Post Your Answer

Is it appropriate if the gamma distribution function is not utilized in the SPI?

3 years ago in Experimental Research By Paula

Data analysis

During my experimentation, the precipitation data exactly corresponds with the Bell curve or Normal Distribution. I doubt that it is inappropriate if the gamma distribution function is not utilized in the SPI. I need to know whether it is appropriate if the gamma distribution function is not used in the SPI index?

All Answers (3 Answers In All)

By Lalit Mudra Answered 3 years ago

Hi Paul, Suppose your precipitation data match specific characteristics of the Bell curve. In that case, you don’t have to worry about the SPI index.

Firstly, the values obtained should identify the positive or negative values - Continuous probability distribution. Secondly - symmetrical distribution. And finally, the symmetrical values obtained will not be expected all the time; If the values are extreme values, then heavy-tailed distribution should be used to evaluate

By Jennifer Answered 3 years ago

Suppose you are not satisfied with the gamma distribution function. In that case, you can apply various probability distribution models that fit your requirements, including chi-square distribution, Poisson distribution, and Binomial distribution for asymmetric values.

Best Regards,
Tim

By Anu Answered 3 years ago

If you are confused with the distribution functions you use, I have attached a reference that uses alternative distribution functions for the SPI index. I hope this will help you to find out what you are looking for. https://www.researchgate.net/publication/257197372_Computation_of_Drought_Index_SPI

All the Best

View Related Questions