Open Access Open Access  Restricted Access Subscription or Fee Access

Simulation Study: Incorporation of Mixed Variables into Principal Component Analysis

Md. Nayem Dewan, Fazle Rabby, Shaila Sharmin


Publications that are concerned to principal component analysis (PCA) and wealth
index is a very popular topic in economics for last several years. This paper also
aims to explore these two things. So far many authors established that the use of traditional PCA approach is not suitable for wealth index construction with all types of data. It is a more serious problem when the data set contains mixed variables. Researchers are trying to solve this issue for many years. This paper is dedicated to explore the two ways of using mixed data into PCA. Here we define mixed data as data set that contains both numeric and categorical variables jointly. Two methods that are discussed and compared are namely nonlinear PCA using homogeneity analysis and PCAmix. Properties of these two methods have also been discussed here with proper references. An extensive simulation study is performed to find the best approach for dealing with mixed data. We have found that PCAmix explains more variation, greater correlation with true scores and gives less misclassification than nonlinear PCA. Overall, PCAmix showed better result than nonlinear PCA in terms of proportion of explained variance, misclassification rate and rank correlation. Statistical analysis and simulation were done by using programming language R.


Principal component analysis, Nonlinear PCA, PCAmix, simulation, wealth index, SES .

Full Text:


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.