DOC PREVIEW
UI STAT 2010 - An Observational Study

This preview shows page 1-2-3-4-5 out of 14 pages.

Save
View full document
Premium Document
Do you want full access? Go Premium and unlock all 14 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

by Rob Cannon John Trachsel Two independent populations Male Undergrads Female Undergrads We are interested in the center or means of these two populations The null and alternative hypotheses for this observational study are Ho M males M females Ha M males M females 0 Collect data Format Data for SAS Use SAS to compare population means Individuals answers are accurate Samples taken are a good representation of University student population Data was entered correctly Two methods of analysis Calculate a confidence interval for the difference between the means test Ha Calculate a two sample t statistic test Ho SAS code for 90 Confidence interval of for males and females data skip infile H documents skip txt input mhours fhours run proc means data skip n mean stddev stderr clm alpha 10 var fhours mhours run Variable N Female Hours 124 Male Hours 137 Mean Std Dev Std Error Lower 90 C level for Mean Upper 90 C level for Mean 1 43548 1 57852 0 14175 1 2005 1 67042 2 13868 1 82379 0 15581 1 88063 2 39674 Female Hours Skipped 1 44 24 Male Hours Skipped 2 14 26 Female Hours Skipped 1 44 24 Male Hours Skipped 2 14 26 Because the confidence intervals do not overlap we can confirm that Ha M males M females at the 90 confidence level 0 SAS Code proc univariate mu0 1 44 2 14 data skip var mhours fhours run This is a test for the location of the mean Testing Ho M M Use SAS to compute location of means males females SAS provided an indirect route to give P the probability of Ho M males M females SAS Output Group T Value Probability Male 4 48 0001 Female 4 97 0001 proven true Created three question surveys Questions What is your sex Are you taking at least 12 semester hours How many hours on average do you miss a week Pooled 137 males and 124 females for the survey Samples collected at random from the University of Iowa Campus Threw out any students who were not full time or any that presented a ridiculous amount of hours missed Based on the data analysis girls on average miss less class than guys Future test could determine the effect of going to class and variability of hours missed between different majors


View Full Document

UI STAT 2010 - An Observational Study

Documents in this Course
Load more
Download An Observational Study
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view An Observational Study and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view An Observational Study and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?