Multiple Regression Flashcards

1
Q

What is Linear Regression?

A

Linear Regression ask about the effect of one on another. It distinguishes between Independent variables (influencing) and the Dependent variable (being influenced).

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

Causality and Linear Regression

A

Line of best fit and ask about the relative variance explained by the straight line model relative to the unexplained variance (like a t-test)

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

Method of Least Squares

A

The straight line minimises the size of the squares resulting from drawing a vertical line from the point to the line and making this into a square

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

What is the equation for the Straight Line Model?

A

Y= mX + c

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

What is Y in the equation for the straight line?

A

Y is the predicted score on the DV

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

What is X in the equation for the straight line?

A

X is the score on the IV

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

What is m in the equation of the straight line?

A

m is the gradient or the slope (the steepness of the line)

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

What is c in the equation of the straight line?

A

c is the intercept (where the line crosses the y axis)

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

How do we calculate the straight line model with Y = mX + c

A

Multiple the score on the IV (X) by the gradient (m) and add the intercept (c)

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

Why is m important?

A

it tells us whether there is a positive, negative or neutral relationship between the DV and Ive, depending on the slope.

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

What would a positive m mean?

A

A line would have an upward slope

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

What would a neutral m mean?

A

A horizontal slope

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

What would a negative m mean?

A

A downward line/slope

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

How to calculate the best fit intercept

A

c = Y(mean) - m X(mean)

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

What is the SST?

A

Total variability in data - difference between each Y value and mean value of Y

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

What is the SSR?

A

Difference between observed Ys and those predicted by the model: Residual/ unexplained variance

17
Q

SSM is calculated by what equation?

A

SSm = SST - SSR

18
Q

What is the difference between the Set and the SSR?

A

The measure of how much variance is explained.

19
Q

How do you calculate the total variance?

A

SST = the sum of (Y- Ymean) and then squared

20
Q

How to calculate the SS residuals?

A

Differences between the Y value and the participant’s predicted Y value.

SSR = Sum of (Y -Ypred) squared

21
Q

How to calculate the SSM

A

SSm = SST - SSR

22
Q

What does Rsquared tell us?

A

The proportion of the variance in the DV is explained by the IV

23
Q

What is the equation for Rsquared?

A

Rsquared = SSM/ SST

24
Q

How to get the mean of X?

A

Add up all the scores of the independent variable and average

25
How to get the mean of Y?
Add up all the scores of the dependent variable and average
26
How to calculate the gradient (m)?
The sum of (X-Xmean) x (Y-Ymean) ___________________________ sum of (X-Xmean) squared
27
How do you calculate the intercept c?
C = Ymean - m(Xmean)