Skip to main content
. 2023 Sep 14;13:15223. doi: 10.1038/s41598-023-42352-2

Table 1.

Statistics for choosing the best number of classes.

G Loglik Conv npm AIC BIC SABIC Entropy %Class 1 %Class 2 %Class 3 %Class 4 %Class 5 %Class 6
m1 1 − 36,891.10 1 4 73,790.20 73,811.36 73,798.65 1.0000000 100.00000
m2 2 − 35,529.74 1 8 71,075.47 71,117.78 71,092.37 0.8517868 52.52732 47.47268
m3 3 − 35,199.73 1 12 70,423.46 70,486.93 70,448.81 0.8027449 38.31967 37.97814 23.70219
m4 4 − 35,060.42 1 16 70,152.84 70,237.47 70,186.64 0.8299584 33.87978 6.830601 21.37978 37.90984
m5 5 − 34,956.54 1 20 69,953.08 70,058.86 69,995.33 0.7886274 30.05464 24.31694 11.27049 26.775956 7.581967
m6 6 − 34,866.60 1 24 69,781.20 69,908.13 69,831.89 0.7860618 20.08197 1.70765 26.91257 20.765027 21.516393 9.016393

AIC, Akaike information criterion; BIC, Bayesian information criteria; SABIC, sample-adjusted information criteria.