Thread: Pearson's Correlation _ with individual X error and Y error

1. Pearson's Correlation _ with individual X error and Y error

Hi all,
I have a problem that I can't seem to solve. I don't know how to account for the individual measurement error in a Pearson's correlation r calculation.

I am comparing two measured data sets X vs. z and Y vs. z with each other, and each individual pairs (x and y) have their own associated error. [where, standard error = standard deviation / sqrt(n)] The x measurements each had an n=5, the y measurements had an n=3. see table and plots below.

z X x std. err Y y std. err

25 0.72855767 0.027897003 1.646892253 0.142322358
75 0.626295068 0.032373739 1.050750426 0.086402134
125 0.503723473 0.040064737 0.821319298 0.054630245
175 0.350974088 0.048911432 0.72469168 0.054934699
225 0.235663134 0.054151294 0.492331475 0.047449739
275 0.153881708 0.041717934 0.326720574 0.026730325
325 0.091734879 0.026676582 0.223300186 0.01824026
375 0.052049261 0.022624755 0.18872933 0.016929851
425 0.065249763 0.028233725 0.169369199 0.016954082
475 0.087642862 0.038713734 0.167518079 0.021577553

from this data you get:

I can easily calculate the r value for the average X and Y (n=10) but I would like to also report, either the error in r due to the error in individual x and y error, or an adjusted r value that already takes this variation into account.

Any help is much appreciated.
Thank you.

2. Re: Pearson's Correlation _ with individual X error and Y error

Thanks.

 Tweet

Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts