You are on page 1of 10

Simple Linear Regression

2.1 Simple Linear Regression Model


y = F0 + F1 x + u x: regressor variable (indep) y: response variable (dep) F0: the intercept, unknown F1: the slope, unknown u: error with E(u) = 0 and Var(u) = W2 (unknown) The errors are uncorrelated.
2

Given x, E(y|x) = E(F0 + F1 x + I) = F0 + F1 x Var(y|x) = Var(F0 + F1 x + I) = W2 Responses are also uncorrelated. Regression coefficients: F0, F1 F1: the change of E(y|x) by a unit change in x F0: E(y|x=0)

2.2 Least-squares Estimation of the Parameters


2.2.1 Estimation of F0 and F1 n pairs: (yi, xi), i = 1, , n Method of least squares: Minimize
n

S ( F 0 , F1 ) ! [ y i  ( F 0  F1 xi )]
i !1

Least-squares normal equations:

The least-squares estimator:

The fitted simple regression model:

A point estimate of the mean of y for a particular x Residual:

An important role in investigating the adequacy of the fitted regression model and in detecting departures from the underlying assumption! 7

Example 2.1: The Rocket Propellant Data Shear strength is related to the age in weeks of the batch of sustainer propellant. 20 observations From scatter diagram, there is a strong relationship between shear strength (y) and propellant age (x). Assumption y = F0 + F1 x + u

S xx ! xi2  nx 2 ! 1106.56
i

S xy ! xi y i  nx y ! 41112.65

F1 !

S xy S xx

! 37.15

F 0 ! y  F 1 x ! 2627.82
The least-square fit:

y ! 2627.82  37.15 x
10

You might also like