9 111313 these crossproducts tell you about the

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

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

Unformatted text preview: ulate the cross ­product of Z scores   Cross ­product = mul7plying scores on one variable by scores on another   What happens in the case of a nega1ve correla1on? ▪  If you mul7ply a high Z score (+) by a low Z score ( ­), you get a nega7ve cross ­product ( ­) ▪  If you mul7ple a low Z score ( ­) by a high Z score (+), you get a nega7ve cross ­product ( ­) ▪  If you add up these cross ­products, you get a large nega7ve number ( ­)   In compu7ng a correla7on, we calculate the cross ­product of Z scores   Cross ­product = mul7plying scores on one variable by scores on another   What happens in the case of no correla1on? ▪  Varied associa7ons: high with high, low with low; high with low, low with high ▪  Adding up all of these cross products would result in posi7ve cross ­products and nega7ve cross ­products canceling each other out, given a result of 0, or close to 0. 9 11/13/13   These cross ­products tell you about the direc1on of the rela7onship   Posi7ve vs. Nega7ve   In order to figure out the strength of the rela7onship in a standard way, need to divide the sum of the cross ­ products by the number of people in the study   This represents the average of the cross ­products of Z scores   Correla7on can range from  ­1 to +1 (with 0 represen7ng no correla7on)   Correla1on coefficient: the resul7ng number when you divide the sum of the cross products of Z score by the number of people in the study   Also called Pearson correla7on coefficient (or the Pearson product ­moment cor...
View Full Document

This note was uploaded on 03/24/2014 for the course PSY 21201 taught by Professor Bernard during the Winter '13 term at SUNY Stony Brook.

Ask a homework question - tutors are online