POWERPOINT 4 Flashcards
quantity of interest
response variable
other data that could influence our prediction
explanatory variables
most widely used statistical tool for understanding relationships among variables; investigates functional relationships between one or more explanatory variables and an outcome of interest- the response variable
regression analysis
Y =f(X1,X2,…,Xp)+e
f(X1,X2,…,Xp) is a deterministic function of X1, X2,…,Xp
e is a random noise term
regression model general relationship
Y = b0 + b1X b0 = intercept b1 = slope in units of y/x
equation of a line
minimizing the amount by which the fitted value differs from the actual value
ei = Yi -Yˆi
residual
the line represents the ? values given by
Yˆi = b0 + b1X1
fitted value
N
chooses b0 and b1 to minimize
Least Squares
compares the predictive ability of each model
N N
1/n
average squared error