Scribd
Upload
4 views9 pages

Understanding Least-Squares Regression

This document provides an overview of least-squares regression and linear regression models. It defines the key components of a regression line including the slope, intercept, and how the line is fitted to minimize the vertical distances between the data points and the line. It describes how linear regression can be used to predict an outcome variable based on an explanatory variable and discusses limitations of extrapolating beyond the data range. The document also covers interpreting regression results and assessing the fit of the linear model.

Uploaded by

Biplove Pokhrel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
4 views9 pages

Understanding Least-Squares Regression

This document provides an overview of least-squares regression and linear regression models. It defines the key components of a regression line including the slope, intercept, and how the line is fitted to minimize the vertical distances between the data points and the line. It describes how linear regression can be used to predict an outcome variable based on an explanatory variable and discusses limitations of extrapolating beyond the data range. The document also covers interpreting regression results and assessing the fit of the linear model.

Uploaded by

Biplove Pokhrel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

Least-Squares Regression

Regression Line (Model)


 It has the form y = a + bx,
 where b is the slope, the amount by which y
changes when x increases by 1 unit
 where a is the intercept, the value of y when x =
0
sy
 Slope: b  r
sx
 Intercept: a  y  bx

 The line that makes the sum of the squares of


the vertical distances of the data points from
the line as small as possible.
Linear Regression
 Purpose: To predict the value of a difficult to
measure variable, Y, based on an easy to
measure variable, X.

 Examples
 Predict state revenues
 Predict GPA based on SAT
 predict reaction time from blood alcohol level
Extrapolation

 Extrapolation is the use of a regression line for


prediction far outside the range of values of the
independent variable x that you used to obtain the
line. Such predictions are not accurate.

 GRE consideration? Be Careful!


Interpreting Results
 The regression line always passes through the point
 x, y 
 The slope ‘says’ that along the regression line, a
change of one standard deviation in x corresponds to
a change of r standard deviations in y
 When r = 1 or –1
 the change in standard units is the same
Variation
 The R squared value, r 2 , is the % of the variation
of Y explained by the model.

 The higher the value, the better the model.

2 variance of predicted
r 
variance of observed
No Straight Line?
 What if the scatterplot shows a straight line
model is not appropriate?
 Might see if some function of y is approximately
linear in some function of x.

 Examples
 Plot y versus ln(x)
 Plot 1/y versus 1/x

 If so, fit straight line model in terms of new


variables.
Example
 Let’s use the alcoholic beverage and recall data

 How can we tell if it is reasonable to fit a linear


regression model?

 Let’s run the analysis and interpret the results

You might also like