Software Development Effort Estimation Using Regression Fuzzy Models

Table 8

Error measures and meaningfulness tests.

	MAE	MBRE	MIBRE	SA	Δ	ME
	Dataset 1
MLR_out	2745.8	77	220.6	61	0.3	1129.9
Fuzzy Lin_out	1842.6	31.7	39.5	73.8	0.4	1225.1
Fuzzy Const_out	2779.5	244.9	45.1	60.5	0.3	1599
Fuzzy Mam_out	4118	303.2	55	41.5	0.2	−2454
	Dataset 2
MLR_out	1418.6	26.1	19.2	80.9	0.9	−910.2
Fuzzy Lin_out	1342.9	21	16.3	81.9	0.9	−801.6
Fuzzy Const_out	3674.7	85.8	40.2	50.5	0.5	2268.4
Fuzzy Mam_out	3268.8	92.8	37.1	56	0.6	−2219
	Dataset 3
MLR_out	7528.6	4.8	34.1	62.6	0.4	3696.3
Fuzzy Lin_out	7241.4	−96.6	32.3	64	0.4	2796.3
Fuzzy Const_out	8849.9	82.1	32.2	56.1	0.4	7721.8
Fuzzy Mam_out	9332.2	76.6	37.6	53.7	0.4	2868.6
	Dataset 4
MLR_out	5536.3	319.2	49.7	49.6	0.3	285.5
Fuzzy Lin_out	4925.3	176.1	60.9	55.1	0.3	−58.9
Fuzzy Const_out	6646.9	413.5	57.2	39.4	0.2	1141.4
Fuzzy Mam_out	7265.7	334.9	55.2	33.8	0.2	−1759