Often in experimental design multiple variables are related in such a way that by analyzing them simultaneously additional information, and often times essentially information, can be gathered that would be missed if each variable was examined individually (as is the case in univariate analyses). For example, in univariate statistics we study random variables that have a normal distribution (characterized by the usual bell shaped curve), while in multivariate statistics we study groups of random variables that have a multivariate normal distribution. Such variables are related in a way that the effects can’t be meaningfully interpreted separately.

Topics:

- Descriptive Multivariate Statistics
- Multivariate Normal Distribution
- Hotelling’s T
^{2}Statistic and Analysis of the Mean - Multivariate Analysis of Variance (MANOVA)
- Box’s Test for the Equality of Covariance Matrices
- Factor Analysis

- Cluster Analysis
- Discriminant Analysis
- Correspondence Analysis

I really appreciate finding this web. Good job.

i also appreciate this site

Hi Charles, I feel honoured to have a discussion with you. Kindly help me with this : I want to test efffects of 13 factors (divided into 31 sub-factors questionnaire survey i.e answers to 31 questions will produce score of 13 factors to relate to 03 result factors) on 03 factors (again divided into five sub-factors). For example, how 13 habits can improve 03 results (say mind, body and soul)! Now 13 habits (factors) converted to 31 questions whose answers will give the score on 03 results(factors) which are subdivided into five sub-factors (Say, mind – smile, memory; body- strength, muscles ;soul-peacefulness.). Pl guide me how do I proceed with data collected and what all Statistical analysis tools I must use to complete my work. Regards

Sanjay,

What hypotheses are you trying to test?

Charles

So kind of you, Charles. I plan to test 13 Hypotheses that state 13 habits can improve 05 results as mentioned above. But that way I will have to formulate 13X5=65 hypotheses. this will be a voluminous task. Is there any way to reduce the work involved in this so that I can test the factors responsible for the results?Also, I want to know what should be the pattern of my questionnaire..my respondents (sample for pilot test & population) are professionals in the related field, so content validity can also be ensured by the questionnaire.

let me elaborate a bit more on this. First hypothesis is “Good habits improve good health”. Good habits are ensured by 13 factors and good health defined by 03 factors. 13 factors subdivided and covered through 31 questions and 03 factors covered though 05 sub-factors.

Sorry Sanjay, but we would need to get into a lot more detail before I could offer much advice, and I frankly don’t have the time to do this now, especially since I plan to go on vacation tomorrow.

Charles