Week 6 Lecture 3 Forecasting

Question 1

Under what circumstances can linear regression be used?

Answer 1

When the data is linear and constant

Question 2

As opposed to the weight given to Moving Averages, the weight given in Exponential smoothing…

Answer 2

Changes and is determined by Alpha

Question 3

Under what circumstances should ‘Single Exponential Smoothing’ be used?

Answer 3

When the data is non-trended and non-seasonal

Question 4

The alpha used in Exponential Smooting is…

Answer 4

Not calculated. It is an estimate set beforehand.

Question 5

Between what values should Alpha lie?

Answer 5

Between 0 and 1

Question 6

What is the formula used in Single Exponential Smoothing for the calculation of St?

Answer 6

Alpha x Yt + (1-Alpha) x St-1

Question 7

Under single exponential smoothing, the forecast for year 2 is always the (………) of year one?

Answer 7

Sales/Data point

Question 8

In relation to significance, a lower alpha…

Answer 8

Gives more significance to older data.

Question 9

In relation to significance, a higher alpha gives…

Answer 9

Less significance to old data

Question 10

A smaller alpha results in what sort of time-series graph line? And why is this the case?

Answer 10

A smoother line.

This is the case because the graph takes longer to react to changes i the data

Question 11

What is the key consideration when setting the alpha?

Answer 11

Is the old data significant? If it is we choose a lower alpha, if it is not, we choose a higher alpha.

Question 12

In single exponential smoothing, a line on a graph representing the quick recognition of changes in data points is likely to be more…

Answer 12

Erratic

Question 13

Although it is not possible in practise, an alpha of 0 would result in what? And why is this the case?

Answer 13

A straight line along the point of the first data entry.

This is because it gives absolute significance to the old data.

Question 14

What is the idea range for an alpha to lie?

Answer 14

Between 0.1 and. 0.3

Question 15

What is the Alpha also known as?

Answer 15

The smoothing constant

Question 16

Under single exponential smoothing, the weight of all data points ad up to what value?

Answer 16

1

Question 17

Under what circumstances is Holts method used?

Answer 17

When there is a trend in the data.

Question 18

Under Holts method, 2 equations are needed, what are they?

Answer 18

St = Alpha(Y1) + (1-Alpha) (St-1+Bt-1)

Bt = Beta(St - St-1) + (1-Beta)bt-1

Question 19

In the Holt model, what does Beta represent?

Answer 19

The smoothing level of the estimated trend.

Question 20

Beta is either given or is calculated how?

Answer 20

By taking an estimate from the first 3 data points.

For example: (3rd point - 1st point)/2

Question 21

When making forecasts using the Holts method, how are they calculated?

Answer 21

The St of the last period + the Bt of the last period.

Question 22

Between what values can Beta be?

Answer 22

0 and 1