Table 3.

Statistical analysis (ANOVA) of the central composite design, including response terms for building the predictive models and optimal response values for the parametric response criteria.

		UAE Extraction						MAE Extraction
		Res1U	Res2U	Res3U	Res4U	Res5U	Res6U	Res1M	Res2M	Res3M	Res4M	Res5M	Res6M
Intercept	b0	138.65	6.26	0.43	67.40	3.15	45.16	−37.68	5.74	0.03	61.48	9.38	65.60
Linear	b1	8.21	−0.23	0.12	2.21	−0.04	0.02	23.64	0.50	0.16	2.66	−0.42	* −2.814
	b2	* −2.278	* −0.085	* −0.009	* −0.304	<0.01	−0.04	1.98	−0.11	−0.02	* −0.720	−0.05	0.21
	b3	* 0.501	* 0.017	* 0.006	* 0.067	* −0.008	* −0.069	* 1.514	0.03	0.01	−0.01	−0.01	* −0.542
	b4	5.60	0.32	* 0.049	−0.19	0.01	0.06	* 1.739	−0.02	0.01	0.19	−0.11	* −0.515
Quadratic	b11	−8.47	0.01	0.03	−0.76	<0.001	−0.27	−0.88	−0.01	<0.001	−0.07	<0.001	0.08
	b22	0.01	<0.001	<0.001	<0.001	<0.001	<0.001	* −0.064	<0.001	<0.001	<0.001	<0.001	<0.001
	b33	* −0.021	<0.001	<0.001	<0.001	<0.001	*0.001	<0.001	<0.001	<0.001	<0.001	<0.001	* 0.003
	b44	−0.08	<0.001	<0.001	<0.001	<0.001	<0.001	−0.01	<0.001	<0.001	<0.001	* 0.001	* 0.003
Interaction	b12	0.76	<0.001	−0.01	0.09	<0.001	0.02	−0.06	0.01	<0.001	−0.03	<0.001	−0.01
	b13	−0.09	−0.02	<0.001	−0.08	<0.001	<0.001	−0.08	* −0.005	<0.001	0.02	<0.001	0.02
	b14	0.27	0.08	0.01	0.16	−0.01	<0.001	−0.09	<0.001	<0.001	−0.01	0.01	0.02
	b23	0.03	* 0.003	* <0.001	0.01	<0.001	<0.001	0.01	<0.001	<0.001	<0.001	<0.001	<0.001
	b24	−0.09	−0.01	* −0.001	−0.02	<0.001	<0.001	0.02	<0.001	<0.001	0.01	<0.001	<0.001
	b34	0.01	<0.001	<0.01	0.01	<0.001	<0.001	* −0.021	<0.001	<0.001	<0.001	<0.001	* 0.003
Statistical information of the fitting analysis
Observations		31	31	31	31	31	31	31	31	31	31	31	31
R2		77.76	70.70	75.51	71.03	60.11	93.41	89.13	53.65	54.06	59.93	65.68	80.34
R2adj		58.31	45.07	54.08	45.68	25.21	87.64	79.61	13.09	13.86	24.87	35.66	63.15
MSE		18.65	0.99	0.16	2.99	0.23	0.85	13.99	0.58	0.13	8.54	0.52	2.65
RMSE		4.32	0.99	0.40	1.73	0.48	0.92	3.74	0.76	0.36	2.92	0.72	1.63
MAPE		10.42	0.55	0.09	1.45	0.13	0.46	8.29	0.34	0.08	4.72	0.27	1.43
DW		2.19	1.76	1.78	* 1.01	1.48	1.62	1.94	1.70	1.53	2.05	2.19	1.68
Factorial Optimization Response
		max	max	max	max	min	max	max	max	max	max	min	max
Optimum value		227.6	17.8	3.1	73.1	2.3	87.1	144.6	8.6	1.5	84.0	1.8	73.7
x1		1.2	2.5	2.5	2.5	2.2	2.1	8.8	2.5	12.5	11.9	12.5	12.4
x2		5.0	5.0	5.0	5.3	5.0	44.3	20.3	34.0	5.0	5.0	44.3	16.2
x3		17.7	0.1	0.0	30.2	0.0	56.3	54.8	100.0	25.1	46.8	0.0	100.0
x4		33.9	34.1	33.8	34.7	35.0	5.0	25.0	103.6	25.0	25.0	25.0	105.0
General Optimization
		max	max	max	max	min	max	max	max	max	max	min	max
Optimum response		201.6	13.9	2.4	71.8	2.9	85.7	132.9	8.0	1.5	79.1	3.6	78.7
Deseability		0.985						0.871
Optimum value				x1 = 2.5	x2 = 5	x3 = 34.6	x4 = 30.0		x1 = 12.4	x2 = 5.0	x3 = 0.0	x4 = 36.6

Numbers in linear quadratic and interaction marked with (*) means statistically significant based on F and p-values cited in the correspondent subsections. Terms included: R2: regression coefficients; R2adj: adjusted regression coefficients; MSE: Minimum Square Error; RMSE Root Minimum Square Error; MAPE: Mean Absolute Percentage Error. DW: Durbin–Watson statistic. Responses are summarized as Res1: Total betacyanins (mg/g). Res2: Total phenolic acids (mg/g). Res3: Total flavonoids (mg/g). Res4: Extractable solid (mg/g). Res5: Antioxidant activity (mg/mL). Res6: Color (a* coordinates). Fixed variables are summarized as x₁ = time (min); x₂ = ratio (g/L); x₃ = methanol concentration (%); x₄ = temperature (°C).