{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# KKMM - The additive method in c has the lower SSE so...

This preview shows pages 1–2. Sign up to view the full content.

3. Quarterly data on electricity consumption are given below as a time series. The value for x was obtained using SOLVER to make the sum of the seasonal index numbers equal to 4. a) Use the method (KMacK) discussed in class to derive a multiplicative model from the additive model using indicator variables for the quarters. x 85.3 912 2 Intercept 91.5 X Variable 1 4.93 75 X Variable 2 3.14 583 3 X Variable 3 - 13.4 583 X Variable 4 - 14.3 958 rhohat1 1.08 407 3 rhohat2 0.93 61 rhohat3 0.93 091 5 rhohat4 1.04 891 3 4 b) Use the model to predict the next four quarters. c) Predict the next four quarters using the additive model using indicator variables for the quarters. d) Decide which model is better, using the SSE criterion for quarters 13 to 16.

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: The additive method in c) has the lower SSE, so appears to be preferable. e) Does your decision in d) match what you might have suspected by looking at the graph of the first 12 values of the time series? The seasonal variations to not get wider as time passes, so the additive model is expected to do beter. DATA AND PRELIMINARY COMPUTATIONS FROM EXCEL t q1 q2 q3 elec 1 1 99 2 1 88 3 1 93 4 111 5 1 120 6 1 108 7 1 111 8 130 9 1 139 x 1 1 127 85.3912 2 1 1 1 131 1 2 152 1 3 1 160 1 4 1 148 1 5 1 150 1 6 170...
View Full Document

{[ snackBarMessage ]}

### Page1 / 2

KKMM - The additive method in c has the lower SSE so...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online