hw2ans - STAT 500 — HW 2 — Solution All parts of Q1 and...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: STAT 500 — HW 2 — Solution All parts of Q1 and Q2 are one point each except for 2b that is 2 points. Q3 is 4 points. Q4 is 1 point. 1. Volatility on stock exchanges (a) No, this study is not a randomized experiment. We are observing the volatility in two major stock exchanges. Treatments (exchange) were not randomly assigned to stocks. (b) Yes, these data can be used to make inferences about the mean volatility of all stocks on the NYSE during the week of 12-16 Feb 2007. Because a random sample was selected from all stocks listed on the exchange that week. By randomly choosing stocks, the sample is representative (on average) of the whole exchange. (c) S p = s ( n 1- 1) S 2 1 + ( n 2- 1) S 2 2 n 1 + n 2- 2 = r (40- 1) × (2 . 23%) 2 + (40- 1) × (3 . 37%) 2 40 + 40- 2 = 2 . 85% df = 40 + 40- 2 = 78 (d) H : μ 1 = μ 2 H a : μ 1 6 = μ 2 T = x 1- x 2 r S 2 p 1 n 1 + 1 n 2 = 2 . 91- 4 . 39 q (2 . 85%) 2 ( 1 40 + 1 40 ) =- 2 . 31 df = 78, so p-value=0.024. Using a table, you should find p < 0.05. There is evidence of difference in mean volatility between the two exchanges. Note: Different tables have different d.f. That shouldn’t change the conclusion. (e) No, I do not agree. Because the consultant’s argument requires a causal conclusion. This study is not a randomized experiment. (f) T = x 1- x 2 r S 2 p 1 n 1 + 1 n 2 = 2 . 91- 4 . 39 q (2 . 85%) 2 ( 1 20 + 1 20 ) =- 1 . 64 df = 20 + 20- 2 = 38, so p-value=0.11. (g) T = x 1- x 2 r S 2 p 1 n 1 + 1 n 2 = 2 . 91- 4 . 39 q (2 . 85%) 2 ( 1 100 + 1 100 ) =- 3 . 66 df = 100 + 100- 2 = 198, so p-value=0.0003. (h) As the sample size increases, p-value becomes smaller and we are more likely to reject the null hypothesis. This is reasonable because a larger sample gives more information about the population which reduces the uncertainty about the mean volatility difference.population which reduces the uncertainty about the mean volatility difference....
View Full Document

This note was uploaded on 02/11/2012 for the course STAT 500 taught by Professor Staff during the Fall '08 term at Iowa State.

Page1 / 4

hw2ans - STAT 500 — HW 2 — Solution All parts of Q1 and...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online