Regression

Question 1

Regression line

Answer 1

Allows one variable, y, to be predicted from the other, x,
Order does matter (predict y from x)
Can handle multiple predictors (predict y from x1, x2, x3…)
Variables don’t have to be numeric

Question 2

Logistic regression

Answer 2

Binary outcome

Question 3

Linear regression

Answer 3

Numeric outcome

Question 4

Univariable regression

Answer 4

y = a + bx

y - dependent variable (outcome)
a - y intercept
b - regression coefficient : line slope
x - independent variable (predictor)

Question 5

Multi variable regression

Answer 5

Combination of risk factors/predictors (x values)
Can adjust for confounders - reduces bias (ADJUSTED)
Explore interactions
Predicts based on
Eg y = a + bx1 + bx2 + …

Question 6

Adjusted

Answer 6

Data adjusted for confounders to reduce bias

Question 7

Crude

Answer 7

Confounding variables not accounted for

Question 8

Multivariate regression

Answer 8

Lots of outcomes (y values)

Question 9

Correlation

Answer 9

a measure of linear relationship between variables
• Quantified by the correlation coefficient r
• r is bound between -1 and 1
• The closer to |1|, the stronger the correlation
• The closer to 0, the weaker the correlation
• Can be positive (as one variable increases, so does the other) Or negative (as one variable increases, the other decreases)
• The ordering of the variables does not

Question 10

B : regression coefficient

Answer 10

The slope (gradient) of the regression line
The larger the value the steeper the slope
The sign indicates the direction of effect
It is the change in y associated with a unit change in x

Question 11

Why do we model multiple variables together

Answer 11

More realistic
More efficient
More accurate

Question 12

Advantages of multiple regression

Answer 12

-We can adjust or control for the effects of other variables. Incorporating multiple variables in a model means we can adjust our variables of interest for the effects of potential confounders.
-We can analyse the simultaneous effects of multiple variables on an outcome and look for independent predictors or interaction effects
-We can make predictions based on combinations of risk factors – this is essential in clinical prediction modelling

Question 13

Prognosis

Answer 13

Forecast of future outcomes

Question 14

Prognostic modelling

Answer 14

uses advanced regression techniques to predict the risk of illness or future course of illness for an individual based on their individual combination of clinical and non-clinical characteristics
-Move towards stratified medicine
-Informs clinical decision-making

Question 15

Statements about prognosis used to

Answer 15

Inform patients and families about likely future outcomes
Guide decisions regarding course of treatment

Question 16

Extrapolation

Answer 16

Data outside the observed data range
Unreliable

Question 17

Interpolation

Answer 17

Data inside the data range
Reliable

Question 18

Null hypothesis

Answer 18

Regression line = 0

Question 19

If 95% confidence interval doesn’t contain 0

Answer 19

Reject null hypothesis- significant predictor of outcome

Question 20

Univariable regression

Answer 20

One predictor (x)

Question 21

Outcome variable

Answer 21

Dependent variable

Question 22

Predictor variable

Answer 22

Independent variable

Question 23

If regression results are reported as adjusted or controlling for….

Answer 23

It was a multi variable model