Classification analysis


1. H-methods in Discriminant Analysis.  
2. Measures of classification.   
3. The H-method of estimation.  
4. Optimal score vectors   
5. Graphic analysis.  
6. Case study  
7. Regression and classification.  
8. Modelling strategies.  
9. Examples  
10. Dimension analysis.  
11. Error rate analysis.  
12. Distance measures.  
13. Importance of variables.  
14. Quadratic procedures  
15. Case study.  
16. Comparisons of methods  
17. Confidence intervals  
18. Detection of special features  
19. Sensitivity analysis  
20. Case study  
21. Guidelines for presentation of results  

Classification analysis is one of the most important methods in applied sciences. The starting point is typically data that have been measured for some classes. In classification the task is to characterize each class of data, such that when a new sample becomes available, it can be allocated to one of the classes.

The H-methods applied here define methods to identify good score vectors that have some optimal properties in characterizing the classes. The importance of these methods is due to that they can be applied to situations, where the classes are characterized by many variables. There can be hundreds or thousands of variables, which can be handled effectively.

An important aspect of these methods is the graphic procedures that are available.

Both linear and non-linear procedures have been developed.

See a short introduction to some of the ideas. In Chapter 4 is presented a case study using the Mushroom data.