a) Sketch two separate time series on two different axes with the following features: i. The first time series should violate only one out of the three requirements for stationarity. ii. The second should violate at least two of the three requirements for stationarity. State each violation mathematically and explain it conceptually. Label your graphs appropriately and explain exactly how these violations are being depicted in your time series plots. b) Can you forecast either of these time series variables using the AR models you studied in this course? Explain in detail how you would do this and outline any limitations or drawbacks of this approach. c) Can you regress one of these time series variables on the other? What kind of results will you get if you do so? Give a well-thought-out answer based on everything you have learnt about this topic in this course.

a) Sketch two separate time series on two different axes with the following features: i. The first time series should violate only one out of the three requirements for stationarity. ii. The second should violate at least two of the three requirements for stationarity. State each violation mathematically and explain it conceptually. Label your graphs appropriately and explain exactly how these violations are being depicted in your time series plots. b) Can you forecast either of these time series variables using the AR models you studied in this course? Explain in detail how you would do this and outline any limitations or drawbacks of this approach. c) Can you regress one of these time series variables on the other? What kind of results will you get if you do so? Give a well-thought-out answer based on everything you have learnt about this topic in this course.

ENGR.ECONOMIC ANALYSIS

14th Edition

ISBN:9780190931919

Author:NEWNAN

Publisher:NEWNAN

Chapter1: Making Economics Decisions

Section: Chapter Questions

Problem 1QTC

See similar textbooks

Similar questions

Only need part B please be clear with all 3 answers to part B. Thanks in advance...
4. Suppose we have a summary of forecasting techniques calculation results for Gundam Auto Sales Inc. (in the prior item) as follows: Mean Next Standard Period Error Forecasting Method Used Forecast (MSE) 1.3-period UnWMA 10.42 3.24 2.4-period UnWMA 10.38 3.51 3.3-period WMA 10.83 3.03 4. Simple Exponential Smoothing 5. Trend Projection 8.24 5.04 11.43 1.16 a. Which among the techniques is the most reliable? b. What does the result of the most reliable technique say?
In the trend model Tt = b0 + b1*Timet, suppose that b1 > 0. Is the series expected to grow or decline in future periods? Does this mean that the series grow or decline with certainty in every period?
1. Suppose you observe (y, x₁,x2,...,k) for N observations. For each observation i, the model is yi Bo + B1x1i + B₂x2i + + BkXki + €į. Write the model out in matrix form. What are the dimensions of Y, X, B, €? =
A materials engineer wants to understand the relationship between the strength of plastic cases and the temperature at which the strength measurements were made. The engineer collects several samples from the manufacturer and records the following observations. Using the data below and what you have learned in Forecasting, determine the following (use four decimal places for values): 1) Which is the response variable? 2) What would be the value of the coefficient of determination between the two variables? 3) What would be the strength of the plastic if the temperature was 210? Sample Temperature Strength 1 185 5150 183 5125 187 5123 188 5140 189 5195 189 5190 192 5150 195 5155 196 5156 198 5162 193 5172 196 5196 200 5063 202 5025 HENDAWNA 10 11 13 14
Use General Linear Proce ss to determine the Emean functon and ARC2) given the autocovariance function of ky XE 七ート 2ヒー2
The following table lists the number of daily visitors to the Web site of a new business during its first year. Month Number Month Number 1 2 3 4 5 6 5,400 5,372 5,265 5,250 5,289 5,350 7 8 9 10 11 12 5,600 5,520 5,280 5,400 5,448 5,500 a. Graph the data with a time-series plot using a vertical scale from 5,000 to 5,700.b. Graph the data with a time-series plot using a vertical scale from 4,000 to 7,000. c. Comment on the difference between these two time-series plots.
A researcher has a sample of 6 annual observations {94, 104, 102, 99, 111 and 107} for the CPI in country Z for the period 2015 to 2020, and wants to forecast CPI for the years 2021, 2022 and 2023. The researcher uses 3 different forecasting models: A, B and C. Model A is an AR(1) model with no drift and with an estimated autoregressive coefficient = 0.7. Model B is a MA(1) model with no constant and with an estimated MA coefficient = -0.4 (note the minus !). Model C is a random walk model with no drift. The error terms over the 2015-2020 period were estimated to have the values: {3, -1, 2, 4, -3, 1}. a. Compute the 2021, 2022 and 2023 forecasted values for the consumer price index based on the three models. Show the formulas and the details of your calculations, and explain all the related symbols. b. Suppose that the actual values of the CPI over the 2021, 2022 and 2023 were {108, 114, 105}. Calculate the Root mean square error of the three model forecasts over the 2021-2023…
Suppose we have the following time series data on variable Y (where t = trend): Y 100 2 120 3 160 200 Using simple exponential smoothing where x = 0.5, calculate the forecast of Y when t = 5. Report your answer to only one decimal point.
Question 22 A computer depreciates 32% per year. A computer is bought for $1200. What is an equation to model this where V is the value of the computer and t is the years that passs since it is bought. Ov= 1200(-0.32)t OV= 1200(0.32) OV = 1200(1.32) OV = 1200(0.68) Question 23 A computer depreciates 32% per year. A computer is bought for $1200. What is an equation for the year since the comupter is bought as a function of the computer's worth? Ot=10g0.68 (1200)
Q. 1B. Clearly explain in détail why logarthmic and dummy variables are regularly used in Time series Econometrics ?
Consider the OLS estimator 3;. Under the Gauss-Markov assumptions, O the estimator is the best linear unbiased estimator. O the estimator is asymptotically normally distributed. O the estimator has the properties stated in the other three possible answers. O the estimator is consistent.