Regression Practice Quiz Flashcards
(36 cards)
What does multiple linear regression analysis explore?
a) Relationship between 1 outcome variable and multiple predictor variables
b) Relationship between one predictor variable and one outcome variable
c) Relationship between multiple outcome variables and a single predictor variable
d) Relationship between multiple predictor variables only, with an outcome
A
What does the hypothesis statement (H₀: β₁ = β₂ = 0) indicate?
a) At least one predictor variable contributes to predicting the outcome variable
b) Both predictor variables contribute to predicting the outcome
c) Neither of the predictor variable has predictive value for the outcome variable
d) A third, unlisted variable is influencing the outcome
C
Which metric is most suitable for evaluating how well a multiple linear regression model fits the data?
a) Adjusted R²
b) R²
c) The models intercept
d) Individual regression coefficients
A
When is it recommended to use standardised coefficients to assess the relative impact of predictor variables in a multiple regression model?
a) When all predictors are measured using the same units
b) When the predictors are measured in different units
c) When not all predictors share the same scale of measurement
d) When all predictors are based on an ordinal scale from 1 to 6
C
What is the slope of the line y = -4.7x + 1.8?
a) 1.8
b) -1.8
c) -4.7
d) 4.7
C
Which term refers to how well the regression line represents the actual data?
a) Slope of the line
b) Coefficient of determination
c) Standard error of the slope estimate
d) Standard error of the intercept
B
My estimated regression line is Y = 12 + 5.6X. The intercept is equal to:
a) 5.6
b) 17.6
c) 6.4
d) 12
D
A psychologist would like to investigate if perceived social support influences cognitive function. The mean of perceived social support scores is 12.4, the mean of cognitive function is 28, and the slope is 1.9. What is the intercept of the regression equation?
a) 3.44
b) 4.44
c) 5.44
d) 6.44
B
Curious about relationship between age (x) and the number of birthday presents (y) received. Find that the correlation coefficient (r) is 0.45, and the following stats are known:
Age(x) Presents(y)
Mean 14.5 6.3
SD 8.1 4.3
What is the regression equation associated with this data?
a) ŷ = 6.3 – 0.45x
b) ŷ= 3.0 – 0.45x
c) ŷ = 10.84 – 0.24x
d) ŷ = 2.82 + 0.24x
D
Which is the following is NOT TRUE regarding linear regression?
a) It identifies significant predictors for a continuous outcome variable
b) It predicts the outcome of a binary variable with continuous variables
c) It quantifies a relationship between 2 continuous variables
d) It models a linear relationship between 2 continuous variables
B
Which of the following is NOT an assumption for simple linear regression?
a) Multicollinearity
b) Linear relationship
c) Constant variance
d) The residuals should be normally distributed
A
Which of the following is TRUE about the homoscedasticity assumption in simple linear regression?
a) The residuals must be normally distributed
b) The residuals have a constant variance
c) The residuals are correlated with the predictor variable
d) The residuals increase as the predictor variable increases
B
What does ŷ represent in the context of linear regression?
a) The actual values of the outcome variable observed in the dataset
b) The residuals or errors between the observed and predicted values
c) The predicted values of the outcome variable based on the regression model
d) The slope of the regression line
C
What does an R-squared value represent in simple linear regression?
a) The ratio of the explained variation to the total variation
b) The slope of the regression line
c) The strength of the correlation between the models predictions and actual values
d) The percentage of data points that fall on the regression line
A
When calculating the residuals of a linear regression model, what is the relationship between ŷ and the residuals?
a) Residuals are the difference between ŷ and the actual y values
b) Residuals are calculated as the sum of ŷ and the actual y values
c) Residuals are the product of ŷ and the actual y values
d) There is no relationship between residuals and ŷ
A
What does multicollinearity in the context of multiple linear regression refer to?
a) A low correlation between the outcome and predictor variables
b) Predictor variables being normally distributed
c) Outcome variable variance being constant
d) A high correlation between two or more predictor variables
D
Which of these write-ups uses the standardised beta coefficients?
a) A linear regression model revealed that head size (measured in cm) significantly predicted participant scores on an IQ test (b = 0.967, t(8) = 10.27, p < .001, R2 = .93)
b) A linear regression model revealed that head size (measured in cm) significantly predicted participant scores on an IQ test (b = 1.194, F(1,8) = 115.1, p < .001, R2 = .93)
c) A linear regression model revealed that head size (measured in cm) significantly predicted participant scores on an IQ test (𝛽 = 0.967, F(1,8) = 115.1, p < .001, R2 = .93)
d) A linear regression model revealed that head size (measured in cm) significantly predicted participant scores on an IQ test (b = 0.74, t(8) = 9.23, p < .001, R² = .91)
C
Your model has three predictors with the following standardised betas:
Variable 1 = -.812
Variable 2 = .127
variable 3 = .456
From most important to least important, what is the correct order of variables:
a) Best is 1 then 2 then 3 is worst
b) Best is 3 then 1 then 2 is worst
c) Best is 3 then 2 then 1 is worst
d) Best is 1 then 3 then 2 is worst
D
A multiple regression model is run to predict job satisfaction from salary, work-life balance and years of experience. The results are:
Job satisfaction = 2.1 + 0.03 (salary) + 1.2 (work life balance) - 0.05 (years of experience)
Which is the following is true?
a) An increase in salary is associated with a decrease in job satisfaction
b) Holding other variables constant, work-life balance has the strongest positive effect on job satisfaction
c) Job satisfaction decreases by 1.2 for every unit increase in work-life balance
d) Years of experience is the only significant predictor
B
A multiple regression model predicting test performance from sleep, study hours and stress level gives an Adjust R² value of 0.52.
What does the Adjusted R² value mean in this context?
a) The model explains 62& of the variability in test performance
b) 62% of the predictors are significant
c) Each predictor explains 62% of the outcome
d) 38% of the variability in test performance is caused by error in measurement
A
What does regression analysis aim to do?
a) Determine the average of all observations
b) Measure the strength of a relationship without implying causation
c) Model the causal effect of one or more variables on an outcome
d) Prove causation in all circumstances
C
In a regression model, the IV is also called:
a) Dependent variable
b) Outcome variable
c) Criterion variable
d) Predictor variable
D- Can be called predictor and explanatory variable (x in regression model)
What does a positive residual indicate in a regression model?
a) the model overestimated the actual value
b) The prediction was perfect
c) the model underestimated the actual value
d) the data point lies on the regression line
C
What is the main limitation of the Mean model?
a) It requires multiple predictors
b) It predicts different values for different inputs
c) It ignores the predictor variable completely
d) It always produces a negative residual
C
