Page 18 - FINAL CFA II SLIDES JUNE 2019 DAY 3
P. 18

LOS 8.h: Distinguish between and interpret the                 READING 8: MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS
     R and adjusted R in multiple regression.
      2
                         2
                                                                    MODULE 8.4: COEFFICIENT OF DETERMINATION & ADJUSTED R-SQUARED

      EXAMPLE: Calculating R and adjusted R An analyst runs a regression of monthly value-stock returns on five independent variables
                                                 2:
                                2
      over 60 months. The total sum of squares for the regression is 460 (SST), and the sum of squared errors is 170 (SSE). Calculate the R and
                                                                                                                                        2
                 2
      adjusted Ra .
                                                                                               The five independent variables together
                                                                                               explain 63% of the variation in monthly
                                                                                               value-stock returns.













                                             2
     EXAMPLE: Interpreting adjusted R : Suppose the analyst now adds 4 more independent variables to the regression, and the
     R increases to 65.0%. Identify which model the analyst would most likely prefer.
       2








     Answer: With 9 independent variables, even though the R has increased from 63% to 65%, the adjusted R has decreased
                                                                                                                       2
                                                                   2
     from 59.6% to 58.7%:
                                                            2
    Analyst would prefer the first because the adjusted R is higher and the model has 5 independent variables as opposed to 9 (all
    else the same, the fewer independent variables, better the predictive accurate/power)
   13   14   15   16   17   18   19   20   21   22   23