Example 13.3 Quarterly Sales at Intel Regression-Based Trend Models.

Slides:



Advertisements
Similar presentations
Example 16.7b Estimating Seasonality with Regression.
Advertisements

Example 2.2 Estimating the Relationship between Price and Demand.
Exercise 7.5 (p. 343) Consider the hotel occupancy data in Table 6.4 of Chapter 6 (p. 297)
Estimating Total Cost for A Single Product
Example 16.1 Forecasting Sales at Best Chips. Thomson/South-Western 2007 © South-Western/Cengage Learning © 2009Practical Management Science, Revised.
Forecasting Models With Linear Trend. Linear Trend Model If a modeled is hypothesized that has only linear trend and random effects, it will be of the.
Applied Econometrics Second edition
Guide to Using Excel 2007 For Basic Statistical Applications To Accompany Business Statistics: A Decision Making Approach, 8th Ed. Chapter 16: Analyzing.
1 Chapter 7 My interest is in the future because I am going to spend the rest of my life there.— Charles F. Kettering Forecasting.
Chapter 11: Forecasting Models
Guide to Using Excel For Basic Statistical Applications To Accompany Business Statistics: A Decision Making Approach, 5th Ed. Chapter 15: Analyzing and.
CHAPTER 5 TIME SERIES AND THEIR COMPONENTS (Page 165)
LINEAR REGRESSION MODEL
Exponential Smoothing Methods
1 Spreadsheet Modeling & Decision Analysis: A Practical Introduction to Management Science, 3e by Cliff Ragsdale.
Prediction and model selection
Example 7.1 Pricing Models | 7.3 | 7.4 | 7.5 | 7.6 | 7.7 | 7.8 | 7.9 | 7.10 | Background Information n The Madison.
Statistical Forecasting Models
| 13.1a | 13.2a | 13.2b | 13.3 | 13.3a | 13.4 | 13.3b | 13.5 | a13.2a13.2b a b Dummy Variables n Some potential.
September 2005Created by Polly Stuart1 Analysis of Time Series Data For AS90641 Part 1 Basics for Beginners.
Naive Extrapolation1. In this part of the course, we want to begin to explicitly model changes that depend not only on changes in a sample or sampling.
Example 16.3 Estimating Total Cost for Several Products.
§ 9.6 Exponential Growth and Decay; Modeling Data.
Time Series and Forecasting
Example 13.1 Forecasting Monthly Stereo Sales Testing for Randomness.
Example 11.4 Demand and Cost for Electricity Modeling Possibilities.
Time-Series Analysis and Forecasting – Part V To read at home.
Linear Trend Lines Y t = b 0 + b 1 X t Where Y t is the dependent variable being forecasted X t is the independent variable being used to explain Y. In.
1 1 Slide © 2012 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole.
Example 5.8 Non-logistics Network Models | 5.2 | 5.3 | 5.4 | 5.5 | 5.6 | 5.7 | 5.9 | 5.10 | 5.10a a Background Information.
1 1 Slide © 2004 Thomson/South-Western Slides Prepared by JOHN S. LOUCKS St. Edward’s University Slides Prepared by JOHN S. LOUCKS St. Edward’s University.
1 Spreadsheet Modeling & Decision Analysis: A Practical Introduction to Management Science, 3e by Cliff Ragsdale.
Chapter © 2015 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or.
Holt’s exponential smoothing
© 2013 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license.
Example 16.6 Forecasting Hardware Sales at Lee’s.
Example 16.7 Forecasting Quarterly Sales at a Pharmaceutical Company.
© 2000 Prentice-Hall, Inc. Chap The Least Squares Linear Trend Model Year Coded X Sales
Example 3.4 Interpretation of the Standard Deviation: Rules of Thumb.
Chapter 6 Business and Economic Forecasting Root-mean-squared Forecast Error zUsed to determine how reliable a forecasting technique is. zE = (Y i -
Time series Decomposition Farideh Dehkordi-Vakil.
Example 13.6a Houses Sold in the Midwest Exponential Smoothing.
1 1 Slide © 2011 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole.
Trend Projection Model b0b0 b1b1 YiYi
Example 2.9 Time Series Plots | 2.2 | 2.3 | 2.4 | 2.5 | 2.6 | 2.7 | 2.8 | 2.10 | 2.11 | TOYS.XLS n Lists.
Example 13.6 Houses Sold in the Midwest Moving Averages.
Ch.5 Financial Forecasting Goals: 1) Develop pro forma financial statements 2) Learn a Trend Analysis 3) Learn a Regression Analysis 4) Calculate Systematic.
Example 13.2 Quarterly Sales of Johnson & Johnson Regression-Based Trend Models.
Example 16.6 Regression-Based Trend Models | 16.1a | 16.2 | 16.3 | 16.4 | 16.5 | 16.2a | 16.7 | 16.7a | 16.7b16.1a a16.7.
Example 16.5 Regression-Based Trend Models | 16.1a | 16.2 | 16.3 | 16.4 | 16.6 | 16.2a | 16.7 | 16.7a | 16.7b16.1a a16.7.
Do Now (3x + y) – (2x + y) 4(2x + 3y) – (8x – y)
©2003 Thomson/South-Western 1 Chapter 17 – Quantitative Business Forecasting Slides prepared by Jeff Heyl, Lincoln University ©2003 South-Western/Thomson.
Example x y We wish to check for a non zero correlation.
Copyright © Cengage Learning. All rights reserved. 3 Exponential and Logarithmic Functions.
Selecting Appropriate Projections Input and Output Evaluation.
MBF1413 | Quantitative Methods Prepared by Dr Khairul Anuar 8: Time Series Analysis & Forecasting – Part 1
Example 16.2a Moving Averages | 16.1a | 16.2 | 16.3 | 16.4 | 16.5 | 16.6 | 16.7 | 16.7a | 16.7b16.1a a16.7b DOW.XLS.
©The McGraw-Hill Companies, Inc. 2008McGraw-Hill/Irwin Time Series and Forecasting Chapter 16.
Chapter 4 More on Two-Variable Data. Four Corners Play a game of four corners, selecting the corner each time by rolling a die Collect the data in a table.
Forecasting. Model with indicator variables The choice of a forecasting technique depends on the components identified in the time series. The techniques.
3-1Forecasting Weighted Moving Average Formula w t = weight given to time period “t” occurrence (weights must add to one) The formula for the moving average.
TIME SERIES MODELS. Definitions Forecast is a prediction of future events used for planning process. Time Series is the repeated observations of demand.
Example 16.7a Deseasonalizing: The Ratio-to-Moving-Averages Method.
Chapter 4 Basic Estimation Techniques
FW364 Ecological Problem Solving Class 6: Population Growth
Correlation and Simple Linear Regression
Multiple Regression.
MBF1413 | Quantitative Methods Prepared by Dr Khairul Anuar
Coefficient of Determination
Chap 4: Exponential Smoothing
Presentation transcript:

Example 13.3 Quarterly Sales at Intel Regression-Based Trend Models

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Objective To estimate Intel’s exponential growth and to see whether it has been maintained during the entire period from 1986 until early 2001.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b INTEL.XLS n This file contains quarterly sales data for the chip manufacturing firm Intel from the first quarter of 1986 through the first quarter of n Each sales value is expressed in millions of dollars. n Are Intel’s sales growing exponentially through this entire period?

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Solution n We will first estimate and interpret an exponential trend for the years Then we will see how well the projection of this trend into the future fits the data after n The time series plot through 1996 appears on the next slide. n We have used Excel’s Chart/Add Trendline menu item, with the Exponential option, to superimpose an exponential tend line on this plot.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Time Series Plot of Sales with Exponential Trend Superimposed

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Solution -- continued n The fit is evidently quite good. n Equivalently, the next slide illustrates the time sereis of log sales for this same period, with the linear trend line superimposed. n It fit is equally good.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Time Series Plot of Log Sales with Linear Trend Superimposed

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Solution -- continued n We can also use StatPro’s regression procedure to estimate this exponential trend as shown on the next slide. n We first add a time variable in column C and make a logarithmic transformation of Sales in column D. n Then we regress Log(Sales) on Time to obtain the regression output. n Note that the two coefficients in cells H18 and H19 are the same as those shown for the linear trend on the previous slide.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Regression Output for Estimating Exponential Trend

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b What does it all mean? n The estimated equation is Forecasted Sales = e t n The most important constant in this equation is the regression coefficient of Time, b= Expressed as a percentage, this coefficient implies that Intel’s sales were increasing by approximately 6.64% per quarter throughout this 11 year period. n To use this equation for forecasting into the future, we start with the final observation, 6440 in quarter 4 of 1996, and multiply by for as many quarters as we are forecasting ahead.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Forecasts n Has this exponential growth continued beyond 1996 at Intel? n As you might have guessed, it has not, due to slumping sales in the computer industry and increase competition from other chip manufacturers. n We checked this by creating the Forecast column in the table on the next slide. n This implements are estimate of the equation.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Creating Forecasts of Sales

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Forecasts -- continued n We then use StatPro’s time series plot procedure to plot the two series Sales and Forecast, shown on the next slide. n It is clear that sales in the forecast period remained rather constant – nowhere near the 6.64% growth they exhibited in the estimation period. n As Intel clearly realizes, nothing that good lasts forever.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Time Series Plot of Forecasts Superimposed on Sales

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Standard Error of Estimate n The standard error of estimate is found in cell I9 in the Forecast of Sales table shown earlier. n This value, , is in log units, not original dollar units. n Therefore, it is a totally misleading indicator of the forecast errors we might make from the exponential trend equation. n To obtain more meaningful measures, we first obtain the forecasts of sales. Then we easily obtain any of the three forecast error measures discussed earlier. n The results appear on the next slide.

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Measures of Forecast Errors

| 13.1a | 13.2 | 13.4 | 13.5 | 13.6 | 13.6a | 13.6b | 13.7 | 13.7a | 13.7b13.1a a13.6b a13.7b Calculations n The squared errors, absolute errors, and absolute percentage errors are first calculated with the formulas =(B4-E4)^2, =ABS(B4-E4), and =G4/B4 in cells F4, G4, and H4, which are then copied down. n The error measures then appear in cells L24, L25, and L26. n The corresponding formulas for RMSE, MAE, and MAPE are straightforward. n Forecasts for the 11-year estimate period were off, on average, by about 7.5%.