Unit 13
Unit 13
Taylor Brown
Fall 2020
1 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
2 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Last Unit
1 ARMA forecasting.
2 Prediction error.
3 Prediction interval.
3 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
This Unit
4 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Motivation
5 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
6 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Method of Moments
7 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
AR Estimation
φ(B)(xt − µ) = wt ,
φ(B) = 1 − φ1 B − · · · − φp B p .
8 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
AR Estimation
E [xt ] = µ can always be estimated with the first sample moment x̄.
9 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
10 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
11 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Γ p φ = γp σw2 = γ(0) − φ0 γp
yields
φ̂ = Γ̂−1
p γ̂p
and
12 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
1 1
Γp φ = γp σw2 = γ(0) − φ0 γp
γ(0) γ(0)
gives us
and
p
→ σw2 .
σ̂w2 −
14 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
σ 2 −1
Var (φ̂) = Γ
n p
σ2
= R −1 (6)
nγ̂(0) p
15 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Simulation Example
xt = 1.5xt−1 − 0.75xt−2 + wt
where σw2 = 1. For the sample, γ̂(0) = 7.69697, ρ̂(1) = 0.8456375,
and ρ̂(2) = 0.5054795.
16 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Simulation Example
The data had ρ̂(1) = .849, ρ̂(2) = .519 and γ̂(0) = 8.903
φ̂ = R̂p−1 ρ̂p
−1
1 .849 .849
=
.849 1 .519
1.463
=
−.723
Also,
h i
σ̂w2 = γ̂(0) 1 − ρ̂0p R̂p−1 ρ̂p
h i
= γ̂(0) 1 − ρ̂0p φ̂
1.463
= 8.903 ∗ (1 − .849 .519 ) = 1.187
−.723
17 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
In Unit 11, we looked at the ACF and PACF of the time series
from “recruit.dat”, which contains data on fish population in the
central Pacific Ocean. The numbers represent the number of new
fish for each month in the years 1950-1987.
18 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
20 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Time 21 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
22 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
θ
ρ(1) = .
1 + θ2
Using method of moments, we equate ρ̂(1) to ρ(1) and solve a
quadratic equation in θ.
23 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
24 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
25 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
26 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
xt = µ + φ(xt−1 − µ) + wt , (7)
27 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
28 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
29 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Likelihood Function
30 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Likelihood Function
and
n [x − µ − φ(x 2o
1 t t−1 − µ)]
fxt |xt−1 (xt |xt−1 ) = p exp − .
2πσw2 2σw2
31 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Likelihood Function
We have
L(µ, φ, σw2 ) = fx1 (x1 ) × fx2 |x1 (x2 |x1 ) × · · · × fxn |xn−1 (xn |xn−1 )
32 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Likelihood Function
where
n
X
2 2
S(µ, φ) = (1 − φ )(x1 − µ) [xt − µ − φ(xt−1 − µ)]2 .
t=2
34 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
35 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
The variance estimator can be obtained after you get the other
estimators:
d 2 d n 2 1 2 S(µ, φ)
L(µ, φ, σw ) = − log(2πσw ) + log(1 − φ ) −
dσ 2 dσ 2 2 2 2σw2
2
n 1
= − 2 + S(µ, φ)
2σw σw2
Setting that equal to 0, replacing σw2 with σ̂w2 , and solving for σ̂w2
gives us
S(µ, φ)
σ̂w2 =
n
36 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
37 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
38 / 39
Method of Moments Estimation Maximum Likelihood Estimation Comparison of MOM and MLE
Properties of ML Estimators
39 / 39