O2PLS分析结果

NULL

O2PLS分析可以分为以下三个步骤： 1 交叉验证 2 拟合模型 3 对模型结果进行可视化

Step1 交叉验证

NULL

*******************
Elapsed time: 6.88 sec
*******
Minimal 5-CV error is at ax=2 ay=2 a=2
*******
Minimum MSE is 160290.7
*******************

Step2 拟合模型

NULL

*** Summary of the O2PLS fit ***

- Call: o2m(X = traScaled, Y = metScaled, n = triple["n"], nx = triple["nx"], ny = triple["ny"])

- Modeled variation
-- Total variation:
in X: 1.839099e+13
in Y: 4.331638e+12

-- Joint, Orthogonal and Noise as proportions:

data X data Y
Joint 0.017 0.199
Orthogonal 0.968 0.799
Noise 0.014 0.002

-- Predictable variation in Y-joint part by X-joint part:
Variation in T*B_T relative to U: 0.438
-- Predictable variation in X-joint part by Y-joint part:
Variation in U*B_U relative to T: 0.49

-- Variances per component:

Comp 1 Comp 2
X joint 245962647172 71263430195
Y joint 848727744970 14916822947

Comp 1 Comp 2
X Orth 414264909498 2.035212e+13

Comp 1 Comp 2
Y Orth 113415318122 2.909037e+12


- Coefficient in 'U = T B_T + H_U' model:
-- Diagonal elements of B_T =
1.322 0.421

Step3 模型结果可视化

NULL

Total Graph  

TRUE