Gov 2002: Problem Set 5

Published

October 19, 2023

Submission instructions | PDF | Rmd |

Problem Set Instructions

This problem set is due on October 25, 11:59 pm Eastern time. Please upload a PDF of your solutions to Gradescope. We will accept hand-written solutions but we strongly advise you to typeset your answers in Rmarkdown. Please list the names of other students you worked with on this problem set.

Question 1 (25 points)

Suppose we want to model the relationship between legislation and politician quality. There are two types of politician quality: high and low. When a high quality politician propose a bill, it has a probability p1 to pass; conversely, when a low quality politician propose a bill, it has a probability p2 to pass, where p1>p2. Unfortunately, we cannot directly observe politicians’ quality, but instead rely on our prior that a politician is a high type with probability h and low type with probability 1h, where h(0,1). Let X be the number of passed bills after a randomly picked politician has made n proposals.

  1. Find the marginal distribution of X.

  2. Find the mean and variance of X.

Question 2 (25 points)

We know from the definition of the variance that E[(YE[Y])2]=E[Y2](E[Y])2. Prove that this equality still holds when we condition on X, i.e., E[(YE[YX])2X]=E[Y2X](E[YX])2

Question 3 (30 points)

Let X1Xn be i.i.d. r.v.s with mean μ and variance σ2, and n2. A bootstrap sample of X1Xn is a sample of n r.v.s X1Xn formed from the Xj by sampling with replacement with equal probabilities. Let X¯ denote the sample mean of the bootstrap sample:

X¯=1n(X1+Xn)

  1. Find E[Xj] and V[Xj] for each j. (Hint: What is the distribution of Xj?)

  2. Find E[X¯X1,,Xn] and V[X¯X1,,Xn] (Hint: Conditional on X1Xn, the Xj are independent, with a PMF that puts probability 1/n at each of the points X1Xn.)

  3. Find E[X¯] and V[X¯] (Hint: Recall that the sample variance 1n1j=1n(XjX¯)2 is an unbiased estimator of the population variance σ2)

Question 4 (20 points)

Jon commutes on the Boston subway from Park Street Station to Harvard Square. He records in minutes every day how long he waits for the train to arrive. He assumes a statistical model that says his waiting times Y1Yn are i.i.d. from Unif(0, θ).

  1. Find an unbiased plug-in estimator θ^PI

  2. Find the variance and mean square error of θ^PI