PSYCH 100A Lecture Notes - Lecture 14: Simple Linear Regression
Document Summary
Y = a + bx + e. A and b are constants (coefficients) expressing the relationship between x and y. A is the y-intercept (the value of y when x = 0) B is the slope of the line: determines how much the y variable will change when x is increased by one point. Example: cover charge for the club is , each drink costs . Residual= error in the prediction e : e = y - (y hat) Standardized statistical technique used for finding the best-fitting straight line for a set of data. What is the best-fitting line: minimize the distance between observed y values and y values predicted by x and the regression line. Technically we minimize the sum of the squared residuals (ssres) B = a = - b a = expected/predicted value of y when x = 0. B = amount of change in y expected/predicted for a 1 unit increase in x.
