Model fitting
The values of responses (yield of flavonoids) at different experimental combinations were given in Table 1. The significance of each coefficient was determined using the p-value (Table 2). The corresponding variables would be more significant if the p-value becomes smaller. It was found that the variables with the largest effect were the linear terms of extraction temperature (x1), ethanol concentration (x4) and the quadratic term of extraction temperature (x21) and extraction time (x22), followed by the quadratic term of ethanol concentration (x24). These results showed that the effect on the yield of total flavonoids was decreased in the following order when MAE was used to extract total flavonoids from
C. paliurus: extraction temperature (p < 0.0001), ethanol concentration (p < 0.0001) and the solid–liquid ratio (p = 0.0585). After analysis, the regression model can be described by the following quadratic polynomial in terms of coded values.