forecasting_lecture_08

forecasting_lecture_08 - Lecture Notes 8 1 Trend...

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

View Full Document Right Arrow Icon
1 Lecture Notes 8 1. Trend Forecasting (or Trend Extrapolation) 1. Polynomials t t u t t Y 2 32 2 1 Y t is the series you want to forecast t is the trend variable Start t =1 u t is the noise term Note – then you use adjusted R 2 , AIC, or SIC to choose the best model. Never use R 2 , because it will choose the largest model with the most k’s 2. Exponential Growth     t t u t Y exp exp 2 1 Or taking the natural logarithm, then   t t u t Y 2 1 ln 2 is the rate of growth 3. Moving Average   t M t t t t e Y Y Y M Y 1 1 1 1
Background image of page 1

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

View Full Document Right Arrow Icon
2 e t is not a residual. It the error in the forecast calculated by t t t M Y e M t is the predicted value There is no error once you start forecasting There is no estimation. You are smoothing out the data and then carrying the average forward. 4. Exponential smoothing
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.

{[ snackBarMessage ]}

Page1 / 4

forecasting_lecture_08 - Lecture Notes 8 1 Trend...

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