## EDUC 812 Quiz Regression

**EDUC 812 Quiz Regression**

Covers the Textbook material from Module 7: Week 7.

- For a bivariate regression, the assessment of effect size is determined by Pearson’s r.
- The researcher found that the model’s effect size was very large where
*r*= .426. Furthermore,*r**2*= .182. How much of the variance can be explained by the linear combination of predictor variables? *r*2 = .739 can be interpreted as 7% of the variance.- Table 1 provides a summary of the regression analysis for the variable predicting happiness. What can the researcher say about the variable sense of humor?
- A researcher rejected the null where
*r*(146) = .148,*p*= .03 and concluded that the effect size was - The researcher found that the model’s effect size was very large where
*r*= .325. Furthermore,*r**2*= .106. How much of the variance can be explained by the linear combination of predictor variables? - The formula Y′=
*b*0+*bX*is equivalent to: - To evaluate whether or not average life satisfaction self reported by residents of 119 nations was predictable from each nations’ GNP per capita, a bivariate linear regression was performed. Because of the small
*N*(only 119 countries), the distributions of scores on GNP and life satisfaction did not correspond closely to an ideal normal distribution. The result of the overall regression equation was,*F*(1, 117) = 3.77,*p*= .067. Based on these results, what can the researcher conclude? - r2 = .672 can be interpreted as 67.2% of the variance.
- Given Y’ =
*b*0 +*b*If*b*0 =0and*b*=5andX=1,Ywillequal: - What assumption is not required for a bivariate regression to be a valid description of the relationship between X and Y?
- The researcher found that the model’s effect size was very large where
*r*= .957. Furthermore,*r**2*= .917. How much of the variance can be explained by the linear combination of predictor variables? - A researcher rejected the null where
*r*(98) = .770,*p*< .001 and concluded that the effect size was - If the true slope is zero in a regression, then there is no relationship between the variables.
- Based on the following statistical statement, what conclusion can be made?
*t*(98) = 7.32,*p*< .001 - In a survey that included assessment of husband and wife heights, Hodges, Krech, & Crutcheld (1975) reported the following results. Treat the wife’s height as the predictor (X) variable and the husband’s height as the outcome (Y) variable.
- In the equation, Y’ =
*b*0 +*b*What does*b*0 represents: - A researcher rejected the null where
*r*(56) = .050,*p*= .27. Was the researcher correct in rejecting the null? - The Multiple Regression is used to determine if there is a relationship between multiple unrelated predictor variables and a criterion variable.
- If a predictor variable (x) is highly correlated with another predictor variable (x), the variables are providing essentially the same information. This is best referred to as multi-collinearity.
- To test for the absence of multi-collinearity, you would examine the Variance Inflation Factor (VIF).
- If you nd signicance in the multiple regression model, then you should examine the Coefficients to determine what variables are the best predictors.
- To detect bivariate outliers between all predictor variables and the criterion variable, the researcher should use which of the following?:
- The researcher found that the model’s effect size was very large where
*R*= .957. Furthermore,*R*2 = .917. How much of the variance can be explained by the linear combination of predictor variables? - If the true slope is zero in a regression, then there is no relationship between the variables.

Set 2

- The researcher found that the model’s effect size was very large where
*r*= .426. Furthermore,*r**2*= .182. How much of the variance can be explained by the linear combination of predictor variables? - To evaluate whether or not average life satisfaction self reported by residents of 119 nations was predictable from each nations’ GNP per capita, a bivariate linear regression was performed. Because of the small
*N*(only 119 countries), the distributions of scores on GNP and life satisfaction did not correspond closely to an ideal normal distribution. The result of the overall regression equation was,*F*(1, 117) = 3.77,*p*= .067. Based on these results, what can the researcher conclude? - A researcher wants to evaluate the null hypothesis which

states that the amount of time college students spend online does not signicantly predict their GPA. What is the best analysis to test this null hypothesis? - In a survey that included assessment of husband and wife heights, Hodges, Krech, & Crutcheld (1975) reported the following results. Treat the wife’s height as the predictor (X) variable and the husband’s height as the outcome (Y) variable.
- In the equation, Y’ =
*b*0 +*b*xX,*b*0 represents the: - The researcher found that the model’s effect size was very large where
*r*= .957. Furthermore,*r**2*= .917. How much of the variance can be explained by the linear combination of predictor variables? - A researcher rejected the null where
*r*(98) = .770,*p*< .001 and concluded that the effect size was - In bivariate regression, the amount of change in Y for one-unit change in X is:
- In the equation Y’ =
*b*0 +*b*x X , Y’ is level of boredom and X is listening to statistics tutorials. If*b*= 0, what can be said about the relationship between boredom and listening to statistics tutorials? - Table 1 provides a summary of the regression analysis for the variable predicting happiness. What can the researcher say about the variable sense of humor?
*r*2 = .739 can be interpreted as 7% of the variance.- What assumption is not required for a bivariate regression to be a valid description of the relationship between X and Y?
- A researcher rejected the null where
*r*(146) = .148,*p*= .03 and concluded that the effect size was - For a bivariate regression, the assessment of effect size is determined by Pearson’s r.
- A Bivariate Regression was conducted to evaluate the predictive relationship between total years of schooling and annual income. The results of the regression model were
*F*(1,88) = 4.1,*p*< .05. What can be concluded about these results? - Given Y’ =
*b*0 +*b*x If*b*0 =0and*b*=5andX=1,Ywillequal: - r2 = .672 can be interpreted as 67.2% of the variance.
- The researcher found that the model’s effect size was very large where
*r*= .325. Furthermore,*r**2*= .106. How much of the variance can be explained by the linear combination of predictor variables? - The Multiple Regression is used to determine if there is a relationship between multiple unrelated predictor variables and a criterion variable.
- If a predictor variable (x) is highly correlated with another predictor variable (x), the variables are providing essentially the same information. This is best referred to as multi-collinearity.
- To test for the absence of multi-collinearity, you would examine the Variance Ination Factor (VIF).
- If you nd signicance in the multiple regression model, then you should examine the Coecients to determine what variables are the best predictors.
- To detect bivariate outliers between all predictor variables and the criterion variable, the researcher should use which of the following?:
- The researcher found that the model’s effect size was very large where
*R*= .957. Furthermore,*R*2 = .917. How much of the variance can be explained by the linear combination of predictor variables? - If the true slope is zero in a regression, then there is no relationship between the variables.