How Many Significant Digits for Mean, Variance, and Standard Deviation?

  • Thread starter Thread starter solarwind
  • Start date Start date
  • Tags Tags
    Significant digits
Click For Summary
For the given dataset, the mean should be reported with three significant digits, reflecting the precision of the measurements. The variance should also maintain three significant digits, as it is derived from the mean's precision. The standard deviation, calculated from the variance, should similarly have three significant digits. When reporting the mass of the sample, "x" should be the mean with three significant digits, while "y" should be the standard deviation, also with three significant digits. The relationship between the standard deviation and the significant digits of the mean is crucial for accurate error analysis.
solarwind
Messages
16
Reaction score
0
Hi all.

Let's say I have a set of data as follows (the mass of a sample of some chemical measured several times):

23.132 g
24.532 g
21.532 g
22.853 g
23.193 g

(I just made that data up, but imagine that a analytical scale put out those numbers, exactly as shown, on its display.)

1. When I calculate the mean, how many significant digits should the mean have?

2. When I calculate the variance, how many significant digits should the variance have?

3. When I calculate the standard deviation (by square rooting the variance), how many digits should it have?

4. When someone asks what is the mass of the sample, I know that I should tell them that the mass is: x g +/- y g. What should "x" be? Should it be the mean? If so, how many significant digits? Also, what should "y" be? I know it should be the standard deviation, but how many significant digits should it be?

5. How does the standard deviation dictate the number of significant digits of "x"?
 
Physics news on Phys.org
The mean has 3 significant digits. The error in Mean^2 is 2* mean * the error in the mean. The variance has the same no. of significant digits as Mean^2.
Perhaps you'd like to look up Error Analysis.
 
The standard _A " operator" maps a Null Hypothesis Ho into a decision set { Do not reject:=1 and reject :=0}. In this sense ( HA)_A , makes no sense. Since H0, HA aren't exhaustive, can we find an alternative operator, _A' , so that ( H_A)_A' makes sense? Isn't Pearson Neyman related to this? Hope I'm making sense. Edit: I was motivated by a superficial similarity of the idea with double transposition of matrices M, with ## (M^{T})^{T}=M##, and just wanted to see if it made sense to talk...

Similar threads

  • · Replies 42 ·
2
Replies
42
Views
5K
  • · Replies 4 ·
Replies
4
Views
3K
  • · Replies 28 ·
Replies
28
Views
3K
  • · Replies 3 ·
Replies
3
Views
3K
  • · Replies 5 ·
Replies
5
Views
3K
  • · Replies 7 ·
Replies
7
Views
3K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 24 ·
Replies
24
Views
6K
  • · Replies 5 ·
Replies
5
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K