pca() not working as advertised

When consulting the documentation for the pca() function, I tried the following example:

load hald

The ingredients data has 13 observations for 4 variables.

Find the principal components for the ingredients data.

 load hald
 coeff = pca(ingredients)

coeff =

-0.0678 -0.6460 0.5673 0.5062

-0.6785 -0.0200 -0.5440 0.4933

0.0290 0.7553 0.4036 0.5156

0.7309 -0.1085 -0.4684 0.4844

The rows of coeff contain the coefficients for the four ingredient variables, and its columns correspond to four principal components.

However on my machine, I get this output for the same commands:

 load hald
 coeff = pca(ingredients)

coeff =

517.7969

67.4964

12.4054

0.2372

Does anyone know why this is happening? I am running the latest version of Matlab r2016b on Ubuntu 16.04

Answer 1

[KSSV]

Try

[pc,score,latent,tsquare] = princomp(ingredients);

[Alexander Tarroni]

This gives an error:

Error using pca Too many input arguments.

Error in princomp (line 30) [varargout{1:nargout}]=pca(varargin{1},'Algorithm','svd','Economy',fEconomy);

[rsnandi]

I'm also getting the same error.

[Hamidreza Heydarian]

Same here. This should be a bug.

[XiXi Liu]

通过命令: which -all princomp 或者 which -all pca

查看pca/princomp都有哪些路径；

会显示至少两个有该函数的路径，因此造成冲突；

手动删除其中的某个路径，尽量保留Matlab 工具箱的路径。

[Image Analyst]

princomp() was removed from the Statistics and Machine Learning Toolbox in R2019a.

In r2020a:

load hald
coeff = pca(ingredients)

coeff =

-0.0678 -0.64602 0.56731 0.50618

-0.67852 -0.019993 -0.54397 0.49327

0.029021 0.75531 0.40355 0.51557

0.73087 -0.10848 -0.4684 0.48442