Regression, a second course in statistics
A readable approach to regression as the most important tool of the applied statistician. Provides a focal point for understanding many other related techniques. Keeping the text as simple as possible, the authors reserve the more difficult points for footnotes, starred sections, and starred problems providing the student with a broader understanding. Solutions for all problems are available in the student's workbook.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Multiple Regression Extensions
17 other sections not shown
Other editions - View all
analysis ANOVA assume autocorrelation Bayes Bayes estimate Bayesian bias biased calculate Chapter column components confidence interval consistent estimator constant covariance cycle effect endogenous equal error term estimating equations example exogenous variables explained F distribution F ratio fertilizer fitted formula Gauss-Markov theorem geometrically graph hence illustrate income increase independent instrumental variable interaction likelihood function linear machines mathematical matrix multicollinearity multiple regression null hypothesis observations obtain OLS estimator parameters plane possible posterior distribution prediction prediction interval prior distribution prob-value probability problem rainfall regression coefficient regression line regressors reject H0 relation residual sample mean score Section serial correlation shown in Figure Similarly simple regression slope solution standard deviation standard error statistical statistician substitute sum of squared Suppose tion true unbiased estimator uncorrelated unexplained variance vector Wonnacott xx and x2 yield zero