Exponential Smoothing

Results in a smoothed data series

To access this command...

Choose Data - Statistics - Exponential Smoothing

Exponential smoothing is a filtering technique that when applied to a data set, produces smoothed results. It is employed in many domains such as stock market, economics and in sampled measurements.

For more information on exponential smoothing, refer to the corresponding Wikipedia article.

Data

Input Range: The reference of the range of the data to analyze.

Results to: The reference of the top left cell of the range where the results will be displayed.

Grouped By

Select whether the input data has columns or rows layout.

Parameters

Smoothing Factor: A parameter between 0 and 1 that represents the damping factor Alpha in the smoothing equation.

Example

The following table has two time series, one representing an impulse function at time t=0 and the other an impulse function at time t=2.

	A	B
1	1	0
2	0	0
3	0	1
4	0	0
5	0	0
6	0	0
7	0	0
8	0	0
9	0	0
10	0	0
11	0	0
12	0	0
13	0	0

The resulting smoothing is below with smoothing factor as 0.5:

Column 1	Column 2
Alpha
0.5
1	0
1	0
0.5	0
0.25	0.5
0.125	0.25
0.0625	0.125
0.03125	0.0625
0.015625	0.03125
0.0078125	0.015625
0.00390625	0.0078125
0.001953125	0.00390625
0.0009765625	0.001953125
0.0004882813	0.0009765625
0.0002441406	0.0004882813

Sampling

Descriptive Statistics

Analysis of Variance (ANOVA)

Correlation

Covariance

Exponential Smoothing