Text: Introduction to Linear Regression Analysis – Douglas M. et al. (5th edition)

  1. Introduction
    1. regression and model building
    2. data collection
    3. uses of regression
    4. role of the computer
  2. Simple Linear Regression
    1. simple linear regression model
    2. least-squares estimation of the parameters
    3. hypothesis testing on the slope and intercept
    4. interval estimation in simple linear regression
    5. prediction of new observations
    6. coefficient of determination
    7. a sevice industry application of regression
    8. using sas and r for simple linear regression
    9. come considerations in the use of regression
    10. regression through the origin
    11. estimation by maximum likelihood
    12. case where regressor x is random
  3. Multiple Linear Regression
    1. multiple regression models
    2. estimation of the model parameters
    3. hypothesis testing in multiple linear regression
    4. confidence intervals in multiple regression
    5. prediction of new observations
    6. a multiple regression model for the patient satisfaction data
    7. hidden extrapolation in multiple regression
    8. standardized regression coefficients
    9. multicollinearity
    10. why do regression cofficients have the wrong sign?
  4. Model Adequacy Checking
    1. introduction
    2. residual analysis
    3. press statistic
    4. detection and treatment of outliers
    5. lack of fit of the regression model
  5. Transformations and Weighting to Correct Model Inadequacies
    1. introduction
    2. variance-stablizing transformations
    3. transformations to linearize the model
    4. analytical methods for selecting a transformation
    5. generalized and weighted least squares
    6. regression models with random effects
  6. Diagnostics for Leverage and Influence
    1. importance of detecting influential
    2. leverage
    3. measures of influence: cook’s d
    4. measures of influence: dffits and dfbetas
    5. a measure of model performance
    6. detecting groups of influencial observations
    7. treatment of influential observations
  7. Polynomial Regression Models
    1. introdution
    2. polynomial models in one variable
    3. nonparametric regression
    4. polynomial models in tow or more variables
    5. orthogonal polynomials
  8. Indicator Variables
    1. general concept of indicator variables
    2. comments on the use of indicator variables
    3. regression approach to analysis of variance
  9. Multicolinearity
    1. introduction
    2. sources of multicollinearity
    3. effects of multicollinearity
    4. multicolinearity diagnostics
    5. methods for dealing with multicolinearity
    6. using sas to perform ridge and pricipal component regression
  10. Variable Selection and Model Building
    1. introduction
    2. computational techniques for variable selection
    3. strategry for variable selectiona and model building
    4. case study: gorman and toman asphalt data using sas
  11. Validation of Regression Models
    1. introduction
    2. validation techniques
    3. data from planned experiments
  12. Introduction to Nonlinear Regression
    1. linear and nonlinear regression is a member of the exponential family
    2. origins of nonlinear models
    3. nonlinear least squares
    4. transformation to a linear model
    5. parameter estimation in a nonlinear system
    6. statistical inference in nonlinear regression
    7. examples of nonlinear regression models
    8. using sas and r
  13. Generalized Linear Models
    1. introduction
    2. logistic regression models
    3. poisson regression
    4. the generalized linear model
  14. Regression Analysis of Time Series Data
    1. introduction to regression models for time series data
    2. detecting autocorrelation: the durbin-watson test
    3. estimating the parameters in time series regression models
  15. Other Topics in the Use of Regression Analysis
    1. robust regression
    2. effect of measurement errors in the regressors
    3. inverse estimation – the calibration problem
    4. classification and regression trees (cart)
    5. neural networks
    6. desinged experiments for regression

 

SNU Class

Prof:

Byeong U. Park

Object :

simple, multiple regression, residual analysis, polynomial regression, variable and model selection, logistics regression, generalized linear models