Numerical Smoothing of Time Series Data

Instructor: Michael Eckert

Michael has a Bachelor's in Environmental Chemistry and Integrative Science. He has extensive experience in working with college academic support services as an instructor of mathematics, physics, chemistry and biology.

We can use numerical and/or graphical smoothing of time series plots to see overall trends, where we may not be able to see trends otherwise. We implement averaging or a process of moving means to smooth a time plot.

Smoothing a Time Plot -Movement of a Nanoparticle Through an Electric Field

Say that a nanoparticle, for instance, an isotope of silver is exposed to an ever-fluctuating electric field over the course of 15 seconds, so that the nanoparticle moves up and down vertically through 1 micrometer. If we are given a table of the nanoparticle's vertical height given in increments of one 10th of a micrometer through 15 seconds, how might we smooth the table's time plot using a 3-mean smooth or a 5-mean smooth?

Before we can perform this smoothing of the time plot representing vertical movement of the nanoparticle, let's look at the table of data giving its position through time.

Table of Nanoparticle Height vs. Time

If we were to plot this data, we have a graph that looks like the following, where our x-axis represents time in seconds and our y-axis is representative of the nanoparticle's position through 1 micrometer -numbered in 1/10ths of a micrometer.

Time Plot of Nanoparticle Height vs. Time

3-Mean and 5-Mean Time Plot Smoothing

Notice how the time plot above, representing the nanoparticle's vertical movement through an electric field, yields sharp peak and valleys. It may be hard to spot any overall trends in this time plot or, perhaps, we might want to extrapolate more information from this time plot of this given data series. In either case, the process of smoothing this time plot can expose overall trends or trends through smaller intervals.

3-Mean Smoothing

Let's look at the table below, showing the operations for numerical smoothing of position versus time. In the case of the 3-mean smoothing operation in column 3, we merely take the average (or mean) of every group of 3 measurements for height or vertical distance from column 2.

Table 3 and 5-Mean Smoothed Height vs. Time

As seen in the 3 -mean column below, our 1st mean value is (0 + 2 + 1) / 3 = 1 and our 2nd is (2 + 1 + 4) / 3 = 2.33, etc. We merely continue averaging groups of 3 until we have no more groups of 3 to average. Our original time plot with the 3-mean smoothed time plot in orange (labeled series 1, superimposed) is shown as:

3-Mean Smoothed (Series 1) Time Plot

5-Mean Smoothing

With 5-mean smoothing, we do essentially the same thing as we do with the 3-mean smoothing; however, as opposed to groups of 3, we mean groups of 5. For example, our first mean is (0 + 2 + 1 + 4 + 2) / 5 = 1.8 and our 2nd is (2 + 1 + 4 + 2 + 5) / 5 = 2.8, etc. Superimposing the 5-mean plot (labeled series 2) onto our last plot, we see

To unlock this lesson you must be a Member.
Create your account

Register to view this lesson

Are you a student or a teacher?

Unlock Your Education

See for yourself why 30 million people use

Become a member and start learning now.
Become a Member  Back
What teachers are saying about
Try it risk-free for 30 days

Earning College Credit

Did you know… We have over 200 college courses that prepare you to earn credit by exam that is accepted by over 1,500 colleges and universities. You can test out of the first two years of college and save thousands off your degree. Anyone can earn credit-by-exam regardless of age or education level.

To learn more, visit our Earning Credit Page

Transferring credit to the school of your choice

Not sure what college you want to attend yet? has thousands of articles about every imaginable degree, area of study and career path that can help you find the school that's right for you.

Create an account to start this course today
Try it risk-free for 30 days!
Create an account