 for the course ECON 103 taught by Professor Sandrablack during the Winter '07 term at UCLA.
- Winter '07