SUMMARY OUTPUT Regression Statistics Multiple R 0.873296211 0.762646272 R Square
ID: 3171413 • Letter: S
Question
SUMMARY OUTPUT Regression Statistics Multiple R 0.873296211 0.762646272 R Square Adjusted R So 0.643969409 Standard Erre 4.80196987 Observation ANOVA Significance F MS 3 444.546512 148.182171 6.42624222 0.026509524 Regression 6 138.353488 23.0589146 Residual 582.9 Total cients tandard Errol t p Lower 95% r 95% Lower 95.0% Upper 95.0% 136.1412621 62.9245496 Stat 290 112088 2.16356355 0.07371354 -17.829 290.112088 17.829564 Intercept -0.1991543 0.237356 Home Runs 0.019100828 0.08919617 o.21414402 0.83752683 -0.199154348 0.237356 Runs 0.176076352 0.06039388 2.91546666 0.02678896 0.028297844 o 3238s486 0.02829784 0.32385486 Batting Avg. 672.9987472 423.303511 1.5898728 0.16296592 1708.785124 362.78763 1708.7851. 362.78763 RESIDUAL OUTPUT Observation Predicted Wins Residuals ABS Erroor 1 94.53903098 7.46096902 7.46096902 2 79.76522031 -0.7652203 0.76522031 3 94.07305981 0.92694019 0.92694019 4 99.3454284 -0.3454284 0.3454284 5 100.3754485 -2.3754485 2.3 6 104.0312396 1.96876036 1.96876036 7 101.292263 0.70773703 0.70773703 8 96.41008921 8.4100892 8.41008921 9 91.46550506 0.53449494 0.53449494 10 89.70271516 0.29728484 0.29728484Explanation / Answer
1) Correlation coefficient measures the relationship between two variables. A value of 1 means there is perfect positive correlation amongst the variables (If one increases, the other increases as well). Whereas, a value of -1 means there is perfect negative correlaions amongst the variables (one increases, the other decreases). Coefficient of determination (better known as r-squared) states how much percentage of a variation in dependent variable is accounted for by the independent variable. Here, it is 0.7626. Hence, about 76% of the variation in dependent variable is accounted for by the independent variable. r is 0.8732. Hence, in case of correlation coefficient, if one variable goes up, the other does as well.
2) MAD lets us know how spread out a data is. t Stat is the coefficient divided by its standard error. F statitics in regression means mean regression sum of squares divided by the mean error sum of squares.
3) Multicollinearity means if two of the independent variables are highly correlated amongst themselves. If such a scenario arises then the model would not be able to determine as to which of the independent variables is actually having an effect on the dependent variable.
Autocorrelation actually means correlation amongst residuals. 0 to 2 is postive serial autocorrelation and 2 to 4 is negative serial autocorrelation.
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.