I have some (2749) senor output values. They range from 0 to 1769. With google spreadsheet I put it thru some calculations to get the (mean) average and standard deviation. With this I created two colums BINS and NORMDIST to create a chart. Please look at the attached image.

Mean is 53.35. Standard deviation is 61.23

What can I extrapolate from this?

Is one deviation 61.23, two deviation 122,46? Two deviations gives me ~95%. So since my mean is 53, 95% is a range from 0 til 122?

My chart shows while the range is from 0 to 1769, its mean is 53. Is my data bad? The form of the curve the data makes is very "typical" distribution, but a little skewed to the left?


  • $\begingroup$ Your question is better suited for stats.stackexchange.com $\endgroup$ – NoChance Nov 26 '18 at 9:49
  • $\begingroup$ @NoChance Thank you for your suggestion! $\endgroup$ – fUrious Nov 26 '18 at 10:55
  1. I think that you can simply ignore data beyond 3σ (usually you don't need more precise results, because you have 99+% probability that each new result will be in 3σ range from the peak of your distribution).
  2. Then try to repeat your calculations without "unnecessary" data (those that lay beyond 3σ). Maybe it will lead to better result.

Each experiment has its own appropriate precision. Your data can be too precise for one experiment and nearly useless for another; depends only on the kind of experiment.

  • $\begingroup$ 1σ = 61.23? With the first round of standard deviation, you mean that I can go back and redo it and ignoring data greater than 3σ (183)? I would pretty much get the same data (ish) as that way up at 1769 is just a single instance. $\endgroup$ – fUrious Nov 26 '18 at 10:51
  • $\begingroup$ 3σ from the peak, so it's more like 53.35+3*61.23=237. Usually, in order to have a "good" distribution, it's better to exclude those data that are beyond 237 (though you can show a bit of horizontal line, if needed) classifying them as low-probability results. After excluding, you can't anymore use excluded results anyway, so your new standard deviation will depend only on "0-237 data" (better for precision than "0-1769 data"). Probably precision will change insignificantly, as you've said, but it definitely will be better. $\endgroup$ – Kelly Shepphard Nov 26 '18 at 11:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.