easyMCA: Multiple Correspondence Analysis

In DiscriMiner: Tools of the Trade for Discriminant Analysis

Description

Performs a basic Multiple Correspondence Analysis (MCA)

Usage

  easyMCA(variables)

Arguments

variables

data frame with categorical variables (coded as factors)

Value

An object of class "qualmca", basically a list with the following elements:

values	table with eigenvalues
coefficients	coefficients of factorial axes
components	factor coordinates

Author(s)

Gaston Sanchez

References

Lebart L., Piron M., Morineau A. (2006) Statistique Exploratoire Multidimensionnelle. Dunod, Paris.

Saporta G. (2006) Probabilites, analyse des donnees et statistique. Editions Technip, Paris.

See Also

disqual, binarize

Examples

## Not run: 
  # load insurance wines dataset
  data(insurance)

  # multiple correspondence analysis
  mca1 = easyMCA(insurance[,-1])
  mca1
  
## End(Not run)

Example output

Multiple Correspondence Analysis
-------------------------------------------
$values         eigenvalues
$coefficients   coeffs of factorial axes
$components     factor coordinates
-------------------------------------------

$values
    eigenvalues  proportion  accumulated
1     0.2438      19.9506     19.9506   
2     0.1893      15.4915     35.4421   
3     0.1457      11.9177     47.3599   
4     0.1201       9.8240     57.1838   
5     0.1091       8.9237     66.1075   
6     0.0999       8.1737     74.2812   
7     0.0855       6.9953     81.2765   
8     0.0732       5.9873     87.2638   
9     0.0573       4.6849     91.9487   
10    0.0511       4.1828     96.1315   
11    0.0473       3.8685    100.0000   


$coefficients
                        U1             U2            U3            U4
private        -0.03362485   0.0843551646  -0.005975991   0.009265931
professional    0.16739724  -0.4199519275   0.029750746  -0.046129310
companies       0.20841174  -0.7533698947   0.190863114  -0.124969772
female          0.07147838   0.1545260331   0.253056684  -0.151656643
male           -0.04115240   0.0181180564  -0.097041337   0.059098333
flemish        -0.13472837  -0.0967814117  -0.217484051  -0.294519199
french          0.04610850   0.0331217938   0.074430221   0.100794192
BD_1890_1949    0.01424527   0.0872725142  -0.199728614   0.264163434
BD_1950_1973    0.19275420   0.1632843832   0.002462495  -0.213596450
BD_unknown     -0.12872757  -0.1546852846   0.119672182  -0.027241715
Brussels        0.14710599  -0.0010703789   0.196205238   0.201369910
Other_regions  -0.07305534   0.0005315684  -0.097438866  -0.100003731
BM_minus        0.18096941  -0.0178773690  -0.009601618  -0.032467853
BM_plus        -0.18360648   0.0181378771   0.009741532   0.032940973
YS<86          -0.13647865  -0.0392861556   0.082328327   0.058911691
YS>=86          0.17996870   0.0518050144  -0.108562930  -0.077684390
HP<=39         -0.04978445   0.1787638011   0.274475273  -0.240531313
HP>=40          0.01215211  -0.0436352585  -0.066997901   0.058712368
YC_33_89       -0.04961241   0.0135793792   0.050792979  -0.011271060
YC_90_91        0.14427921  -0.0394905622  -0.147712444   0.032777675
                         U5
private        -0.016670704
professional    0.082993071
companies       0.119828632
female          0.304042165
male           -0.106854515
flemish        -0.019361141
french          0.006626021
BD_1890_1949    0.249356204
BD_1950_1973   -0.214203902
BD_unknown     -0.017877443
Brussels       -0.101524718
Other_regions   0.050418906
BM_minus       -0.059170907
BM_plus         0.060033143
YS<86          -0.008319811
YS>=86          0.010970987
HP<=39          0.185864693
HP>=40         -0.045368547
YC_33_89       -0.105998503
YC_90_91        0.308257130
...

DiscriMiner documentation built on May 1, 2019, 10:32 p.m.