Chapter 52- Quantitative Sales Forecasting

Question 1

Centring

Answer 1

A method used in the calculation of a moving average where the average is plotted or calculated in relation to the central figure

Question 2

Moving average

Answer 2

A succession of averages derived from successive segments (typically of constant size and overlapping) of a series of values

Question 3

Time series analysis

Answer 3

A method that allows a business to predict future levels from past figures

Question 4

Time series data

Answer 4

• 4 main components that a business wants to identify in time series data
• Trend
• Seasonal fluctuations
• Cyclical fluctuations
• Random fluctuations

Question 5

Calculating moving averages

Answer 5

Depends on what year moving average you are doing, for this example its 3 year moving average.
•Add first 3 years
125+130+130=385

•Divide by number of years
385/3= 128.3

•Proceed by moving one up the scale
(130+130+150)/3= 136.7

•Do this till the end
This can then be plotted on a scatter graph, and the data will show you what the trends have been.

Question 6

Variations from trend equation

Answer 6

Variations from trend = actual sales – trend

Question 7

Limitations of quantitative sales

Answer 7

Quantitative sales forecasts are a powerful tool for businesses and used to inform key decisions. The fact that they are often produced using advanced computer models and algorithms, does not mean they are infallible.

• The forecast is for a short period of time in the future, such as six months, rather than a long time, such as five years
• They are revised frequently to take account of new data and other information
• The market is slow changing
• Those preparing the forecast have a good understanding of how to use data to produce a forecast.

No forecaster is accurate all the time – even in slow-moving markets, sales can change by a few percent for no apparent reason – one way to take this into account is to produce a forecast range.

Question 8

Correlation formula-

Answer 8

When looking at a graph, if there appears to be a correlation – the extent of this relationship can be calculated using the correlation formula

• A correlation of +1 means that there is an absolute positive relationship between the two variables
• A correlation coefficient of 0 means that there is no relationship between the variables
• A correlation of -1 means that there is an absolute negative relationship between the two variables

Question 9

Necessity to be careful when making decisions based on such calculations

Answer 9

However, businesses must be careful when basing decisions on such calculations 1. A large quantity of sales in any period may be due to factors other than advertising, such as other forms of promotion 2. There are sometimes examples of nonsense calculations – these are correlation coefficient that appear to show strong relationships between the two variables, when in fact these relationships are pure coincidence