Ivy_Honeywell_Data Analytics_3.1

The strength of the correlation between a set of independent variables X and a dependant variable Y is measured by:

• Coefficient of correlation

• Coefficient of Determination

• Standard Error of Estimate

• All of the above

The percent of total variation of the dependant variable Y explained by the set of independent variables X is measured by:

• Coefficient of Correlation

• Coefficient of Skewness

• Coefficient of Determination

• Standard Error or Estimate

• Multicollinearity

A coefficient of correlation is computed to be -0.95 means that

• The relationship between the two variables is weak

• The relationship between the two variables is strong and positive

• The relationship between the two variables is strong but weak.

• Correlation coefficient cannot have this value.

Let the coefficient of determination computed to be 0.39 in a problem involving one independent variable and one dependant variable. This result means that:

• The relationship between the two variables is negative.

• The correlation coefficient is 0.39

• 39% of the total variation is explained by the independent variable.

• 39% of the total variation is explained by the dependant variable.

Relationship between correlation coefficient and coefficient of determinants is that

• Both are unrelated

• The coefficient of determination is the coefficient of correlation squared

• The coefficient of determination is the square root of the coefficient of correlation.

• Both are equal

Multicollinearity exists when

• Independent variables are correlated less than -0.70 or more than 0.70

• An independent variable is strongly correlated with a dependant variable.

• There is only one independent variable.

• The relationship between dependant and independent variable is nonlinear.

If ‘Time’ is used as the independent variable in a simple linear regression analysis, then which of the following assumption could be violated

• There is a linear relationship between the independent and dependent variables.

• The residual variation is the same for all fitted values of Y

• The residuals are normally distributed.

• Successful observations of the dependant variable are uncorrelated.

In multiple regression, when the global test of significance is rejected, we can conclude that

• All of the net sample regression coefficients are equal to zero.

• All of the same regression coefficients are not equal to zero.

• At least one sample regression coefficient is not equal to zero.

• The regression equation intersects the Y-axis at zero.

A residual is defined as

^

• Y-Y (Y-Y cap)

• Error sum of square

• Regression sum of squares

• Type I Error

What test statistic is used for a global test of significance?

• Z test

• T test

• Chi-square test

• F test