PSYC232 Test 3, Week 8 Flashcards

(31 cards)

1
Q

Who is considered the father of behavioral and educational statistics?

A

Sir Francis Galton.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What was Galton’s goal in studying mental processes?

A

To measure psychological phenomena like boredom using observable behaviors (e.g., fidgets per breath).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Why might Galton’s boredom measurement not apply to kids or older adults?

A

Due to issues with reliability and validity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is linear regression?

A

Predicting a score on one variable using another variable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is multiple regression?

A

Predicting a score on one variable using more than one predictor variable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What does the regression equation look like?

A

Y′ = intercept + (predictors) + error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What does “predict” in a test question usually indicate?

A

That regression is being used.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are the key assumptions of regression?

A

Independence of observations
Normal distribution of variables
Linearity between predictors and outcome
Homoscedasticity of residuals

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is homoscedasticity?

A

Equal variance of residuals across all levels of the predictor(s).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What does R represent in regression output?

A

The correlation between the predicted and actual outcome values.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What does R² represent?

A

The proportion of variance in the outcome explained by the model.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is Adjusted R²?

A

A corrected R² that accounts for the number of predictors in the model.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How is model error calculated?

A

Error = 1 − R2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What does Box 1 in Jamovi show?

A

Overall model fit and significance (e.g., F-test, R²).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What does Box 2 in Jamovi show?

A

The contribution of each predictor (e.g., B, β, t, p-values).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What does the unstandardized coefficient (B) represent?

A

The change in the outcome for a one-unit change in the predictor.

17
Q

What does the standardized coefficient (β) represent?

A

The change in standard deviation units of the outcome per SD unit change in the predictor.

18
Q

What is the main goal of multiple regression?

A

To determine the unique contribution of each predictor to the outcome variable, controlling for other predictors.

19
Q

When is a predictor considered significant in multiple regression?

A

When it explains variance in the outcome that is not explained by other predictors.

20
Q

How is interpretation in multiple regression similar to linear regression?

A

The interpretation is the same, but in multiple regression, each predictor’s effect is assessed while controlling for all other predictors.

21
Q

How do you interpret a predictor in multiple regression?

A

As the amount of change in the outcome associated with a one-unit change in the predictor, controlling for other variables.

22
Q

Example interpretation: “A one-unit increase in attractiveness was associated with a .809 increase in romantic interest, controlling for gender.” What does this mean?

A

Attractiveness has a positive effect on romantic interest, independent of gender.

23
Q

Can categorical variables be used in regression?

A

Yes, especially if they have only two groups.

24
Q

How are categorical variables interpreted in regression?

A

As the difference in the outcome between the two groups, based on the numeric coding (e.g., 1 = men, 2 = women).

25
Example: “Going from men (1) to women (2) was associated with a decrease in romantic interest by .509 units.” What does this mean?
Men scored .509 units higher in romantic interest than women, controlling for attractiveness.
26
How do we compare the importance of predictors in a regression model?
By using the Standardized Estimates, which put all predictors on the same scale.
27
Why ignore the sign (+/-) when comparing standardized estimates?
Because we are interested in the size of the effect, not the direction.
28
What is regression to the mean?
A statistical phenomenon where extreme measurements tend to be closer to the mean upon repeated measurement.
29
Is regression to the mean a causal effect?
No, it is not causal and should not be confused with actual change over time.
30
Example: Why might a second album seem worse than the first?
Because the first was unusually good (extreme), and the second is closer to the average.
31
What’s the danger of ignoring regression to the mean in real-world decisions?
You might wrongly attribute changes to interventions (e.g., speed cameras) when they may be due to natural variation.