Critical Numbers 6: Regression: estimation and prediction

Question 1

correlation vs regression

Answer 1

Correlation
Quantifies the linear association between two numeric variables
Variable order doesn’t matter (correlate x~y or y~x)

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

Question 2

univariable regression equation: what does each variable show

Answer 2

y= a + bx

y=response/outcome/dependent
a= known as constant
b= regression coefficient (gradiebt of regression line)

Question 3

multivariable regression

Answer 3

y= α+β1x1+ β2x2 + …

account for confounding variable, used for predictions

Question 4

prognostic modelling

Answer 4

forecast of future outcomes, 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
Used to guide decision making