Application of Multiple Unsupervised Models to Validate Clusters Robustness in Characterizing Smallholder Dairy Farmers

Table 10

Proportion of variance accounted for by cluster of production in Ethiopia.

	Fitted model	Total Variance	Residual variance	-2log likelihood	P value	Variance accounted for by cluster
K-means		Milk yield
	Model with cluster	1.015	0.239	1867.4	<0.00001	73%
	Model without cluster		0.977	3718.4
		Milk sales
	Model with cluster	0.988	0.222	1770.1	<0.00001	54%
	Model without cluster		0.76	3388.6
SOM		Milk yield
	Model with cluster	1.015	0.283	2091.8	<0.00001	68%
	Model without cluster		0.977	3718.4
		Milk sales
	Model with cluster	0.988	0.258	1969.8	<0.00001	51%
	Model without cluster		0.76	3388.6
Fuzzy		Milk yield
	Model with cluster	1.015	0.074	337	<0.00001	89%
	Model without cluster		0.977	3718.4
		Milk sales
	Model with cluster	0.988	0.073	319.4	<0.00001	70%
	Model without cluster		0.76	3388.6

Data scaled to have unit variance and mean of zero.