{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

AndersonB_Lab5_Sec2

# AndersonB_Lab5_Sec2 - Biological Statistics I Biometry 3010...

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

Biological Statistics I Biometry 3010 / Natural Resources 3130 / Statistical Science 2200 Lab 5 Name: Beverly Anderson Section: 2 Date: 11 October 2010 Lab 5 is intended to allow us to explore confidence intervals under various sample sizes and for various methods of computation. We shall look at 95% confidence bounds for the normal distribution, for the intuitive +/- 2SE, for the t-distribution, and for bounds resulting from an application of the bootstrap. We haven’t learned about bootstrap in lecture yet. It is a technique where we resample from the sample (with replacement) and treat it as if it were the population. We shall also learn about and apply the finite population correction. Please download the leaves data and the script Lab5.R . Run the script line by line to get a feel for the commands. You should have done this line-by-line approach before. Not doing so greatly reduces ones appreciation for what the code is doing. Consider the following definitions provided in the lectures ) ( 30 ) ( 30 , 2 1 % 95 2 1 % 95 x SE t x CI n x SE z x CI n df α α - - ± = < ± = where n s x SE x = ) ( As part of Lab 5 we will use the following special form of the standard error applied in situations where the population being sampled is finite (i.e. a small sized population): n s N n N x SE x 1 ) ( - - = This extra component is known as the finite population correction (fpc) factor, and corrects the estimated SE for large sample sizes or small populations. Please explore the various subroutines that make up the Lab5.R script and the different confidence intervals that are created. Note the CI

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}