1
$\begingroup$

This question already has an answer here:

enter image description here

I am doing a PCA on 24 satisfaction variables from a survey.

Respondents indicate their levels of satisfaction towards different aspects of the service.

These variables are all measured in same unit, 1-5, 1= very dissatisfied, 5= very satisfied.

x1-x3 are about pier, x4-x11 are about staff, x12-x16 are about food, x17-x18, x19-x22, x23-x24 are related

EDIT: if the principal components show a satisfaction variable with high eigenvector loading value,

does it mean that respondent is satisfied with that aspect of service,

or does it mean that the respondent puts more weight on that aspect of service when he/she thinks of his overall satisfaction of the service.

If the answer is the former one, I should find the factor with lowest/negative score across all PCs and interpret that that aspect of service needs to be improved, yes?

$\endgroup$

marked as duplicate by amoeba, kjetil b halvorsen, Peter Flom Dec 5 '18 at 11:54

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • $\begingroup$ Question was mangled in an edit by OP. Please don't do that. (You can't unilaterally delete a thread with upvoted answer, but mangling it serves no good purpose.) $\endgroup$ – Nick Cox Dec 16 '18 at 7:36
2
$\begingroup$

"It means what it says" will no doubt not seem helpful.

So, let's try to make it concrete.

As the variables are all on the same scale, you do have a choice. Using a correlation matrix will ignore differences in variance (variation) so that e.g. a variable with many 1s and 5s will have the same weight as one with mostly 3s.

If that sounds what you want, go for correlation.

If not, go for covariance.

In any case, look at the variances, or equivalently the standard deviations (SDs), of the variables: if they are about the same, it should not matter much which you choose. If even one variable has very different variance (SD), it will matter.

For data like yours, I would typically use the covariance matrix. If say one variable is nearly constant, it doesn't much help to explain patterns of variation or covariation and I would see no point in standardising so it does, which would just mean that small noise is amplified.

In practice, researchers don't usually include a question unless they expect variability that is interesting and informative, so SDs may not differ enormously.

On a different note, I would be cautious about putting all 20 variables into a PC unless they are measures of the same underlying phenomenon. It is often much more fruitful to be strict about looking only at clusters of variables that make sense as being closely related.

EDIT A table of results (loadings?) has been added. You seem to be throwing all 24 (!) (not 20) variables into one PCA. As already hinted, I don't usually find that helpful unless variables all have similar meaning in the first place. I find it's more helpful to show correlations between original variables and PCs; that's not always a default from software and you may have to do some work to get them. Here PC1 just appears to be an average of everything (which can happen). Any interpretation of results needs more subject-matter knowledge than we can possibly have.

Although you asked a question, you aren't saying whether these results come out of a covariance or a correlation matrix.

Also, the whole question is still backwards. It perhaps needs to start "P people in situation S were asked Q questions with the aim of finding out about X" -- where the abstractions are all to be made concrete.

$\endgroup$
  • $\begingroup$ Thanks a lot. Also, lets say the 3rd principal component, 3 variables about comfort have high positive weights but 3 variables about price have -0.5 weightings. What can I interpret from it? $\endgroup$ – Kenny Dec 4 '18 at 18:00
  • $\begingroup$ And, if most of the PC's eigenvectors have below 0.5 weightings, what can I interpret from it? Lets say highest weighting for PC1 is 0.2, 0.3 for PC2, 0.4 for PC3. Does this mean there are no standout variables? All of the variables are considered? $\endgroup$ – Kenny Dec 4 '18 at 18:03
  • $\begingroup$ I think you've had a strong hint already not to mix different clusters of variables in a PCA. We know no more about "price" and "comfort" than that you have just mentioned them. You are giving us small fragments of the resuts. If you want serious help with the analysis, post (an example of) the data, show graphs, more of the results, etc. $\endgroup$ – Nick Cox Dec 4 '18 at 18:08
  • $\begingroup$ imgur.com/a/OrxH8gy, only PC4 and 6 have positive weightings above 0.5. Also for PC5 and PC6, X23 and X24 have high negative weights in PC5 and high positive weightings in PC6, X17 and X18 have high positive weights in PC5 and PC6. What can I interpret from it. X17 and X18 is about the route and scenery, X23 and X24 are about the staff hospitality and efficiency. $\endgroup$ – Kenny Dec 4 '18 at 18:57
  • $\begingroup$ posted above, x1-x3 are about pier, x4-x11 are about the cruise ship itself, x12-x16 are about food, x17-x18, x19-x22, x23-x24 are related. $\endgroup$ – Kenny Dec 4 '18 at 19:43

Not the answer you're looking for? Browse other questions tagged or ask your own question.