PSYC 1010 Study Guide - Final Guide: Simple Linear Regression, Standard Error
29 Jun 2018
School
Department
Course
Professor
1010 Exam Ch14
Simple Linear Regression
•An equation to predict a person’s score on a scale dependent variable from his or her score
on a scale independent variable
Prediction vs. Relation
•Regression: statistical technique that can provide specific quantitative information that
predicts relations between variables
•Simple linear regression: tool that lets us predict a person’s score on a dependent variable
from his or her score on one independent variable ( straight line)
Regression with Z Score
•Standardized regression equation:
•Regression to the mean: tendency of scores that are particular high or low to drift toward
the mean over time ( Predicted values will always be closer to the mean then the z score)
•Step1: Calculate the z score
•Step2: Multiply the z score by the correlation coefficient
•Step3: Convert the z score to a raw score
•when you have two sum of squares and the slope √sx/sy (slope)
RANDOM FACTS:
•The regression line is the line that minimizes our error in predicting scores on the dependent
variable
•Regression is to predict as correlation is to relation
•As standard error of the estimate gets smaller, our predictions become more accurate
•As the correlation coefficient gets stronger,our predictions become more accurate
Determining the Regression Equation
•Equation for a line
•In the regression formula a is the intercept: the predicted value for Y when X is equal to 0,
which is the point at which the line crosses, or intercepts
•b is the slope
Using Regression Equation finding a
•Find the z score for an X of 0
•Then, Use z score regression equation to calculate the predicted z score on Y
•Convert z score for Ŷ : Ŷ = ZŶ(SDY) +M Y
bXaY +=
ˆ
Document Summary
Simple linear regression: an equation to predict a person"s score on a scale dependent variable from his or her score on a scale independent variable. Determining the regression equation: equation for a line, in the regression formula a is the intercept: the predicted value for y when x is equal to 0, Y a bx which is the point at which the line crosses, or intercepts: b is the slope. Using regression equation nding a: find the z score for an x of 0, then, use z score regression equation to calculate the predicted z score on y, convert z score for : = z (sd. Proportionate reduction in error, symbolized as: r2 = (sstotal- sserror) Sstotal: for ss total it is the squared error added up for the mean for everyone, for ss error it is the squared error added up for regression equation to predict. 1: determine the error associated with using the mean as the predictor.
