Chapter_6 - Stat 373 Ch 6 1 Chapter 6 Forecasting The prediction of future event and conditions(forecasting is very important in many organizations

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Stat 373 – Ch. 6 - 1 Chapter 6 Forecasting The prediction of future event and conditions (forecasting) is very important in many organizations since predictions are often incorporated into the decision making process. For example governments predict tax revenues and expenses for budgeting school boards predict the number of school age children living in each school district in the future in order to decide whether a new school should be build Forecasting is important in many aspects of business such as marketing – forecast demand finance – forecast income/expenditures personnel – forecast number of workers needed production – forecast demand We can divide forecasting methods into two general categories: qualitative and quantitative. With qualitative methods, we use the opinion of experts. Qualitative methods may be useful if there is no good historical data or if the historical pattern is expected to change. One technique for combining expert opinion is the Delphi method ( http://www.iit.edu/~it/delphi.html ). A big problem with quantitative methods is the assessment of prediction error. We do not discuss these methods further in the course. With quantitative methods to make predictions (or forecasts), we analyze past data in order to identify a pattern and then assume the observed pattern will continue into the future. Note that there is no way to assess this assumption. We call a chronological sequence of observations on a particular variate a time series . Much business data are collected as time series, e.g. sales per week, inventory per month, number of employees per year, etc. A time series is best viewed in a time series plot, a run chart of the variate versus time. See Figures 1-3. We can think of a time series as consisting of several components: trend, cycle, seasonal variation and irregular variation. Trend – upward or downward movement, e.g. inflation, growth, changes in taste Cycle – recurring up and down movements around trend levels, e.g. business cycle of growth and recessions, changes in weather or fashion Seasonal Variation – periodic patterns that complete themselves within a calendar year and then repeat on a yearly basis – a special case of a cyclic component Irregular variation – erratic movements that follow no apparent pattern, or at least is unexplained by the other components We give some examples of time series plots in Figures 1 to 3 where different components dominate. The data come from the Times Series Data Library Adapted from Stat 372 Course Notes © R.J. MacKay and S. Steiner, University of Waterloo, 2006
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Stat 373 – Ch. 6 - 2 http://www-personal.buseco.monash.edu.au/~hyndman/TSDL/ 90 80 70 60 50 40 30 20 200 100 house sales Index Figure 1: Monthly sales of new one-family houses sold in the USA since 1973 40000 30000 20000 10000 160 140 120 100 80 60 40 20 wine sales Index Figure 2: Total wine sales by Australian wine makers in bottles Jan 1980 - Aug 1994 500 400 300 200 100 0 100 80 60 40 20 Armed Robberies Index Figure 3: Monthly Boston armed robberies Jan. 1966 - Oct. 1975 Adapted from
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 05/03/2011 for the course ECON 202 taught by Professor Na during the Spring '11 term at University of Toronto- Toronto.

Page1 / 26

Chapter_6 - Stat 373 Ch 6 1 Chapter 6 Forecasting The prediction of future event and conditions(forecasting is very important in many organizations

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online