[R-sig-eco] Limits of the Moran correlogram?

[Alexandre Fadigas de Souza]

Dear friends,

   I am using the function correlog in the ncf package to generate univariate correlograms of abiotic variables in my study area (nutrients, topographic variables, canopy openness).

   The resulting correlation values, however, frequently exceed 1.0. I am intrigued by that, since Moran's autocorrelation values vary between -1.0 and 1.0. Am I setting something wrong?

   Here is my command line:

moranslope = correlog(Long, Lat, Slope, increment = 100, latlon = F, resamp = 50)

   I set latlon = F despite my x and y values are Latitude and Longitude in UTM, because when I set latlon = T values in the x axis become quite larger than the ones that make sense to my dataset (up to ca 4000 m).

   Thank you in advance for any help,

   Alexandre

Dr. Alexandre F. Souza 
Professor Adjunto II, Departamento de Ecologia  Universidade Federal do Rio Grande do Norte (UFRN)
Caixa Postal 1524, Campus Universitario Lagoa Nova
CEP 59078-970 http://www.docente.ufrn.br/alexsouza  Curriculo: lattes.cnpq.br/7844758818522706