Chronology Current Month Current Thread Current Date
[Year List] [Month List (current year)] [Date Index] [Thread Index] [Thread Prev] [Thread Next] [Date Prev] [Date Next]

Re: uncertainty



Good question.

I am assuming that the uncertainties in x and y are independent and random.

See for example, An Introduction to error analysis by J.R. Taylor.


At 09:24 3/5/98 -0800, Timothy Usher wrote:
[Tim Sullivan]
What exactly do you want the program to calculate? Just standard
deviation of
the mean or errors in linear fit parameters?

None of the above. I want it to carry through error propagation
calculations. Simple example: If length = 3.0 +/- 0.2 m and width = 5.0
+/- 0.2 m then area = 15 +/- 1 m^2


This is a most interesting proposition.
One could easily assume that if the error limits of one dimension are
2.8 and 3.2 m and the limits of the other are 4.8 and 5.2 m
Then their product might be bounded by 2.8 x 4.8 = 13.4 m^2
and 3.2 x 5.2 = 16.6 m^2
So one might be tempted to express this as 15 +/- 1.6 m^2

I would very much like to hear the methods actually taught, and the
distributions which underlie these methods.

Whatcott Altus OK