Saturday, 15 September 2012

Factor_Analysis_session_15&16_Team_A


Factor Analysis
Factor analysis attempts to identify underlying variables, or factors, that explain the pattern of correlations within a set of observed variables. Factor analysis is often used in data reduction to identify a small number of factors that explain most of the variance observed in a much larger number of manifest variables. Factor analysis can also be used to generate hypotheses regarding causal mechanisms or to screen variables for subsequent analysis (for example, to identify collinearity prior to performing a linear regression analysis).
Types of factor analysis
Exploratory factor analysis seeks to uncover the underlying structure of a relatively large set of variables. The researcher's assumption is that any indicator may be associated with any factor. This is the most common form of factor analysis.
Confirmatory factor analysis seeks to determine if the number of factors and the loadings of measured (indicator) variables on them conform to what is expected on the basis of pre-established theory.

Factor Rotation
Factor rotation is an important tool in factor analysis. In factor analysis, the rotated component matrix displays the loadings of variables on factors. Variables are associated with factors based on high loadings. If the factor axes are rotated, the loading of a variable on one factor is maximized while it is loading on the other factors is minimized thereby making the factor structure easier to interpret.
When the factor axes are turned by 90 degrees, the rotation is called orthogonal. When the axes are turned by some other arbitrary degree the rotation is called oblique. Varimax, Quartimax and Equamax are types of orthogonal rotations, whereas Direct Oblimin and Promax are types of oblique rotations.
Varimax
The most popular rotation technique in factor analysis is Varimax. A Varimax rotation attempts to simplify the columns of the factor matrix achieving the maximum simplification when only 1s or 0s are present in the columns of the matrix. It results in factors that are independent of  each other.

It is desirable to rotate the factor axes during factor analysis because unrotated solutions do not have a clean factor structure and therefore are difficult to interpret. On the other hand, rotation changes factor loadings and this may lead to factors with different meanings dependent on the rotation.
Naquib Ahmed
Group-A
Operations

No comments:

Post a Comment