第5章 多元回归分析：进一步讨论.pptVIP

第五章　多元回归分析论Multiple Regression Analysis Redefining Variables: An Examplethe determinations of infant birth weight Variables bwghtkg, child birth weight in kilograms bwghtg, child birth weight in grams bwghtjin, child birth weight in jin cigs, number of cigarettes the mother smoked per day while pregnant packs, packs of cigarettes the mother smoked per day while pregnant and 1 packs=20 cigs faminc, annual family income Model y=b0+b1x+b2faminc+u y stand for bwghtkg, bwghtg, bwghtkjin; x stand for cigs or packs Redefining Variables, cont. Redefining Variables , cont. Redefining Variables , cont. Changing the scale of the y variable will lead to a corresponding change in the scale of the coefficients and standard errors, t-stats and R2 is not changed Changing the scale of one x variable will lead to a change in the scale of that coefficient and standard error, t-stats and R2 is not changed Standardized Coefficients (Beta Coefficients) Occasional you’ll see reference to a “standardized coefficient” or “beta coefficient” which has a specific meaning Idea is to replace y and each x variable with a standardized version – i.e. subtract mean and divide by standard deviation Coefficient reflects standard deviation of y for a one standard deviation change in x Standardized Coefficients, ExampleThe determinations of wage, wage1.raw The population model in level-level model wage=b0+b1educ+b2exper+b3tenure+u Estimating the standardized model zwage=0.449zeduc+0.082zexper+0.331ztenure What the meaning of the estimated parameters? The estimated coefficient of zeduc means when the educ changed one standard deviation, the wage will change 0.449 standard deviation. Stata command reg wage educ exper tenure, beta Functional Form OLS can be used for relationships that are not strictly linear in x and y by using nonlinear functions of x and y – will still be linear in the parameters Can take the natural log of x, y or both Can use quadratic forms of x Can use interactions of