Beruflich Dokumente
Kultur Dokumente
Chapter 14
Multiple Regression Analysis
LEARNING OBJECTIVES
2. Understand and apply significance tests of the regression model and its
coefficients.
3. Compute and interpret residuals, the standard error of the estimate, and the
coefficient of determination.
CHAPTER OUTLINE
KEY TERMS
Adjusted R2 R2
Coefficient of Multiple Determination (R2) Residual
Dependent Variable Response Plane
Independent Variable Response Surface
Least Squares Analysis Response Variable
Multiple Regression Standard Error of the Estimate
Outliers Sum of Squares of Error
Partial Regression Coefficient
There are four independent variables. If x2, x3, and x4 are held constant,
the predicted y will decrease by - 0.174 for every unit increase in x1.
Predicted y will increase by 6.02 for every unit increase in x2 is x1, x3, and
x4 are held constant. Predicted y will increase by 0.00026 for every unit
increase in x3 holding x1, x2, and x4 constant. If x4 is increased by one unit,
the predicted y will increase by 0.0041 if x1, x2, and x3 are held constant.
For every unit increase in x1, the predicted y increases by 0.08425 if x2 and
x3 are held constant. The predicted y will increase by 289.62 for every
unit increase in x2 if x1 and x3 are held constant. The predicted y will
decrease by 0.0947 for every unit increase in x3 if x1 and x2 are held
constant.
For every unit increase in paper consumption, the predicted per capita
consumption increases by 0.23368 if fish and gasoline consumption are
held constant. For every unit increase in fish consumption, the predicted
per capita consumption increases by 18.09 if paper and gasoline
consumption are held constant. For every unit increase in gasoline
consumption, the predicted per capita consumption decreases by 0.2116 if
paper and fish consumption are held constant.
Chapter 14: Multiple Regression Analysis 5
Insider Ownership =
17.68 - 0.0594 Debt Ratio - 0.118 Dividend Payout
The coefficients mean that for every unit of increase in debt ratio there is a
predicted decrease of - 0.0594 in insider ownership if dividend payout is
held constant. On the other hand, if dividend payout is increased by one
unit, there is a predicted drop of insider ownership by 0.118 if debt ratio is
held constant.
14.7 There are 9 predictors in this model. The F test for overall significance of
the model is 1.99 with a probability of .0825. This model is not
significant at α = .05. Only one of the t values is statistically significant.
Predictor x1 has a t of 2.73 which has an associated probability of .011 and
this is significant at α = .05.
14.8 This model contains three predictors. The F test is significant at α = .05
but not at α = .01. The t values indicate that only one of the three
predictors is significant. Predictor x1 yields a t value of 3.41 with an
associated probability of .005. I would recommend rerunning the model
using only x1 and then search for other variables besides x2 and x3 to
include in future models.
This model yields an F = 24.63 with p-value = .002. Thus, there is overall
significance at α = .01. One of the three predictors is significant. Paper
Consumption has a t = 5.31 with p-value of .003. Paper Consumption is
statistically significant at α = .01. The p-values of the t statistics for the
other two predictors are insignificant indicating that a model with just
Paper Consumption as a single predictor might be nearly as strong.
Chapter 14: Multiple Regression Analysis 6
Insider Ownership =
17.68 - 0.0594 Debt Ratio - 0.118 Dividend Payout
The overall value of F is only 0.02 with p-value of .982. This model is
not significant. Neither of the t values are significant (tDebt = -0.19 with a
p-value of .855 and tDividend = -0.11 with a p-value of .913).
14.12 The regression equation for the model using both x1 and x2 is:
ˆ
Yˆ = 235.143 - 16.7678 x1
14.14 The standard error of the estimate is 3.503. R2 is .408 and the adjusted R2
is only .203. This indicates that there are a lot of insignificant predictors
in the model. That is underscored by the fact that eight of the nine
predictors have nonsignificant t values.
14.15 se = 9.722, R2 = .515 but the adjusted R2 is only .404. The difference in the
two is due to the fact that two of the three predictors in the model are non-
significant. The model fits the data only modestly. The adjusted R2
indicates that 40.4% of the variance of y is accounted for by this model,
but 59.6% is unaccounted for.
14.16 The standard error of the estimate of 2085 indicates that this model
predicts within + 2085 on Per Capita Consumption about 68% of the time.
The entire range of Per Capita for the data is slightly more than 19,000.
Relative to this range, the standard error of the estimate is small. R2 = .
937 and the adjusted value of R2 is .899. Overall, this model is strong.
14.17 se = 6.544. R2 = .005 but the adjusted value of R2 is zero. This model has
no predictability.
14.19 For the regression equation for the model using both x1 and x2, se = 6.333,
R2 = .963 and adjusted R2 = .957. Overall, this is a very strong model. For
the regression model using only x1 as a predictor, the standard error of the
estimate is 6.124, R2 = .963 and the adjusted R2 = .960. The value of R2 is
the same as it was with the two predictors. However, the adjusted R2 is
slightly higher because the nonsignificant variable has been removed. In
conclusion, by using the one predictor model, we get virtually the same
predictability as with the two predictor model and it is more parsimonious.
14.21 Both the Normal Plot and the Histogram indicate that there may be some
problem with the error terms being normally distributed. Both the I Chart
and the Residuals vs. Fits show that there may be some lack of
homogeneity of error variance.
14.22 There are four predictors. The equation of the regression model is:
ŷ = -55.9 + 0.0105 x1 – 0.107 x2 + 0.579 x3 – 0.870 x4
The test for overall significance yields an F = 55.52 with a p-value of .000
which is significant at α = .001. Three of the t tests for regression
coefficients are significant at α = .01 including the coefficients for
x2, x3, and x4. The R2 value of 80.2% indicates strong predictability for the
model. The value of the adjusted R2 (78.8%) is close to R2 and se is 9.025.
14.23 There are two predictors in this model. The equation of the regression
model is:
ŷ = 203.3937 + 1.1151 x1 – 2.2115 x2
The F test for overall significance yields a value of 24.55 with an
associated p-value of .0000013 which is significant at α = .00001. Both
variables yield t values that are significant at a 5% level of significance.
x2 is significant at α = .001. The R2 is a rather modest 66.3% and the
standard error of the estimate is 51.761.
Chapter 14: Multiple Regression Analysis 9
14.26 The overall F for this model was 12.19 with a p-value of .002 which is
significant at α = .01. The t test for Silver is significant at α = .01 ( t =
4.94, p = .001). The t test for Aluminum yields a t = 3.30 with a p-value of
.016 which is significant at α = .05. The t test for Copper was
insignificant with a p-value of .939. The value of R2 was 82.1% compared
to an adjusted R2 of 75.3%. The gap between the two indicates the
presence of some insignificant predictors (Copper). The standard error of
the estimate is 53.44.
The low value of adjusted R2 indicates that the model has very low
predictability. Both t values are not significant (tNavalVessels = 0.67 with
p = .541 and tCommercial = 1.07 with p = .345). Neither predictor is a
significant predictor of employment.
Only one of the four predictors has a significant t ratio and that is Utility
with t = 2.57 and p = .018. The ratios and their respective probabilities
are:
This model is very weak. Only the predictor, Utility, shows much promise
in accounting for the grocery variability.
Chapter 14: Multiple Regression Analysis 11
14.32 Two of the diagnostic charts indicate that there may be a problem with the
error terms being normally distributed. The I Chart shows some slight
tendency for the error terms to be nonindependent. In addition, the
residuals vs. fits chart indicates a potential heteroscadasticity problem with
residuals for higher values of x producing more variability that those for
lower values of x.