Scribd
Upload
10 views2 pages

Statistical Terminologies Explained

The document provides simplified explanations of key statistical terminologies related to Factor Analysis and Discriminant Analysis. It covers essential concepts such as the KMO Test, Bartlett's Test, and various matrices used in Discriminant Analysis, including Box's M Test and Wilks' Lambda. These terms help in understanding the suitability of data for analysis and the relationships among variables and groups.

Uploaded by

chauhanpt2
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views2 pages

Statistical Terminologies Explained

The document provides simplified explanations of key statistical terminologies related to Factor Analysis and Discriminant Analysis. It covers essential concepts such as the KMO Test, Bartlett's Test, and various matrices used in Discriminant Analysis, including Box's M Test and Wilks' Lambda. These terms help in understanding the suitability of data for analysis and the relationships among variables and groups.

Uploaded by

chauhanpt2
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Simplified Explanation of Statistical Terminologies

1. Factor Analysis (Simple Explanation)

Kaiser-Meyer-Olkin (KMO) Test: Checks if your data is suitable for factor analysis. Closer to 1 is

better.

Bartlett's Test of Sphericity: Tests if the data has enough relationships. Significant result = suitable

for factor analysis.

Communalities: Shows how much of a variable's variance is explained by the factors.

Initial: Represents starting values before extracting the main factors.

Extraction: Shows how much each variable is explained by the chosen factors.

Factor: The underlying group formed from variables.

Initial Eigenvalues: Tells how much of the total variance each factor explains.

Total: Total variance explained by each factor.

% of Variance: Percentage of total variance explained by each factor.

Cumulative %: Combined total variance explained by multiple factors.

Extraction Sums of Squared Loadings: Total variance explained by selected factors.

Rotation Sums of Squared Loadings: Shows variance distribution after rotation for clarity.

Scree Plot: Graph of eigenvalues to decide number of factors to retain.

Factor Matrix: Shows which variable loads on which factor.

Reproduced Correlation: Estimated vs actual correlations to assess model fit.

Residual: Difference between original and reproduced correlations.

Rotated Factor Matrix: After rotation, shows clearer loading of variables on factors.
2. Discriminant Analysis (First Part)

Means: Shows average values of each variable for each group.

Univariate ANOVAs: Checks if the average values are significantly different among groups.

3. Discriminant Analysis (Second Part)

Box's M Test: Checks if group variances are equal. Non-significant result means groups are similar.

Function Coefficients: Weights used in classification formulas. Shows importance of variables.

Fisher's Function Coefficients: Group-specific formulas to assign a case to a group.

Matrices: Shows relationships like correlation and covariance among variables and groups.

Within-groups correlation: Average correlation from all groups.

Within-groups covariance: Average of covariances from all groups.

Separate-groups covariance: Covariance calculated separately for each group.

Total covariance: Covariance from treating all data as one group.

Wilks' Lambda: Shows how well the function separates groups. Lower is better.

You might also like