Lab 6 - Simulation and Bootstrap Exercises: BJ Orn Andersson Department of Statistics, Uppsala University

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

Lab 6 - Simulation and bootstrap exercises

Bj
orn Andersson
Department of Statistics, Uppsala University

March 7, 2014

1/3

Standard error estimation

Consider the i.i.d. sample variablex which is from an unknown


distribution. We are interested in estimating the median and its
standard error. Use the bootstrap to estimate the standard error of
the median for the sample. Plot the bootstrap values of the
median and decide on a method for calculating a 95% confidence
interval for the median.

2/3

Bootstrap techniques for regression

Consider the data lt67 from Assignment 1. With OLS, fit the
model
weight = 0 + 1 height
and use both the parametric bootstrap and case re-sampling to
create the studentized bootstrap confidence intervals for 1 .
Compare the results with the two methods. Repeat the analysis
when the outliers as determined by the cooks distance have been
removed.

3/3

You might also like