Question 1

What does a &#946; = -.17 indicate?&#10;A) That a one point increase in our predictor is associated with a .17 decrease in our outcome&#10;B) That a one point increase in our predictor is associated with a .17 increase in our outcome&#10;C) That the finding is not significant&#10;D) How much variance is explained by the predictor

Accepted Answer

A β (beta) coefficient of -.17 in regression analysis indicates that for every one unit increase in the predictor variable, the outcome variable is expected to decrease by .17 units, assuming all other variables in the model are held constant. This is a measure of the strength and direction of the association between the predictor and the outcome.

Question 2

In a regression, what does the R² statistic tell us? A) Whether the model is significant B) The relationship that the predictors have with the outcome variable C) If there is evidence of multicollinearity D) The amount of variance explained by the model

Accepted Answer

The R² statistic appears to be a typographical error or a misunderstanding. However, based on the context of regression analysis, it seems the question is referring to the R-squared (R²) statistic, which tells us the amount of variance in the dependent variable that is explained by the independent variable(s) in the model.

Question 3

Multicollinearity is when&#8230;&#10;A) there are very strong relationships between our predictor variables.&#10;B) there are very strong relationships between our predictor variables and the outcome variable.&#10;C) there are very weak relationships between our predictor variables.&#10;D) there are very weak relationships between our predictor variables and the outcome variable.

Accepted Answer

Multicollinearity refers to a situation in statistics where predictor variables in a multiple regression model are highly correlated. This correlation means that changes in one predictor variable are closely related to changes in another predictor variable, making it difficult to assess the individual effect of each predictor on the outcome variable.

Question 4

How many outliers are acceptable in a regression model?&#10;A) None&#10;B) Up to 5%&#10;C) Up to 10%&#10;D) Up to 1%

Accepted Answer

In practice, up to 5% of data points can be considered acceptable as outliers in a regression model, as they may not significantly affect the overall model performance.

Question 5

If our histogram of residuals shows a positive skew, then this means that the model is&#8230;&#10;A) overestimating.&#10;B) underestimating.&#10;C) neither over or underestimating.&#10;D) a good predictive model.

Accepted Answer

A positive skew in the histogram of residuals indicates that the model is overestimating.

Question 6

In an ideal regression model, we want our tolerance and VIF to be&#8230;&#10;A) tolerance greater than 2 and VIF less than 10.&#10;B) tolerance greater than 0.2 and VIF less than 10.&#10;C) tolerance less than 2 and VIF greater than 10.&#10;D) tolerance less than 0.2 and VIF greater than 10.

Accepted Answer

Tolerance values greater than 0.2 and VIF values less than 10 are generally considered acceptable thresholds indicating that multicollinearity is not a concern in the regression model. Tolerance is the inverse of VIF, so as tolerance increases, VIF decreases, indicating lower multicollinearity.

Question 7

If we find gender (0 = Male; 1 = Female) to be a significant predictor of aggression with a &#946; of -.82, then how would we interpret this?&#10;A) A one unit increase in gender is associated with a .82 decrease in aggression.&#10;B) Being female is associated with a .82 decrease in aggression.&#10;C) A .82 decrease in gender is associated with a one unit increase in aggression.&#10;D) Being male is associated with a .82 decrease in aggression.

Accepted Answer

Being female is associated with a .82 decrease in aggression.

Question 8

To interpret whether there is evidence of homoscedasticity we should look at&#8230;&#10;A) the histogram.&#10;B) the scatterplot.&#10;C) VIF.&#10;D) tolerance.

Accepted Answer

The scatterplot is used to visually assess the relationship between two quantitative variables, including patterns of variability (homoscedasticity) across the range of values. Homoscedasticity refers to the situation where the variance of the residuals is constant across all levels of the independent variable(s), and scatterplots can help identify whether this assumption is met.

Question 9

A researcher wants to explore the relationship between hair colour (blonde, brunette, auburn), salary, and empathy on amount of money donated to charity. He plans to use a regression analysis, what is wrong with this?

A) You cannot use a categorical variable (hair colour) in a regression analysis.
B) There are too many predictor variables.
C) There are too few predictor variables.
D) You cannot have a continuous outcome variable.

Accepted Answer

Regression analysis can indeed handle categorical variables by converting them into dummy variables, but the statement incorrectly suggests that categorical variables cannot be used in regression analysis. This is a common misconception.

Question 10

If a researcher found that being a smoker was associated with an increase in the risk of heart disease, then how should they graph this finding?&#10;A) Scatterplot&#10;B) Histogram&#10;C) Pie chart&#10;D) Bar chart

Accepted Answer

A bar chart is used to compare the frequencies of different categories. In this case, the categories are smokers and non-smokers, and the frequency is the risk of heart disease.

Question 11

In the worksheet analysis, which of the assumptions of multiple regression have been violated?&#10;A) Normal distribution of residuals&#10;B) Homoscedasticity&#10;C) No multicollinearity&#10;D) None of the assumptions have been violated.

Accepted Answer

The answer of In the worksheet analysis, which of the...

Question 12

How much of the variance (as a %) in the outcome variable can be explained by the predictors entered into the model?&#10;A) 49.9%&#10;B) 11.5%&#10;C) 24.0%&#10;D) 4.99%

Accepted Answer

The answer of How much of the variance (as a...

Question 13

What is the significance of the overall model?&#10;A) p = .037&#10;B) p = .003&#10;C) p = .044&#10;D) p < .001

Accepted Answer

The answer of What is the significance of the overall...

Question 14

How would you interpret the &#946; for the &#34;location&#34; predictor variable?&#10;A) Children living in rural environments have a score 3.027 higher than children living in urban environments.&#10;B) Children living in rural environments have a score 3.027 lower than children living in urban environments.&#10;C) Children living in rural environments have a score 4.481 higher than children living in urban environments.&#10;D) Children living in rural environments have a score 4.481 lower than children living in urban environments.

Accepted Answer

The answer of How would you interpret the &#946; for...

Question 15

Which variable was the most highly significant predictor of the outcome variable?&#10;A) Attention (n back)&#10;B) Hours spent in nature&#10;C) Connectedness to nature&#10;D) Living environment (urban/rural)

Accepted Answer

The answer of Which variable was the most highly significant...

Deck 16: Multiple Regression