Women’s weekly earnings. The following graph shows the quarterly median weekly earnings for U.S. women 25 years of age or older (www.bls.gov). Data are provided from the first quarter of 2000 through the fourth quarter of 2007.

Why does the exponential smoother with the higher coefficient fit the series better? What about this series is important for this result? What does this suggest about using exponential smoothers on such time series?

Transcribed Image Text:

660- 640 620 600 Median Weekly Earings 580 560 540- 520 500 Qtr 22001 Qtr 1 2002 Qtr. 3 2000 2002 2004 Qtr 4 2005 Qr 3 2006 Qtr 22007 Quarter Here is single exponential smoothing model to these data using a = 0.2. Median Weekly Eamings 700- 650- 600+ 550+ 500- 3 6 9 12 15 18 21 24 27 30 33 Quarters (Q1 2000=1) Smoothing Constant Variable -Actual Apha 0.2 --Fits -Forecasts -95.0% Pl Accuracy Measures MAPE 3.212 MAD 18.972 MSD 405.401