Regression - Regression Regression is a technique used to analyze the relationship between a dependent(criterion variable and one or more

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
Regression Regression Regression is a technique used to analyze the relationship between a dependent (criterion) variable and one or more independent (predictor) variables We need an interval dependent variable and either interval or binary independent variables. (i.e. we predict or explain Y with one or more X's)
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
What’s the Purpose? What’s the Purpose? 1. Predict the dependent variable for a new set of data. 2. Assess the explanatory power of the independent variable(s). 3. Identify the subset of measures that is most effective for predicting the DV. 3 Reasons to Fit a Regression Model:
Background image of page 2
Regression equation: Υ = b o + b 1 x 1 + b 2 x 2 + … ε where: b o is the intercept (a.k.a. the constant) b n are the regression coefficients ε is the residual - difference b/t the observed values and the values predicted by the model = true error Regression Regression
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
So what do the different parts of the equation tell you? Intercept/Constant : tells you (1) where the regression line crosses the Y axis and (2) the value of Y when the IVs are equal to 0 Regression coefficients: tell you (1) the slope of the regression line and (2) how much the dependent variable is expected to increase when that particular independent variable increases by one, holding all the other independent variables constant. Regression Regression
Background image of page 4
IV Sales = DV 0 20 40 60 80 80 60 40 20 b o slope= b 1 Σ = ε regression line (predicted) Y - observed Regression Regression
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Salespeople Sales = DV 0 2 4 6 8 10 400 300 200 100 500 regression line (predicted) Predicting with Regression: Predicting with Regression: Given the 2 to 1 linear relationship, we can accurately predict sales.
Background image of page 6
Regression is related to statistics that we have discussed at length Correlation - measure of the covariation between variables. varies between -1 and +1 so r = +1 means that the variables are perfectly positively correlated Regression Regression
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Q: How Are Correlation and Regression Related?? A: The square of the correlation is R 2 - gives the explained variance of the dependent variable by the independent variable(s) - called the coefficient of determination (R 2 ) So, regression is a linear relationship which depicts the way two or more variables covary.
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/23/2011 for the course MKTG 352 taught by Professor ? during the Summer '10 term at South Carolina.

Page1 / 34

Regression - Regression Regression is a technique used to analyze the relationship between a dependent(criterion variable and one or more

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online