Applied regression: an introduction
Applied regression allows social scientists who are not specialists in quantitative techniques to arrive at clear verbal explanations of their numerical results. Provides a lucid discussion of more specialized subjects: analysis of residuals, interaction effects, specification error, multicollinearity, standardized coefficients, and dummy variables.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Assumptions and Inferences
1 other sections not shown
Other editions - View all
05 level applied regression autocorrelation average beta weight bias bivariate regression model biXi campaign contributions causal coal mining fatality coefficient of determination coefficient of multiple confidence interval correlated dependent dummy variable effect employee error of estimate error term explanation explanatory variables Figure formula high multicollinearity Homoskedasticity impact income in dollars independent variables indicates instance least squares estimates Lewis-Beck measured mining fatality rate multiple regression equation multiple regression model noninterval variables normal null hypothesis observations ordinal variable outliers parameter estimates partial slope estimate population prediction equation prediction error problem provides ratio Regressing each independent regression analysis regression assumptions regression coefficients regression line relationship Republican residuals respondent Riverside example Riverside study safety budget safety expenditures sample scatterplot score seniority significance tests simple random sample specification error standard deviation standard error statistical significance straight line Suppose three-variable two-tailed Type II error variance variation Xi and X2