Advice on use of Line fit statistic Pr and ChiSqr
Wed, 10/19/2022 - 09:54 am
I have experimental data - measured frequncy (in Hz) v time. The time data have variations due to logging jitter. The data would be expected to be linear over a portion of the measurement. There are between 5 and 50 pairs to which I apply the line option in programmed CurveFit. I use the slope to derive a further parameter. Ideally I would like a number that told me how much I can depend on the paramater based on the line fit. At some stage I will need a look-up table for probabilities for V_chisq or V_Pr. Which is the right statistic to use?