regression analysis Flashcards
what is correlation used for
to quantify linear relationship between two numeric variables
what are values for correlation
bound between -1 and 1
0 means no linear relationship
the further away from 0 the stronger the linear relationship
can be positive or negative
does variable order matter for correlation
no
you can correlate x-y or y-x
what is regression
allows one variable to be predicted from the other
can handle multiple predictors
variables don’t have to be numeric
does variable order matter for regression
yes
you predict x from y
what do y and x represent
the variables we are looking at
what do a and b represent
they explain the linear relationship betweeen y and x
what is the regression equation
y = a + bx
what is y
the variable being predicted
the “response “ or “outcome” or “dependent” variable ( its value depends on x)
what is a
the intercept of the regression line
also known as the constant
this is the point at which the line cross the y axis when x=0
what is b
the regression coefficient
the slope ( gradient ) of the regression line
the ledger 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
what is x
the “predictor” or “ explanatory” or “independent “ variable
it is the variable we are using to predict y