What does it mean if my result is off the known value by one Sigma?

  • Context: Undergrad 
  • Thread starter Thread starter content404
  • Start date Start date
  • Tags Tags
    Mean Sigma Value
Click For Summary

Discussion Overview

The discussion revolves around interpreting the significance of a measurement result that deviates from a known value by one sigma (σ) in the context of error analysis and experimental uncertainty. Participants explore the implications of this deviation, particularly in relation to the probability of future measurements falling within a certain range of the true value.

Discussion Character

  • Exploratory
  • Technical explanation
  • Conceptual clarification
  • Debate/contested

Main Points Raised

  • One participant notes their result is off from the known value by 1.43 σ and questions the meaning of the associated probability of ~85% in terms of future experiments.
  • Another participant explains that if experiments are repeated with perfect uncertainty analysis and uncorrelated deviations, 85% of those results should be closer to the true value, assuming a Gaussian error distribution.
  • It is suggested that the approximation holds under the assumption that the width of the Gaussian distribution does not change significantly with slight deviations in the measured value.
  • A participant emphasizes that in real experiments, one cannot assume knowledge of the exact value and must estimate uncertainty based on measurements, which complicates the analysis.
  • There is a clarification that the known value is treated as the true value for the purpose of statistical analysis, and that the 85% probability is contingent on this assumption and a proper understanding of uncertainties.
  • One participant shares their context of conducting the Franck Hertz experiment with older equipment, highlighting issues of high precision but low accuracy.
  • Another participant warns that one cannot disregard the known value when considering it as the true value, as even if it is accurate, there will still be a 15% chance of obtaining measurements deviating by at least that much in the long run.

Areas of Agreement / Disagreement

Participants express varying levels of understanding regarding the implications of the statistical analysis, with some agreeing on the interpretation of the 85% probability while others raise questions about the assumptions involved. The discussion remains unresolved regarding the broader implications of using the known value as the true value in experimental contexts.

Contextual Notes

Participants acknowledge limitations in their assumptions about the Gaussian distribution of errors and the dependency on the known value being treated as the true value. There is also mention of the potential impact of measurement uncertainties on the analysis.

content404
Messages
3
Reaction score
0
I'm putting together a lab report and my result is off from the known value by 1.43 σ. According to the error function tables provided by my prof, and using the error function in my error analysis textbook, that gives me a probability of ~85%.

I don't understand what this means though. Will a repeat experiment have an 85% chance of being within my standard of deviation or was there only a 15% chance that my result would be off by this much? The discrepancy between the known value and my experimental value is less than my total uncertainty so I think my result is reasonable.
 
Physics news on Phys.org


If you repeat the experiment with perfect uncertainty analysis over and over again and have uncorrelated deviations, 85% of those experiments should be closer to the "true" value.
Note that this is an approximation for a gaussian error where the width does not change significantly if your measured value changes a bit. If that is not true, you need something like the Feldman-Cousins method to get a similar number.
 


Ok, I can see how that makes sense but I don't understand why it works like that.
 


Let's assume we know the exact value and all sources of error in the measurement (which can depend on that exact value), so we can predict how the measurements will be distributed. In addition, let's assume a gaussian distribution of those errors. If you get one measurement 1.43σ away from this exact value, you know that just 15% of all measurements will get a larger deviation (this is just a result of the gaussian distribution).

In a real experiment, you cannot use your knowledge of the exact value - you have to estimate the uncertainty based on your measurement. In many studies, this does not matter, and you can work like you had the situation described above: A gaussian distribution around the exact value, with the uncertainty of your measurement.
 


mfb said:
In a real experiment, you cannot use your knowledge of the exact value - you have to estimate the uncertainty based on your measurement. In many studies, this does not matter, and you can work like you had the situation described above: A gaussian distribution around the exact value, with the uncertainty of your measurement.

Perhaps to clarify: in the OP situation the described "known" value is assumed to be the true value (forming the so-called null hypothesis), and this number of 85% is cooked up using that assumption, and -as mfb says- the assumption that you understand your uncertainties.
 


Ok I get it now, thank you both.

If you're curious, I was conducting a repeat of the Franck Hertz experiment with 30 year old equipment. High precision, low accuracy.
 


This really means that you cannot throw away your "known" value if you are interested in using it as the "true" value, at usual 1% or 5% levels. Because, even if the "known" is exactly the "true" value, then in the long run of your experiment you will get 15% values off by at least that much.
 

Similar threads

  • · Replies 21 ·
Replies
21
Views
3K
  • · Replies 18 ·
Replies
18
Views
3K
  • · Replies 3 ·
Replies
3
Views
5K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 8 ·
Replies
8
Views
3K
  • · Replies 9 ·
Replies
9
Views
3K
  • · Replies 0 ·
Replies
0
Views
3K
  • · Replies 0 ·
Replies
0
Views
4K
  • · Replies 7 ·
Replies
7
Views
5K
  • · Replies 5 ·
Replies
5
Views
3K