To make realistic and accurate sales forecasts, managers can use several quantitative methods of sales forecasting:
1. Statistical techniques. There are several statistical techniques that can be used to analyze the past sales data:
1. AVERAGE. Shows the center point of the data:
a. Arithmetic mean – Average value
b. Median – Middle value
2. FREQUENCY. Shows how often the data occurred:
a. Mode – Most frequent value
b. Frequency data – Most frequent average value
c. Grouped frequency data – Frequency of values within different groups
3. DISPERSION. Shows how widely the data are spread:
a. Range – Difference between highest and lowest values
b. Quartiles – Distribution of all values into 4 equal groups
c. Inter-quartile range – Range of the central 50% of the dataset
4. DEVIATION. Shows distance of the data from the center point (mean):
a. Variance – Spread of data from the mean
b. Standard deviation – Average difference between data and the mean
c. Mean deviation – Average of differences between data and the mean
5. CHANGE. Shows how the data changed over time.
a. Index numbers – Changes in values
b. Weighted index – Changes in values of unequal importance
2. Simple linear regression. There are several statistical tools that can be used to analyze the relationship between two variables:
- Correlation. This shows that there is a relationship between two different variables in the data set.
- Scatter Diagrams. This shows on the chart all the correlations between two different variables in the data set.
- Line of Best Fit. This shows the straight regression line going through the middle of all points (correlations) on the scatter diagram.
3. Time-series analysis. There are several statistical techniques that can be used to identify the trend from past sales figures:
- Trend Extrapolation. This extends the trend of past sales data into the future to predicted future sales based on historical results.
- Fluctuations. These show variations from the trend that occur over time:
- Seasonal
- Cyclical
- Random
- Moving Averages. These smooth out variations in the data set that are caused by fluctuations to establish underlying trends:
- Three-Point Moving Average
- Four-Point Moving Average
- Trend forecasting using moving averages
The previous article was concerned with using qualitative methods of sales forecasting. Check it out as well!