Glosarium AI
Kamus lengkap Kecerdasan Buatan
Principal Component Analysis (PCA)
Dimensionality reduction method that transforms correlated variables into new uncorrelated variables called principal components, maximizing explained variance.
Correspondence Analysis (CA)
Multivariate analysis technique adapted for contingency tables, allowing the study of relationships between categories of qualitative variables.
MANOVA
Multivariate analysis of variance allowing simultaneous testing of differences between groups on multiple continuous dependent variables.
Canonical Correlation Analysis
Exploratory method identifying maximal linear relationships between two sets of quantitative variables.
Partial Correlation Coefficient
Measure of association between two variables after statistically controlling for the effect of one or more other variables.
Multiple Correspondence Analysis (MCA)
Extension of CA for simultaneous analysis of more than two qualitative variables, creating a factorial space representing associations.
PLS Regression
Predictive modeling method combining regression and dimensionality reduction, particularly effective for multicollinear data.
Kohonen Map (SOM)
Unsupervised artificial neural network performing nonlinear projection of multidimensional data onto a two-dimensional grid.
Multiple Factor Analysis (MFA)
Method allowing simultaneous analysis of multiple variable tables while balancing the influence of each group in the factorial structure.
Independent Component Analysis (ICA)
Blind source separation technique seeking to decompose a multivariate signal into statistically independent components.
Mahalanobis Distance
Distance measure accounting for the correlation structure between variables, identifying atypical observations in a multivariate space.