Simple Linear Regression Models
[Pages:49]Simple Linear Regression Models
Raj Jain Washington University in Saint Louis
Saint Louis, MO 63130 Jain@cse.wustl.edu
These slides are available on-line at:
Washington University in St. Louis
CSE567M
14-1
?2008 Raj Jain
Overview
1. Definition of a Good Model 2. Estimation of Model parameters 3. Allocation of Variation 4. Standard deviation of Errors 5. Confidence Intervals for Regression Parameters 6. Confidence Intervals for Predictions 7. Visual Tests for verifying Regression Assumption
Washington University in St. Louis
CSE567M
14-2
?2008 Raj Jain
Simple Linear Regression Models
! Regression Model: Predict a response for a given set of predictor variables.
! Response Variable: Estimated variable ! Predictor Variables: Variables used to predict the
response. predictors or factors ! Linear Regression Models: Response is a linear
function of predictors. ! Simple Linear Regression Models:
Only one predictor
Washington University in St. Louis
CSE567M
14-3
?2008 Raj Jain
Definition of a Good Model
y
x Good
y
y
x Good
x Bad
Washington University in St. Louis
CSE567M
14-4
?2008 Raj Jain
Good Model (Cont)
! Regression models attempt to minimize the distance measured vertically between the observation point and the model line (or curve).
! The length of the line segment is called residual, modeling error, or simply error.
! The negative and positive errors should cancel out Zero overall error Many lines will satisfy this criterion.
Washington University in St. Louis
CSE567M
14-5
?2008 Raj Jain
Good Model (Cont)
! Choose the line that minimizes the sum of squares of the errors.
where, is the predicted response when the predictor variable is x. The parameter b0 and b1 are fixed regression parameters to be determined from the data. ! Given n observation pairs {(x1, y1), ..., (xn, yn)}, the estimated response for the ith observation is:
! The error is:
Washington University in St. Louis
CSE567M
14-6
?2008 Raj Jain
Good Model (Cont)
! The best linear model minimizes the sum of squared errors (SSE):
subject to the constraint that the mean error is zero:
! This is equivalent to minimizing the variance of errors (see Exercise).
Washington University in St. Louis
CSE567M
14-7
?2008 Raj Jain
Estimation of Model Parameters
! Regression parameters that give minimum error variance are:
and
! where,
Washington University in St. Louis
CSE567M
14-8
?2008 Raj Jain
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- hands on with python
- confidence sets and hypothesis testing in a
- scikit learn intro scikit learn provides tools for data
- regression analysis with python laboratoire eric
- introduction to machine learning with scikit learn
- analyzing data using python risk engineering
- simple linear regression models
- notes on median and quantile regression
- introduction to time series regression and forecasting
- primal an linear programming based sparse learning
Related searches
- simple linear regression test statistic
- simple linear regression hypothesis testing
- simple linear regression null hypothesis
- simple linear regression model calculator
- simple linear regression uses
- simple linear regression model pdf
- simple linear regression practice problems
- simple linear regression least squares
- simple linear regression excel
- simple linear regression example pdf
- simple linear regression example questions
- simple linear regression business example