BUS 082 Lecture Notes - Lecture 20: 2Degrees, Confidence Interval, Normal Distribution
Document Summary
Assumptions need to apply to do analysis. Linearity relationship needs to be linear. Independent error values are statistically independent. Error values are normally distributed for any given x value. Only need this assumption for very small samples or prediction intervals. The probability distribution of the errors has constant variance. Equal variance for all levels of x. Tests that the linear relationship is not due to change. Standard error of the regression slope coefficient b1 is estimated by. Is there a relationship between x and y. T stat = b1 b1 / sb1. Sb1 = standard error of the slope. Orange line guess for one particular house. Blue average of all houses of a certain size. Confidence interval estimate for an individual value of y given x. Confidence interval estimate for a mean value of y given a particular x. Examines the linear relationship between the dependent (y) and several. The multiple regression model independent variables (x)