Week 2

Question 1

What is a regression?

Answer 1

A regression is an approach for modelling the relationship between a DV and one or more IVs.

Question 2

What is a linear regression?

Answer 2

This is when the DV is quantitative and it is used to model the relationship between a quantitative DV and one or more IVs

Question 3

What is a linear probability model or LLogistic regression?

Answer 3

When the DV is qualitative / binary

Question 4

So what’s the different in the objective of findings for when the regression is observational vs experimental?

Answer 4

When looking at observational data, the regression uncovers patterns of association.
When looking at experimental data, the regression is used to estimate the causal effect

Question 5

Simple vs multiple linear regression?

Answer 5

Simple -> 1 IV
Multiple -> 2+ IVs

Question 6

What is the error term in a regression model?

Answer 6

It is a catch-all term for what we miss with the simple model. It includes all other factors that can affect the DV

Question 7

What is the residual?

Answer 7

The difference between the actual value and the predicted value. IT captures all factors or variations in the DV that are not explained by the IV

Question 8

What is the kind of effect for a IV when there are multipl

Answer 8

it has a partial effect on the DV

Question 9

So what does the intercept coefficient mean in a regression equation?

Answer 9

it is the average value of y when x=0, the baseline level of y when x has no influence

Question 10

What is the slope coefficient?

Answer 10

The expected difference in y corresponding to one unit different in x

Question 11

What is the different in interpretation for slope coefficient for observational data vs experimental data?

Answer 11

Experimental -> slope is interpreted as the causal effect of x on y
Observational -> slope coefficient shows the association or expected difference in y for a one unit difference in x