NAG C Library Function Document

nag_mv_prin_comp (g03aac) performs a principal component analysis on a data matrix; both the principal component loadings and the principal component scores are returned.

2

Specification

#include <nag.h>

#include <nagg03.h>

void	nag_mv_prin_comp (Nag_PrinCompMat pcmatrix, Nag_PrinCompScores scores, Integer n, Integer m, const double x[], Integer tdx, const Integer isx[], double s[], const double wt[], Integer nvar, double e[], Integer tde, double p[], Integer tdp, double v[], Integer tdv, NagError *fail)

3

Description

Let

X

be an

n

p

data matrix of

n

observations on

p

variables

x_{1}, x_{2}, \dots, x_{p}

and let the

p

p

variance-covariance matrix of

x_{1}, x_{2}, \dots, x_{p}

S

. A vector

a_{1}

of length

p

is found such that:

a_{1}^{T} {S a}_{1}

is maximized subject to

a_{1}^{T} a_{1} = 1 .

The variable

z_{1} = \sum_{i = 1}^{p} a_{1 i} x_{i}

is known as the first principal component and gives the linear combination of the variables that gives the maximum variation. A second principal component,

z_{2} = \sum_{i = 1}^{p} a_{2 i} x_{i}

, is found such that:

a_{2}^{T} {S a}_{2}

is maximized subject to

a_{2}^{T} a_{2} = 1

and

a_{2}^{T} a_{1} = 0 .

This gives the linear combination of variables that is orthogonal to the first principal component that gives the maximum variation. Further principal components are derived in a similar way.

The vectors

a_{1}, a_{2}, \dots, a_{p}

, are the eigenvectors of the matrix

S

and associated with each eigenvector is the eigenvalue,

λ_{i}^{2}

. The value of

λ_{i}^{2} / \sum λ_{i}^{2}

gives the proportion of variation explained by the

i

th principal component. Alternatively, the

a_{i}

's can be considered as the right singular vectors in a singular value decomposition with singular values

λ_{i}

of the data matrix centred about its mean and scaled by

1 / \sqrt{(n - 1)}

X_{s}

. This latter approach is used in nag_mv_prin_comp (g03aac), with

X_{s} = V Λ P^{'}

where

Λ

is a diagonal matrix with elements

λ_{i}

P^{'}

is the

p

p

matrix with columns

a_{i}

and

V

is an

n

p

matrix with

V^{'} V = I

, which gives the principal component scores.

Principal component analysis is often used to reduce the dimension of a dataset, replacing a large number of correlated variables with a smaller number of orthogonal variables that still contain most of the information in the original dataset.

The choice of the number of dimensions required is usually based on the amount of variation accounted for by the leading principal components. If

k

principal components are selected, then a test of the equality of the remaining

p - k

eigenvalues is

(n - (2 p + 5) / 6) \{- \sum_{i = k + 1}^{p} \log (λ_{i}^{2}) + (p - k) \log (\sum_{i = k + 1}^{p} λ_{i}^{2} / (p - k))\}

which has, asymptotically, a

χ^{2}

distribution with

\frac{1}{2} (p - k - 1) (p - k + 2)

degrees of freedom.

Equality of the remaining eigenvalues indicates that if any more principal components are to be considered then they all should be considered.

Instead of the variance-covariance matrix the correlation matrix, the sums of squares and cross-products matrix or a standardized sums of squares and cross-products matrix may be used. In the last case

S

is replaced by

σ^{- 1 / 2} S σ^{- 1 / 2}

for a diagonal matrix

σ

with positive elements. If the correlation matrix is used, the

χ^{2}

approximation for the statistic given above is not valid.

The principal component scores,

F

, are the values of the principal component variables for the observations. These can be standardized so that the variance of these scores for each principal component is

1.0

or equal to the corresponding eigenvalue.

Weights can be used with the analysis, in which case the matrix

X

is first centred about the weighted means then each row is scaled by an amount

\sqrt{w_{i}}

, where

w_{i}

is the weight for the

i

th observation.

4

References

Chatfield C and Collins A J (1980) Introduction to Multivariate Analysis Chapman and Hall

Cooley W C and Lohnes P R (1971) Multivariate Data Analysis Wiley

Hammarling S (1985) The singular value decomposition in multivariate statistics SIGNUM Newsl. 20(3) 2–25

Kendall M G and Stuart A (1979) The Advanced Theory of Statistics (3 Volumes) (4th Edition) Griffin

Morrison D F (1967) Multivariate Statistical Methods McGraw–Hill

5

Arguments

1: $pcmatrix$ – Nag_PrinCompMatInput

On entry: indicates for which type of matrix the principal component analysis is to be carried out.

$pcmatrix = Nag_MatCorrelation$: It is for the correlation matrix.
$pcmatrix = Nag_MatStandardised$: It is for the standardized matrix, with standardizations given by s.
$pcmatrix = Nag_MatSumSq$: It is for the sums of squares and cross-products matrix.
$pcmatrix = Nag_MatVarCovar$: It is for the variance-covariance matrix.

Constraint:

pcmatrix = Nag_MatCorrelation

Nag_MatStandardised

Nag_MatSumSq

Nag_MatVarCovar

2: $scores$ – Nag_PrinCompScoresInput

On entry: specifies the type of principal component scores to be used.

$scores = Nag_ScoresStand$: The principal component scores are standardized so that $F^{'} F = I$ , i.e., $F = X_{s} P Λ^{- 1} = V$ .
$scores = Nag_ScoresNotStand$: The principal component scores are unstandardized, i.e., $F = X_{s} P = V Λ$ .
$scores = Nag_ScoresUnitVar$: The principal component scores are standardized so that they have unit variance.
$scores = Nag_ScoresEigenval$: The principal component scores are standardized so that they have variance equal to the corresponding eigenvalue.

Constraint:

scores = Nag_ScoresStand

Nag_ScoresNotStand

Nag_ScoresUnitVar

Nag_ScoresEigenval

3: $n$ – IntegerInput

On entry: the number of observations,

n

Constraint:

n \geq 2

4: $m$ – IntegerInput

On entry: the number of variables in the data matrix,

m

Constraint:

m \geq 1

5: $x [n \times tdx]$ – const doubleInput

On entry:

x [(i - 1) \times tdx + j - 1]

must contain the

i

th observation for the

j

th variable, for

i = 1, 2, \dots, n

and

j = 1, 2, \dots, m

6: $tdx$ – IntegerInput

On entry: the stride separating matrix column elements in the array x.

Constraint:

tdx \geq m

7: $isx [m]$ – const IntegerInput

On entry:

isx [j - 1]

indicates whether or not the

j

th variable is to be included in the analysis. If

isx [j - 1] > 0

, then the variable contained in the

j

th column of x is included in the principal component analysis, for

j = 1, 2, \dots, m

Constraint:

isx [j - 1] > 0

for nvar values of

j

8: $s [m]$ – doubleInput/Output

On entry: the standardizations to be used, if any.

pcmatrix = Nag_MatStandardised

, then the first

m

elements of s must contain the standardization coefficients, the diagonal elements of

σ

Constraint: if

isx [j - 1] > 0

s [j - 1] > 0.0

, for

j = 1, 2, \dots, m

On exit: if

pcmatrix = Nag_MatStandardised

, then s is unchanged on exit.

pcmatrix = Nag_MatCorrelation

, then s contains the variances of the selected variables.

s [j - 1]

contains the variance of the variable in the

j

th column of x if

isx [j - 1] > 0

pcmatrix = Nag_MatSumSq

Nag_MatVarCovar

, then s is not referenced.

9: $wt [n]$ – const doubleInput

On entry: optionally, the weights to be used in the principal component analysis.

wt [i - 1] = 0.0

, then the

i

th observation is not included in the analysis. The effective number of observations is the sum of the weights.

If weights are not provided then wt must be set to NULL and the effective number of observations is n.

Constraints:

if wt is not NULL, $wt [i - 1] \geq 0.0$ , for $i = 1, 2, \dots, n$ ;
if wt is not NULL, the sum of weights $\geq nvar + 1$ .

10: $nvar$ – IntegerInput

On entry: the number of variables in the principal component analysis,

p

Constraint:

1 \leq nvar \leq \min (n - 1, m)

11: $e [nvar \times tde]$ – doubleOutput

On exit: the statistics of the principal component analysis.

e [(i - 1) \times tde]

, the eigenvalues associated with the

i

th principal component,

λ_{i}^{2}

, for

i = 1, 2, \dots, p

e [(i - 1) \times tde + 1]

, the proportion of variation explained by the

i

th principal component, for

i = 1, 2, \dots, p

e [(i - 1) \times tde + 2]

, the cumulative proportion of variation explained by the first

i

principal components, for

i = 1, 2, \dots, p

e [(i - 1) \times tde + 3]

, the

χ^{2}

statistics, for

i = 1, 2, \dots, p

e [(i - 1) \times tde + 4]

, the degrees of freedom for the

χ^{2}

statistics, for

i = 1, 2, \dots, p

pcmatrix \neq Nag_MatCorrelation

, then

e [(i - 1) \times tde + 5]

contains the significance level for the

χ^{2}

statistic, for

i = 1, 2, \dots, p

pcmatrix = Nag_MatCorrelation

, then

e [(i - 1) \times tde + 5]

is returned as zero.

12: $tde$ – IntegerInput

On entry: the stride separating matrix column elements in the array e.

Constraint:

tde \geq 6

13: $p [nvar \times tdp]$ – doubleOutput

Note: the

(i, j)

th element of the matrix

P

is stored in

p [(i - 1) \times tdp + j - 1]

On exit: the first nvar columns of p contain the principal component loadings,

a_{i}

. The

j

th column of p contains the nvar coefficients for the

j

th principal component.

14: $tdp$ – IntegerInput

On entry: the stride separating matrix column elements in the array p.

Constraint:

tdp \geq nvar

15: $v [n \times tdv]$ – doubleOutput

Note: the

(i, j)

th element of the matrix

V

is stored in

v [(i - 1) \times tdv + j - 1]

On exit: the first nvar columns of v contain the principal component scores. The

j

th column of v contains the n scores for the

j

th principal component.

If weights are supplied in the array wt, then any rows for which

wt [i - 1]

is zero will be set to zero.

16: $tdv$ – IntegerInput

On entry: the stride separating matrix column elements in the array v.

Constraint:

tdv \geq nvar

17: $fail$ – NagError *Input/Output

The NAG error argument (see Section 3.7 in How to Use the NAG Library and its Documentation).

6

Error Indicators and Warnings

NE_2_INT_ARG_GE: On entry, $nvar = 〈value〉$ while $n = 〈value〉$ . These arguments must satisfy $nvar < n$ .
NE_2_INT_ARG_GT: On entry, $nvar = 〈value〉$ while $m = 〈value〉$ . These arguments must satisfy $nvar \leq m$ .
NE_2_INT_ARG_LT: On entry, $tdp = 〈value〉$ while $nvar = 〈value〉$ . These arguments must satisfy $tdp \geq nvar$ .

On entry, $tdv = 〈value〉$ while $nvar = 〈value〉$ . These arguments must satisfy $tdv \geq nvar$ .

On entry, $tdx = 〈value〉$ while $m = 〈value〉$ . These arguments must satisfy $tdx \geq m$ .
NE_ALLOC_FAIL: Dynamic memory allocation failed.
NE_BAD_PARAM: On entry, argument pcmatrix had an illegal value.

On entry, argument scores had an illegal value.
NE_INT_ARG_LT: On entry, $m = 〈value〉$ .
Constraint: $m \geq 1$ .

On entry, $n = 〈value〉$ .
Constraint: $n \geq 2$ .

On entry, $nvar = 〈value〉$ .
Constraint: $nvar \geq 1$ .

On entry, $tde = 〈value〉$ .
Constraint: $tde \geq 6$ .
NE_INTERNAL_ERROR: An internal error has occurred in this function. Check the function call and any array sizes. If the call is correct then please contact NAG for assistance.
NE_NEG_WEIGHT_ELEMENT: On entry, $wt [〈value〉] = 〈value〉$ .
Constraint: when referenced, all elements of wt must be non-negative.
NE_OBSERV_LT_VAR: With weighted data, the effective number of observations given by the sum of weights $= 〈value〉$ , while the number of variables included in the analysis, $nvar = 〈value〉$ .
Constraint: effective number of observations $> nvar + 1$ .
NE_SVD_NOT_CONV: The singular value decomposition has failed to converge. This is an unlikely error exit.
NE_VAR_INCL_INDICATED: The number of variables, nvar in the analysis $= 〈value〉$ , while the number of variables included in the analysis via array $isx = 〈value〉$ .
Constraint: these two numbers must be the same.
NE_VAR_INCL_STANDARD: On entry, the standardization element $s [〈value〉] = 〈value〉$ , while the variable to be included $isx [〈value〉] = 〈value〉$ .
Constraint: when a variable is to be included, the standardization element must be positive.
NE_ZERO_EIGVALS: All eigenvalues/singular values are zero. This will be caused by all the variables being constant.

7

Accuracy

As nag_mv_prin_comp (g03aac) uses a singular value decomposition of the data matrix, it will be less affected by ill-conditioned problems than traditional methods using the eigenvalue decomposition of the variance-covariance matrix.

8

Parallelism and Performance

nag_mv_prin_comp (g03aac) is not threaded in any implementation.

9

Further Comments

None.

10

Example

A dataset is taken from Cooley and Lohnes (1971), it consists of ten observations on three variables. The unweighted principal components based on the variance-covariance matrix are computed and unstandardized principal component scores requested.

NAG C Library Function Document

nag_mv_prin_comp (g03aac)

▸▿ Contents

1 Purpose

2 Specification

3 Description

4 References

5 Arguments

6 Error Indicators and Warnings

7 Accuracy

8 Parallelism and Performance

9 Further Comments

10 Example

10.1 Program Text

10.2 Program Data

10.3 Program Results

1

Purpose

2

Specification

3

Description

4

References

5

Arguments

6

Error Indicators and Warnings

7

Accuracy

8

Parallelism and Performance

9

Further Comments

10

Example

10.1

Program Text

10.2

Program Data

10.3

Program Results