PSY 302 Chapter Notes - Chapter 14: Simple Linear Regression, Standard Deviation, Prediction Interval

• School: University of Oregon
• Department: Psychology
• Course: PSY 302
• Professor: Dasa Zeithamova Demircan

Document Summary

Linear aggression: one or more predictor variables are used to predict cases" scores on an outcome variable. Simple linear regression: one predictor variable, x, is used to predict y, the outcome variable. Regression equation: created using pearson r for simple linear regression. Simple linear regression should only be used with a statistically significant pearson r. Regression line: the best-fitting straight line for predicting y from x. Y prime: the value of y predicted from x by a regression equation, . Least squares criterion: prediction errors are squared and the best-fitting regression line is the one that has the smallest sum of squared errors. Best prediction is the one that yields smallest errors between predicted outcomes and actual outcomes. Residuals: difference between actual score and predicted score, size of the error in prediction. Squared error scores are all positive because the residual scores are squared and then summed. If slope is positive, the line is moving up and right.