关键词 > PSTAT174/274
PSTAT 174/274: Homework # 3
发布时间:2023-02-13
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
PSTAT 174/274: Homework # 3 (week 4 & 5).
1. (both 174 & 274 attempt)
A random walk is expressed as X1 = Z1, Xt = Xt − 1 + Zt, t = 2, 3, . . . , where Zt ∼ WN (µZ , σZ(2)), that is, E (Zt) = µZ , Var(Zt) = σZ(2), and Cov (Zt, Zs) = 0 for t s. Determine which statements are true with respect to a random walk model; show calculations and provide complete explanations.
i If µZ 0, then the random walk is nonstationary in the mean.
(Hint: Nonstationary in the mean means that the mean changes with time .)
ii If σZ(2) = 0, then the random walk is nonstationary in the variance.
(Hint: Nonstationary in the variance means that the variance changes with time.) iii If σZ(2) > 0, then the random walk is nonstationary in the variance.
2. (both 174 & 274 attempt) Calculation of sample acf.
You are given the following quarterly rainfall totals over a two-year span:
Quarter |
Rainfall |
2016 q1 2016 q2 2016 q3 2016 q4 2017 q1 2017 q2 2017 q3 2017 q4 |
25 19 10 32 26 38 22 20 |
Question: Calculate the sample lag 1,2,3 and 4 autocorrelations denoted by 1 ,
2 ,
3 ,
4 .
3. (both 174 & 274 attempt) Gaussian White Noise and its square .
Let {Zt} be a Gaussian white noise, that is, a sequence of i.i.d. normal r.v.s each with mean zero and variance 1. Let Yt = Zt(2) . Questions:
i Using R generate 350 observations of the Gaussian white noise Z . Plot the series and its acf. ii Using R, plot 350 observations of the series Y = Zt(2) . Plot its acf.
iii Analyze graphs from (i) and ii).
– Can you see a difference between the plots of graphs of time series Z and Y? From the graphs, would you conclude that both series are stationary (or not)?
– Is there a noticeable difference in the plots of acf functions ρZ and ρY ? Would you describe Y as a non-Gaussian white noise sequence based on your plots?
Provide full analysis of your conclusions.
iv Calculate the second-order moments of Y: µY (t) = E (Yt), σY(2)(t) = Var (Yt), and
ρY (t, t + h) = Cor (Yt, Yt+h). Do your calculations support your observations in (iii)?
4. (both 174 & 274 attempt)
This question explores time series decomposition in R. You will learn about X11 and SEATS: For over three decades X11 has been the standard approach used to seasonally adjust time series at the Bureau of the Labor Statistics (BLS). There is a nice guide briefly you can review from the Australian Beauro of Statistics (ABS) that gives a simple overview (see Time Series AnalysisS easonalAdjustmentMethods.pdf )
• NOTE: we will discuss this further in Module Part IV so for now we just look at the R implementa- tions.
Familiarise yourself with the decomposition tool:
• http://www.seasonal.website/
• https://rdrr.io/cran/seasonal/src/R/seasonal-package.R
• http://www.seasonal.website/seasonal.html
There is an R example to assist you that I have provided as a markdown
• R Example Data Input Output Prep Week 1 and 2.Rmd
Use this as a guide to help you do the following:
• Explain the difference between an additive and a product time series decomposition method.
• First create an R script (function) that will read in the file ECONOMICS USIRYY, 1M.csv and then convert the first column to a valid time format given by yyy-mm-dd and keep only the open values
- output the new tibble into a csv file titled YSIRYoYformatted.csv.
• upload data set which is the USA inflation rate Year-over-Year (YoY) monthly from 1914 to present that you created called YSIRYoYformatted.csv to the seasonal website.
• decompose the time series contained using the X11 command and discuss the outputs obtained - it will help to review the section https://otexts.com/fpp2/x11.html and to use the R commands provided below
• Decompose the time series using the SEATS package, again example commands below. Discuss your findings.
YourDataFrame %>% seas(x11="") -> fit
autoplot(fit)
YourDataFrame %>% seas() %>%
autoplot()
5. (both 174 & 274 attempt)
You are provided data since 1914 for US 10Y Treasury prices - Open High Low and Close as well as traded volume on a monthly sampling time. Write an R function that will do the following steps:
• Read in the csv file provided TVC US10Y,1M.csv to a tibble format
• Convert the first column of times in ISO format to a relevant mm/yyyy format
• Create a ts() object based on the ISO time with monthly frequency
• Explore the time series structure with relevant time series plots (see file PlotsExamples.Rmd for examples)
• Explore the difference and twice differenced time series - plot three subplots: first with Yt vs t, second subplot with ∇Yt vs t and third subplot with ∇2 Yt vs t, where Yt is the monthly open price
• Perform two different time series decomposition’s on the monthly open price time series: an ad- ditive Seasonal - Trend - Residual decomposition and a multiplicative Seasonal - Trend - Residual decomposition. Plot the results of these decompositions and comment on what you find.
• Construct a quarter year forecast - based on examples provided in (Simple-Forecast-Functions-in- R.Rmd) and plot this result.