Scribd
Upload
53 views3 pages

ANOVA Results for Regression Model

The document analyzes the results of an ANOVA test conducted on a regression model. The ANOVA table shows that the regression model is statistically significant at predicting the dependent variable (DPR) based on the independent variables (LC, TANG, DEBT, EXT), as the significance value is 0.00, which is less than 0.01. The model explains 79.3% of the variance in the dependent variable, as shown by the R-square value. However, as shown in the Coefficients table, none of the independent variables are statistically significant predictors on their own, as all the significance values are greater than 0.1.

Uploaded by

Muhammad Ali
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as RTF, PDF, TXT or read online on Scribd
53 views3 pages

ANOVA Results for Regression Model

The document analyzes the results of an ANOVA test conducted on a regression model. The ANOVA table shows that the regression model is statistically significant at predicting the dependent variable (DPR) based on the independent variables (LC, TANG, DEBT, EXT), as the significance value is 0.00, which is less than 0.01. The model explains 79.3% of the variance in the dependent variable, as shown by the R-square value. However, as shown in the Coefficients table, none of the independent variables are statistically significant predictors on their own, as all the significance values are greater than 0.1.

Uploaded by

Muhammad Ali
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as RTF, PDF, TXT or read online on Scribd

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 49.210 4 12.302 45.969 .000a

Residual 12.846 48 .268

Total 62.056 52

a. Predictors: (Constant), LC, TANG, DEBT, EXT

b. Dependent Variable: DPR

To measure the model fit I interpret the ANOVA table first. ANOVA table explained the deviation
in the dependent variable. In this table If Sig < .01, then the model is significant at 99%, if Sig
< .05, then the model is significant at 95%, and if Sig <.1, the model is significant at 90%.
Significance implies that we can accept the model. If Sig>.,1 then the model was not significant
(a relationship could not be found) or "R-square is not significantly different from zero." In my
case significance of model is .00, which is less than .01 . it means that model is significant at
99%. The results show the significant relationship of dependent variable and independent
variable.

In the ANOVA table the TSS (Total Sum of Squares) is the total deviations in the dependent
variable. The aim of the regression is to explain these deviations. In my result TSS is 62.056.
The ESS (Explained Sum of Squares) is the amount of the TSS that could be explained by the
model. In my results the ESS is 49.210. The RSS is the amount that could not be explained (TSS
minus ESS). In my results RSS is 12.846.
Model Summary

Adjusted R Std. Error of the


Model R R Square Square Estimate

1 .891a .793 .776 .5173245

a. Predictors: (Constant), LC, TANG, DEBT, EXT

Adjusted R-square
Adjusted R-square Measures the proportion of the variance in the dependent variable
(DIVIDEND PAYOUT RATIO) that is explained by variations in the independent variables. In
this table the “Adjusted R-Square” shows that 77.6% of the variance is explained.

R-square
The R-square is the ratio of ESS/TSS. It captures the percent of deviation from the mean in the
dependent variable that could be explained by the model. In my result R square is 79.3%, which
means that 79.3 % of deviation from the mean in the dependent variable is explained by the
model.
Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) -.053 .508 -.105 .917

TANG .522 .379 .101 1.377 .175

DEBT .713 .444 .120 1.605 .115

EXT -.149 .361 -.056 -.412 .682

LC -2.776 .408 -.922 -6.802 .000

a. Dependent Variable: DPR

The table “Coefficients” provides information on the confidence with which we can support the
estimate for each such estimate. If the value in “Sig.” is less than 0.05, then we can assume that
the estimate in column “B” can be asserted as true with a 95% level of confidence. So I interpret
the "Sig" value first. If this value is more than 0 .1 then the coefficient estimate is not reliable
because it has "too" much dispersion/variance. In my results all the independent variable are not
statistically significant.

You might also like