Table 6

K

total number of datasets, k = 1.. K

I

number of rows (objects)

J _k

number of columns (variables) for matrix k

J

total number of variables (∑₁ ^K J _k )

c _c

number of components for common part

c _k

number of components for distinctive part of matrix k

c _t

total number of components ((∑ _{k  = 1} ^K c _k ) + c _c )

X _k

data matrix (I × J _k )

X

concatenated data matrix [X _k | … |X _K ](I × J)

C _k

common part of matrix k (I × J _k )

C

concatenated common parts [C _k | … |C _K ](I × J)

D _k

distinctive part of matrix k (I × J _k )

D

concatenated distinctive parts [D _k | … |D _K ] (I × J)

E _k

the residual error of matrix k (I × J _k )

E

concatenated residual errors [E _k | … |E _K ] (I × J)

T _sca

scores of SCA model (corresponds to objects) (I × J _t )

P _sca

loadings of SCA model (corresponds to variables) (J × c _t )

P*

rotation target loading in DISCO model (J × c _t )

B

rotation matrix in DISCO (c _t  × c _t )

W

weight matrix (used in DISCO) to penalize rotation matrix (J × c _t )

T _c

common scores (SCA and JIVE) (I × c _c )

P _c

common loadings (JIVE) (I × c _c )

${\mathbf{T}}_{c_k}$

common scores (O2-PLS) for matrix k (I × c _c )

${\mathbf{P}}_{c_k}$

common loadings for matrix k (J _k  × c _c )

${\mathbf{T}}_{d_k}$

distinctive scores for matrix k (I × c _k )

${\mathbf{P}}_{d_k}$

distinctive loadings for matrix k (J _k  × c _k )

∘

Hadamard (element-wise) matrix product