Regression with Graphics: A Second Course in Applied StatisticsThis text demonstrates how computing power has expanded the role of graphics in analyzing, exploring, and experimenting with raw data. It is primarily intended for students whose research requires more than an introductory statistics course, but who may not have an extensive background in rigorous mathematics. It's also suitable for courses with students of varying mathematical abilities. Hamilton provides students with a practical, realistic, and graphical approach to regression analysis so that they are better prepared to solve real, sometimes messy problems. For students and professors who prefer a heavier mathematical emphasis, the author has included optional sections throughout the text where the formal, mathematical development of the material is explained in greater detail. REGRESSION WITH GRAPHICS is appropriate for use with any (or no) statistical computer package. However, Hamilton used STAT A in the development of the text due to its ease of application and sophisticated graphics capabilities. (STATA is available in a student package from Duxbury including a tutorial by the same author: Hamilton, STATISTICS WITH STAT A, 5.0, 1998; ISBN: 0-534-31874-6.) |
Contents
Contents | 1 |
Bivariate Regression Analysis 29 | 29 |
Basics of Multiple Regression | 65 |
Copyright | |
10 other sections not shown
Common terms and phrases
ANOVA assumptions autocorrelation b₁ bivariate biweight bootstrap bounded-influence boxplots calculate Chapter confidence intervals Cov[X covariance cubic feet curves curvilinear degrees of freedom DFBETAS diagonal downweights dummy variable effect equals Equation estimated standard error example Exercise F-statistic F-test F₁ F₂ factor analysis factor scores Figure Gompertz curves graphs heteroscedasticity hypothesis income intercept Iteration leverage plot linear loadings Log Likelihood logarithms logit regression M-estimation mean median methods Monte Carlo multicollinearity negative nonlinear normal distribution Number of obs obtain outliers P-values parameters pattern percentile pollution population positively skewed postshortage water predicted values preshortage water principal components Prob problems quantile Quantile-Normal Plot R-square regression coefficients relationship resampling residuals robust regression rotation runoff sampling distribution scatterplot slope ẞ₁ standard deviation standard errors statistics sum of squares Summer 1981 Water symmetrical t-statistics Table theoretical transformation variance versus weights X₁ X₂ Y-intercept zero