What this calculator does
A moving average is a filter. It replaces each observation with the mean of a fixed number of recent observations, which removes the up-and-down noise and makes the underlying direction easier to see. A short window follows the data closely but stays noisy; a long window is smoother but lags further behind a turning point. The choice of window is therefore a trade-off between responsiveness and stability, not a matter of one correct setting. This calculator produces the full simple moving average series, reports the latest value and the change from the previous one, and adds an exponential average, which weights recent observations more heavily. It also reports the simple average of all values, the minimum and maximum, and the number of observations, so the smoothed figure can be read in context rather than on its own.
How to use it
- Paste the values in order, separated by commas, spaces, or semicolons.
- Choose a window size; a common starting point is three to five periods.
- Check that the number of observations is at least the window size.
- Read the latest average and the change from the previous average.
- Compare the trend with the raw latest value; they can disagree.
- Try a different window to see how sensitive the conclusion is.
How it works
Example calculations
Example 1: A three-period average on a short series
The series 10, 12, 11, 15, 14, 16, 18 has 7 observations and produces 5 averages: 11.00, 12.67, 13.33, 15.00, 16.00. The latest is 16.00, up 1.00 from the previous average, so the trend is rising. The exponential average is 16.38.
Example 2: A five-period window
A longer window smooths more and produces fewer averages: 12.40, 13.60, 14.80. The latest is 14.80 against a previous 13.60, still rising, and the exponential average is 15.24. The overall mean of all 7 values is 13.71.
Example 3: A two-period window
A two-period average tracks the data almost exactly: 11.00, 11.50, 13.00, 14.50, 15.00, 17.00. The latest is 17.00, and each average responds fully to the newest value. That responsiveness is useful for detecting a turn, but it also passes most of the noise through, which is the opposite of what a long window does.
What the result means
The moving average answers a simple question: what does the recent level look like if the noise is removed? It does not forecast. A rising average means the recent level is above the earlier level; it says nothing about the next value. The window length is the main decision. A short window is good for spotting a change quickly but can be fooled by a single outlier; a long window is stable but slow. The exponential average is a different compromise, because it never fully drops an old observation but gives it less weight over time. Compare the two: when they agree, the trend is robust; when they diverge, the choice of method is doing some of the work.
Common mistakes
- Using a window longer than the number of observations.
- Changing the window between comparisons and treating the results as equivalent.
- Reading a moving average as a forecast rather than a smoothed description.
- Forgetting that the first n − 1 positions have no average.
- Comparing averages computed on different series lengths.
- Ignoring a single large outlier that dominates a short window.
Assumptions and limits
- The observations are in chronological order.
- The series is numeric and evenly spaced in time.
- The window is fixed for the whole calculation.
- Missing values are not present; every position has a number.
- The simple average weights every observation in the window equally.
- The exponential average uses the standard α = 2 ÷ (n + 1).
Frequently asked questions
What is a moving average?
A moving average replaces each value with the mean of it and the previous values in a fixed window. It smooths short-term noise so the underlying level or trend is easier to see.
How do I choose the window size?
Short windows respond quickly but are noisy; long windows are smooth but lag. Start with three to five periods for a short series, and test a longer window to see whether the conclusion survives the smoothing.
What is the difference between simple and exponential?
A simple moving average weights every observation in the window equally. An exponential average gives more weight to recent values and never fully drops older ones, so it reacts faster to a change.
Why are there fewer averages than observations?
The first average needs a full window, so the first n − 1 positions have no value. A series of ${number(ma.count, 0)} observations with a window of ${number(ma.window, 0)} produces ${number(ma.averages.length, 0)} averages.
Can a moving average predict the next value?
No. It describes the recent level, not the future. Forecasting requires a model of the underlying process, and a moving average is only one input to that model.
Does the order of the numbers matter?
Yes. The series is treated as a time sequence, so reordering the values changes every average. Enter the observations in the order they occurred.
Sources
2026 update
How to use the professional output
This page is not just a formula box. The result is designed to be checked, compared, and taken away.
- Professional worksheet. The result includes the inputs used, the method and scope, and a one-variable sensitivity check for finance calculators.
- A/B scenarios. Save two input sets in the browser and compare the primary, secondary, and breakdown figures side by side.
- Print / PDF and CSV. Print a branded worksheet, or export the year-by-year table when the calculator produces one.
The formulas and assumptions above still govern the number. The worksheet makes the estimate auditable; it does not make it a lender quote, tax return, or personalized advice.