Principal Component Analysis (PCA) Accounting Assignment (Essay Sample)

Name
Tutor
Course
Date
Principal Component Analysis
The principal component analysis (PCA) is a non-parametric approach used to extract relevant information from intricate data sets. This method utilizes an orthogonal transformation for converting correlated variables into linearly uncorrelated ones, which are referred to as principal components. Karl Pearson developed the PCA concept in 1991 as a derivative of the principal axis theorem as used in mechanics. In general, PCA helps in highlighting patterns and emphasizing variation in a dataset; this eases data exploration and visualization. PCA computes an optimal metric for re-expressing a noisy dataset; the main objective for this is that the new metric will filter the noise and emphasize the hidden dynamics (Shlens 2).
This orthogonal transformation method is commonly used to develop predictive models and for exploratory analysis of data; the concept mainly uses eigenvalue decomposition of a selected data sets covariance matrix. PCA is a simple form of the true multivariate analyses based on the eigenvector; arguably, it can be stated that this method highlights a data set's internal structure using an approach that explicates the variance. This technique seeks to establish whether there is another basis for re-expressing a data set using a linear combination of the initial basis.
The assumption and inclusion of linearity in the PCA concept helps simplif...