Post-Training Analysis (postreg)

Question

Ong Teng 2014 年 3 月 5 日

コメント済み: Chenguang Zhang 2019 年 3 月 7 日

Hi,

Good Day!

May I know hows the calculation of the code below:

[m,b,r] = postreg(evu(r,:),ev);

I am now have a data set with 90(sample)x14(dimensions), can I know the calculation to get the value of m, b and r?

Thanks.

Answer 1

Chenguang Zhang 2019 年 3 月 5 日

m表示实际值和预测值的拟合系数，越靠近1，表明二者越接近。

b表示实际值和预测值的拟合截距，越靠近0 ，表明效果越好。

r表示实际值和预测值的相关系数。

John D'Errico 2019 年 3 月 5 日

With no disrespect intended, I've attached the efforts of Google Translate to help others who might read this answer:

m represents the fit coefficient of the actual value and the predicted value, and the closer to 1, the closer the two are.

b represents the fit intercept of the actual value and the predicted value. The closer to 0, the better the effect.

r represents the correlation coefficient between the actual value and the predicted value.

Chenguang Zhang 2019 年 3 月 7 日

Thank you.