Subscribe Bookmark RSS Feed

Variability Gauge - Gauge Studies - Linearity: How to understand the t-test prob>|t|?

gucafg0

Community Member

Joined:

Oct 23, 2015

How can i say if a gauge is linear or not, by the result prob>|t|? I have the results, of prob>|t|, 0,2757 for the intercept, and 0,2639 for the slope.

Does it mean i can accept H0=0 ? How can i interpret these results? I am confused about what it means.

2 REPLIES
tonya_mauldin0

Joined:

Jan 21, 2015

Ideally, you want to find a slope of zero. If the slope is significantly different from zero, you can conclude that there is a significant relationship between the size of the part or variable measured as a standard and the ability to measure.  The null hypothesis is that the slope is 0.  Your p-value is a good deal higher than 0.05 so you fail to reject the null hypothesis that the slope is 0.

The test for the intercept is useful only if the test on the slope fails to reject the hypothesis of slope = 0.  You failed to reject the hypothesis so you are interested in this test.  The test for the intercept is a test of bias.  Again, your p-value is a good deal higher than 0.05 so you also fail to reject the null hypothesis that the intercept (bias) is 0.

There is a JMPer Cable article about this that you may find useful.  http://www.jmp.com/content/dam/jmp/documents/en/newsletters/jmper-cable/26_winter_2010.pdf

"Instrument Measurement Linearity".

Peter_Bartell

Joined:

Jun 5, 2014

gucafg0: Just to reinforce tonya.mauldin0's phraseology regarding 'failure to reject the null hypothesis', you should NEVER 'accept' a null hypothesis using any inferential tests. All you can do with any inferential test is reject or fail to reject the null hypothesis. Failure to reject is not synonymous with acceptance...morally or statistically.