vuoi
o PayPal
tutte le volte che vuoi
APPLIED STATISTICS
→
Multivariate analysis 2 types with different goals:
1. Analysis of dependence: simple multiple linear regression, LOGISTIC
REGRESSION
2. Analysis of interdependence: FACTOR ANALYSIS, CLUSTER ANALYSIS
(hierarchical and non-hierarchical)
FACTOR ANALYSIS
• Def: it is a multivariate technique for interdependence analysis among quantitative
variables
• Main objective: reduce variables, more aggregate information, new quantitative variables
characterized by optimal properties. Input have multicollinearity problem, with factor
analysis we adjust it.
• Extraction method: (PCA) Principal components method, it assumes that the specific
information contribution of the input variables is very low, while the shared information
contribution is very high, so that can be explained through k principal common factors
• How many factors:
1. the factors must be 30% of the initial variables (=k/p)
2. scree plot, stop before the point where the line gets flatter
3. percentage of tot Variance explained: btw 60 and 75%. (if it is more, you have to
reduce factors)
4. Latent Roots (EIGENVALUES): > 1 (default factor)
2
5. Communalities (∑
Accedi a tutti gli appunti
Tutor AI: studia meglio e in meno tempo
