Time-Series Forecasting
Learning Objectives 1.Describe What Forecasting Is 2. Forecasting Methods 3.Explain Time Series & Components 4.Smooth a Data Series 5.Forecast Using Smoothing Methods, & Trend 6.Use MAD to Measure Forecast Error
What Is Forecasting? 1.Process of Predicting a Future Event 2.Underlying Basis of All Business Planning Production Inventory Personnel Facilities Sales will be $200 Million!
Forecasting Methods 1.Qualitative Methods Expert Opinion Delphi Method Surveys 2.Quantitative Methods Time Series Causal Regression
Quantitative Forecasting Steps 1.Select Several Forecasting Methods 2.‘Forecast’ the Past 3.Evaluate Forecasts 4.Select Best Method 5.Forecast the Future 6.Monitor Continuously Forecast Accuracy
What’s a Time Series? 1.Set of Numerical Data 2.Obtained by Observing Response Variable at Regular Time Periods 3.Assumes that Factors Influencing Past & Present Will Continue 4.Example Year: Sales:
Time Series Components Trend Seasonal Cyclical Irregular
Trend Component 1. Persistent, Overall Upward or Downward Pattern 2. Due to Population, Technology, etc to 20 Years Duration Mo., Qtr., Yr. Response
Linear Increasing Trend Linear Decreasing Trend Nonlinear TrendNo Trend Examples of Some Time Series Trend Patterns
Toaster Sales in Hundreds, By Quarter, TIME QUARTER1 QUARTER2 QUARTER3 QUARTER
Long-Term Trend in Toaster Sales
Cyclical Component 1. Repeating Up & Down Movements 2. Due to Interactions of Factors Influencing Economy 3. Usually 2-15 Years Duration Mo., Qtr., Yr. Response Cycle Prosperity Recession Depression Recovery
Cycles in Toaster Sales
Seasonal Component 1. Regular Pattern of Up & Down Fluctuations 2. Due to Weather, Customs,etc. 3. Occurs Within 1 Year Mo., Qtr. Response Summer
The Seasonal Pattern of Toaster Sales
Irregular Component l 1.Erratic, Unsystematic, ‘Residual’ Fluctuations l 2.Due to Random Variation or Unforeseen Events n Union Strike n Tornado l 3.Short Duration & Nonrepeating
Irregular Fluctuations in Toaster Sales Quarters
Multiplicative Time-Series Model l 1.Any Observed Value in a Time Series Is the Product of Time Series Components l 2.If Annual Data n Y = T x C x I l 3.If Quarterly or Monthly Data n Y i = T x S x C x I
Time Series Forecasting Linear Time Series Forecasting Trend? Smoothing Methods Trend Models YesNo Exponential Smoothing QuadraticExponential Holt- Winters Auto- Regressive Moving Average
Moving Average Method 1.Series of Arithmetic Means 2.Used Only for Smoothing Provides Overall Impression of Data Over Time 3.Equation L = Averaging Period (Odd # Years) MA (L) Y L i it (L-1)/2 T=(1-L)/2
Time Response Y i Moving Total ( L =3) Moving Avg ( L =3) 19914NA = 1515/3 = = 1414/3 = = 1515/3 = = 1616/3 = NA Moving Average Calculation
Moving Average Graph Year Sales
Moving Average with Even Number of Periods
Time Series Forecasting Linear Time Series Forecasting Trend? Smoothing Methods Trend Models YesNo Exponential Smoothing QuadraticExponential Holt- Winters Auto- Regressive Moving Average
Exponential Smoothing Method l 1.Form of Weighted Moving Average n Weights Decline Exponentially n Most Recent Data Weighted Most l 2.Used for Smoothing & Forecasting n Assumes No Trend l 3.Requires Smoothing Coefficient (W) n Subjectively Chosen n Ranges from 0 to 1
Exponential Smoothing Equations l 1.Smoothing Equations E i = W·Y i + (1 - W)·E i-1 l 2.Forecasting Equation Y i+1 = E i E i = Smoothed Value Y i = Actual Value W = Smoothing Coefficient
Time Y i Smoothed Value, E i ( W =.2) Forecast Y i NA 19926(.2)(6) + (1-.2)(4.0) = (.2)(5) + (1-.2)(4.4) = (.2)(3) + (1-.2)(4.5) = (.2)(7) + (1-.2)(4.2) = NA 4.8 Exponential Smoothing Calculation ^ E i = W·Y i + (1 - W)·E i-1
Exponential Smoothing Graph Year Sales
Exponential Smoothing Thinking Challenge l You’re an economist for GM. You want to get a feel for the long-term trend in car sales. You want to smooth cyclical & random fluctuations using exponential smoothing with W =.25. Yearly sales (million units) are 2, 4, 1, 3.
To obtain starting values: 1.E 1 = Y 1 = 2 l 2.E 2 = W·Y 2 + (1 - W)·E 1 = (.25)(4) + ( )(2) = 2.5 l 3.E 3 = W·Y 3 + (1 - W)·E 2 = (.25)(1) + ( )(2.5) = l 4.E 4 = W·Y 4 + (1 - W)·E 3 l = (.25)(3)+( )(2.125)=2.34 Exponential Smoothing Solution*
Selecting Smoothing Coefficient (W) l 1.Subjectively Chosen n Computer Search Routines Available l 2.To Smooth Cyclical & Irregular, Small W n Reveals Long-Term Pattern l 3.To Forecast, Large W n Forecast Will Reflect Prior Period Data Most l 4.Recent Data Weighted Most for All W