lecture 5

lecture 5 - 8. outliers will overestimate r 9. if someone...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Statistics Lecture 5 1. quiz-a little on correlation, not expected to calculate it but will need to know its limitations and advantages and how to interpret it 2. z scores are populations but correlation deals with samples, how things relate to each other 3. two variables that are ratio or interval and dependent in nature will suggest to use a correlation design 4. pearson’s r a. magnitude-strength-how closely related are the two variables? Closer to absolute value of 1 is strong b. direction-negative or positive value 5. r 2 = this percentage is due to that relationship 6. r is only for linear relationships 7. restricted range in the x axis will underestimate the value of r
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 8. outliers will overestimate r 9. if someone has an optimistic attitude it will make them more likely to develop good health a. if someone is in good health they are more likely to have an optimistic mood b. we are not saying one causes the other c. there are also third variables i. education, money, genetics, influence good health 10. illusory correlation a. the more attractive you are, the less intelligent you are b. see slide for more c. biased, based on expectations 11. regression is prediction 12. since r is not one there will be some error in the regression line, as r increases closer to 1 there is less error...
View Full Document

This note was uploaded on 03/26/2008 for the course STAT 0032 taught by Professor Dicorcia during the Spring '08 term at Tufts.

Ask a homework question - tutors are online