[ncl-talk] What is the method used in "dim_spi_n" function to estimate three gamma parameters of the Pearson type III distribution

[Kritanai Torsri]

Dear All,

I used the "dim_spi_n" function with the Pearson type III to compute SPI.

Am I correct that, by default, the NCL function still used the Maximum 
likelihood to estimate

the location, scale, and shape of the gamma distribution as in 
two-parameter gamma distribution or it uses another method?

If any one know, please give me suggestion and thanks in advance.

BRGs,

Kritanai Torsri

Assistant Researcher

Hydro and Agro Infomatics Institute, Bangkok, Thailand.