Class Notes (811,155)
Canada (494,530)
Statistics (266)
STAB22H3 (208)
Ken Butler (34)
Lecture 13


15 Pages
Unlock Document

University of Toronto Scarborough
Ken Butler

STAB22CHAPTER 13COVERS CHAPTER 13 rest 14160DETECTING THAT A TREATMENT MAKES A DIFFERENCE see LEC12 as well for this slide Additional notes for this slide adding on to from last lecture LEC12 randomization is key for exptl designbc if you decide who gets what treatment by randomization then nth about who gets what has ath to do w any other factorswheras if you picked them yourself then those decisions may have been due to the persons condition your relationship with them if you appreciate them or not etcif doing by randomization then can make conclusion that if treatments are equally good then the only diff bween who gets what treatment are just by random chance Example have 2 treatments that both have mean20 SD5can differ by 3 or 4 but typically not more than that given that they are both the same ie no diffs exist bween thembut suppose you did expt and you found sample means to have diff greater than 10 then sth else must be going on other than random diffs bween the groups that had caused this greater diffthis is evidence that treatments are diff one better than otherExample treatment A mean20 SD5 treatment B mean40 SD5 161PLACEBOS fake treatment thats designed to look as if its the real treatmentEx real treatment is pill while placebo would like completely like the real one from the outside but it would not have its drug effects Why is it important to use this subj will feel as if he is experiencing improvement if he or she knows he is receiving the treatment Ex suppose were involved in a medical study and we are a subj suffering from some disease the scientist gives you a treatment to what you are suffering from after a few days you dont really feel better if its fake but it feels to you you did bc you were treatedwould like to show that subjs feel MUCH better having the Real treatment than having the Fake placebo treatment Ex placebo is the base for comparison against the real treatments if the subjs somehow feel better taking the placebo then for the real treatment to be really making a diff it must have ppl feeling a LOT better by itst they feel better than those who took placebo Additional NotesControl groups a can consist of ppl who get placebo while the real treatment ppl get the real substance or b can consist of ppl getting the standard treatment while the real treatment is the NEW treatment that we are comparing to standarddepicts to us what happens if nth is givento have new treatment adopted it has to be better than the best right now aka standard treatment Example
More Less

Related notes for STAB22H3

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.