theta_vals = c(0, 0.2, 0.4, 0.6, 0.8, 1)
theta_prior = c(0.02, 0.02, 0.02, 0.7, 0.2, 0.04)
n_trials = 10000
sigma = 2
n_data = 256
confidence = 0.95
studio9_problem_1a(theta_vals, theta_prior, sigma, n_data, confidence, n_trials)
##
## ----------------------------------
## Problem 1a: Simulated type 1 CI error rate for z-confidence intervals
## Last confidence interval: [ 0.4718141 , 0.9618051 ]
## Type 1 CI-error rate: 0.0494
studio9_problem_1b(theta_vals, theta_prior, sigma, n_data, confidence, n_trials)
##
## ----------------------------------
## Problem 1b: Simulated type 1 CI-error rate for t-confidence intervals
## Last confidence interval: [ 0.8469393 , 1.314208 ]
## Type 1 CI-error rate: 0.0473
xbar = 0.2
studio9_problem_1c(theta_vals, theta_prior, sigma, n_data, confidence, xbar)
##
## ----------------------------------
## Problem 1c: Bayesian updating and probability of hypotheses
## 1c(i) theta_prior 0.02 0.02 0.02 0.7 0.2 0.04
## 1c(i) theta_posterior 0.1574983 0.5664648 0.1574983 0.1184822 5.624715e-05 1.444947e-09
## 1c(ii) 0.95 z confidence interval: [ -0.0449955 , 0.4449955 ]
## 1c(iii) prior prob. theta is in the CI: 0.06
## 1c(iii) posterior prob. theta is in the CI: 0.8814615
studio9_problem_2(0.55, 400)
##
## ----------------------------------
## Problem 2: Simulated polling confidence interval
## Confidence interval: 0.52 plus or minus 0.05
18.05 Introduction to Probability and Statistics
Spring 2022
Authors: Jeremy Orloff and Jennifer French
For information about citing these materials or our Terms of Use, visit: https://ocw.mit.edu/terms