214 (2) lecture 2 Flashcards

(23 cards)

1
Q

What is linear regression?

A

The simplest form of generalized linear modelling (GLM)

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

What is the equation for regression when you have 1 IV?

A

Y= a + bX (+e)

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

What does the +e stand for in the regression equation?

A

Error

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

What are outcome variables?

A

DVs

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

What are predictor variables?

A

IVs

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

What does linear regression seek to do?

A

determine how well a model can recreate the data

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

What does linear regression do?

A

looks to fit a ‘line of best fit’ through (scatterplot) points

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

What does linear regression allow us to do?

A

allows prediction of one variable from another (diff. to correlation)

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

What does regression assume about variables?

A

assumes effects of one variable on others is additive: an increase of 1 unit onA leads to a change of X units in B no matter where this change happens

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

What does regression allow us to predict?

A

allows us to predict the value of one variable (Y) from the value of another (X)

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

How does regression allow us to predict?

A

does this using the line of best fit

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

What is the line of best . fit?

A

the linear line that minimizes deviation of each point

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

What does less deviation (variance) mean for prediction?

A

More accurate predictions

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

What information is needed to construct a linear equation?

A
  1. Slope

2. Intercept

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

What is B in the regression equation?

A

The slope

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

How do you work out the slope (B)

A

The change in Y / associated change in X

- requires 2 co-ordinates, the difference between these coordinates is calculated and these are divided.

17
Q

What is regression weight?

A

(B) The slope, the amount by which the X value is being weighted in the calculation .

18
Q

What is Beta?

A

when X and Y are measured in standard (Z) scores

19
Q

What are residuals?

A

Essentially the error

Observed values minus predicted value
The score with the effect of X removed.

20
Q

How is prediction accuracy assessed?

A

Looking at variability (sum of squared deviations) - coefficient of determination (R2)

Significance testing - ANOVA, sig result suggests there is a relationship between IV and DV.

21
Q

What are
SS(Regression) .
and
SS(error)

A
Regression = R2 
error = 1 - R2
22
Q

How do you conduct regression in SPSS?

A
Analyze
Regression 
Linear 
Select DV and IV 
OK
23
Q

What are the Intercpet, B (slope) and Beta values in SPSS output?

A
Intercept = top 'B' column 
B = bottom 'B' column 
Beta = beta column