Now-a-days there is an increase in number of applications that produce large volumes of high dimensional datasets. It is very common that we come across very large sets of observations, represented by hundreds and thousands of input variables in scientific databases. With these large datasets, for example some of the data mining tasks such as clustering, classification, prediction become ineffective. Even when we apply effective data mining algorithms for doing these tasks, results are not satisfactory. Thus, applications on Data mining, Image processing etc., need Dimensionality reduction as first step for solving classification, clustering, prediction problems. It has become a challenge for the researchers to reduce the collected data. There are many statistical Dimension reduction methods used in signal processing, machine learning, data mining applications viz., Factor analysis, Mahalanobis Taguchi method, Singular Value Decomposition, Principal Component Analysis. In this paper, MATLAB program for a simple multivariate statistical model called Principal Component Analysis is written and has been applied to a sample dataset. Multivariate statistics is a form of statistics encompassing the simultaneous observation and analysis of more than one outcome variable. Step by step explanation for the numerical example has also been presented. Principal Component Analysis is becoming popular now-a-days because of its simplicity. © Research India Publications.