This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Problem Set 3  Econometrics 120A Due Friday Nov 12 1. Suppose you have a sample of n observations { X i } n i =1 , and we are interested in learning about the population mean μ . (a) A researcher decides to estimate μ by looking at the sample average over the first half of the sample (Assume n is even). Denote this estimator by ˆ μ 1 = 1 n/ 2 ∑ n/ 2 i =1 X i . What is the expectation of ˆ μ 1 ? What is the variance of ˆ μ 1 ? (b) How does the estimator in (a) compare to the average over the whole sample? Which one would you use? 2. Computer Problem. We are going to do a Monte Carlo by generating random variables and examining sample means. There is a function in the Data Analysis Toolpak (look in the TOOLS menu for DATA ANALYSIS, if it is not there see the introduction in EXCEL hints) that computes draws from random variables for us. The experiment I want to do is to examine the distribution of the sample mean from Bernoulli random variables with π =0.5. We will generate 100 samples with n=20, so we can=0....
View
Full
Document
This note was uploaded on 12/05/2010 for the course ECON 120A taught by Professor M.abajian during the Spring '10 term at San Diego.
 Spring '10
 M.Abajian
 Econometrics

Click to edit the document details