Skip to main content

Table 2 Fitting criteria of the ZIP and ZINB models with the training dataset

From: Using a zero-inflated model to assess gene flow risk and coexistence of Brassica napus L. and Brassica rapa L. on a field scale in Taiwan

Dispersal kernel functionZIP modelZINB model
RMSEAdj. R2AICBICRMSEAdj. R2AICBIC
Log-sech0.010480.00286− 16,963− 16,9540.008230.38911− 17,859− 17,852
Exponential power0.01049− 0.001− 16,956− 16,9470.008230.38925− 17,859− 17,852
Power law0.010440.01014− 16,976− 16,9670.008260.38495− 17,846− 17,839
Logistic0.010430.01097− 16,978− 16,9690.008260.38517− 17,847− 17,840
2Dt0.010430.01097− 16,978− 16,9690.008240.38769− 17,855− 17,847
Gamma0.01,064− 0.0292− 16904− 16,8950.008230.38884− 17,858− 17,851
WALD0.010440.00994− 16,976− 16,9670.008250.38542− 17,848− 17,841
Weibull0.010430.01064− 16,977− 16,9680.008230.38947− 17,860− 17,853
Neg. Exponential0.010440.00989− 16,977− 16,9660.008280.38183− 17,838− 17,829
Log-normal0.01,0440.00954− 16,975− 16,9660.008240.38717− 17,853− 17,846
Gaussian0.010440.00971− 16,977− 16,9650.008260.38444− 17,846− 17,837
  1. RMSE: root mean square error; adj. R2: adjusted coefficient of determination; AIC: Akaike’s information criterion; BIC: Schwarz’s Bayesian information criterion; MSPR: mean squared prediction error