Skip to content Skip to footer

An Introduction To Multivariate Statistical Analysis

In this book we shall concern ourselves with statistical analyses of data that consist of sets of measurements on a number of individuals or objects. For example, the sample data may be heights and weights of some indi- viduals drawn randomly from a population of school children in a given city, or the statistical treatment may be made on a collection of measure- ments, such as lengths and widths of petals and lengths and widths of sepals of iris plants taken from two species, or one may study the scores on batteries of mental tests administered to a number of students.

Additional information



Accession No




Number Of Pages



Paṉmuka puḷḷiyiyal pakuppāyviṟku oru aṟimukam


WIley Eastern Private Limited

Publishing Year




Categories: , Tags: , Product ID: 25476


The mathematical model on which analysis is based is a multivariate normal distribution or a combination of multivariate normal distributions. The problems we shall treat have to do with inference concerning para- meters of such distributions, such problems as testing a hypothesis of equality of means, point estimation of correlation coefficients, and decision between several hypotheses of specified distributions.
Although there are statistical problems of multiple measurement that cannot be based on the model of normal distributions and although there are other statistical methods which are applicable to samples from other types of distributions (for example, the multinomial distribution), we shall consider in this book only statistical analysis based on the normal distribu- tion. The main justification for studying methods relating to the normal distribution so intensively is that this mathematical model is suitable for such a large number of cases where multiple measurements are treated.



There are no reviews yet.

Be the first to review “An Introduction To Multivariate Statistical Analysis”

Your email address will not be published. Required fields are marked *