0

I am undertaking spatial autocorrelation (Global Moran's I) in ArcMap 10.3. The p value returned is 0, does this just mean its extremely significant or is this an incorrect result?HTML report

  • If it really is a p value of zero, or close to, then the map of the quantity you are computing Moran's I for should look very smooth. Does it? Does p < 0.0001 look feasible? How many decimal places does ArcMap's Moran statistic get displayed to? Using R, not ArcMap, I can get p-value = 6.398e-11 which is as near to zero as makes no odds, so maybe ArcMap is rounding? Show some maps and the output from the Moran function. What's your neighbourhood structure? So many questions... – Spacedman Apr 7 '17 at 7:35
  • I guess it must be rounding. The dataset it storm genesis locations for the western North Pacific and I was undertaking autocorrelation based on MEI values. Output attached to questions -hopefully that will answer your many questions? – rb1234 Apr 7 '17 at 9:15
1

A z-score of 15 gives a p-value (using R) of:

> pnorm(15, lower.tail=FALSE)
[1] 3.670966e-51

Yes, 0.00000000000000000000000000000000000000000000000000367

Assuming you haven't done anything wrong, like feeding it the wrong attribute value or constructing a silly adjacency matrix, I'd say that was significant. Note that Moran's I will usually be significant if there's a large-scale trend in the data, so make sure you plot the map and eyeball anything like that first, then detrend it and look for residual spatial correlation with your Moran I then.

I'd also only ever say p < 0.01 in this sort of case.

Also, I assume that diagram of a Normal distribution is just illustrative. Your data is FIFTEEN standard deviations from the mean. On my screen, that would put it somewhere in the next door office :)

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.