AMS316
Tianhe Pan
Report for Fitting a Time Series Model
1.
Introduction
I have always fond of Teslas gorgeous electric cars. So, I choose to
analysis the stock price of Tesla Motors, Inc. (TSLA) without any
hesitation after Professor Zhu assigned this ho
AMS 316
Introduction to Time Series Analysis
Review for Midterm
Additional Questions
& Answers
1
Problem 1A
X t - 0.5 X t - 1 =Z t
2
Problem 1A, Solutions
X t X t - h =f1 X t - 1 X t - h +Z t X t - h
Now taking expectations throughout produces
g (h) =f1g(
1. For the MA(1) process X t Zt 0.5Zt 1
1)
Determine whether this process is invertible
X t (1 0.5B) Zt
1 0.5B 0
B 2, B 1
So this process is invertible
2)
If invertible, please write this process as AR() process
X t ( 1 0 .B Zt )
5
Zt
1
Xt
1 0.5B
Zt [1 0
1. According to the joint distribution of X and Y, We can get the joint distribution of X-Y and X+Y.
Assume U=X-Y, V=X+Y. P(U) and P(V) are the marginal distributions.
U
-2a
-a
0
a
2a
P(V)
-2a
0
0
0
0
0
0
-a
0
1/4
0
1/4
0
1/2
0
0
0
0
0
0
0
a
0
1/4
0
1/4
0
AMS316 Homework 2
2.1
The following data show the coded sales of company X in successive 4-week periods over
1995-1998.
1995
1996
1997
1998
I
153
133
145
111
II
189
177
200
170
III
221
241
187
243
IV
215
228
201
178
V
302
283
292
248
VI
223
255
220
202
VI
AMS316 Homework #1
This problem set is used as a self-test of your background on AMS311 and AMS315, it
doesnt represent the format or level of homework in AMS316. The grade of homework 1
will be not counted for nal grade.
1. Let the random variable X and
AMS 582, FALL 2013
Computer Project
Each group will select a corresponding member, who is authorized to request data (which
generates a data charge for the group). Each group has a unique model, and there are a
number of classes of models. Each groups rep
AMS 582, Fall 2013
Obtaining Statistical Computing Resources
Statistical Programming Languages
A number of computer programs specialize in performing statistical computations: SAS,
R, SPSS, and Minitab among others. Since the SAS program is currently the
EXPECTED MEAN SQUARES AND MIXED MODEL ANALYSES
Fixed vs. Random Effects
The choice of labeling a factor as a fixed or random effect will affect how you will
make the F-test.
This will become more important later in the course when we discuss interactions.
Thailand Statistician
January 2012; 10(1) : 121-128
http:/statassoc.or.th
Contributed paper
Expected Mean Squares for the Random Effects One-Way
ANOVA Model when Sampling from a Finite Population
Teerawat Simmachan [a] John J. Borkowski [b] and Kamon Buds
DATA & DECISION (2009) - Understanding the Analysis of Variance II
Daniel J. Denis, Ph.D., University of Montana.
These notes have been adapted from Hays, W. L. (1994). Statistics. Wadsworth: CA. All other contributions,
including explanations and comment
AMS 582
Fall, 2013
Chapter 14: Nested and Split-Plot Designs
14.1. Two Stage Nested Design
These designs are called hierarchical. Montgomerys example problem is three suppliers
provide four batches of raw material. Three measurements are taken on each bat
AMS 582
Fall 2013
Chapter 8: Two-Level Fractional Factorial Designs
There are three key ideas: the assumption of sparsity of effects; higher order fractional
replicates can be reduced to more complete lower order designs; we can group fractions
to assembl
l . A research team sought to specify a tnanu factoring process so that Y. the area in a
product affected by surface [laws was as smali as possible. They had three leueLs of
concentration of a clterni al used to wash the product before the ti nai manufact