|
Lecturer(s)
|
-
Javůrek Milan, doc. Ing. CSc.
|
|
Course content
|
Metrology: Introduction to the basics of metrology, statistical estimation parameters position, dispersion and form, calculation uncertainties establish entitlements result. Character range unit data: Data matrix, objects and variables. Types of variables and multidimensional accidental vector. Preliminary treatment multidimensional data: Sorts transformation. Centering and standardization data. Exploratory analysis of multivariate data: Sorts display range multivariate data. Searching of outliers. Statistical testing of multivariate accidental selections: Estimates parameters position and dispersion. Statistic analysis vector mean value, statistic analysis of covarince matrixes. Analysis covariance: Interpretation of covariane matrix. Analysis of correlation matrix. Pair correlation coefficient, partial correlation coefficient, multiple correlation coefficient. Principal components analysis PCA: Characteristics and geometric meaning of the chief component and their reading. Graphic tools PCA. Diagnostics PCA. Factor analysis FA: Principles of method and progress FA. Model of factor analyses and parameter estimate. Estimation of factor score, rotation factors. Statement of a problem FA and graphic tools. Found solving and achieved tightness fitting. Reading results and naming factors. Canonical correlation analysis CCA: Principles of method and progress diagnosed CCA. Test of significance canonical correlation. Found solving and achieved tightness fitting. Discriminant analysis DA: Classification objects. Principles of method, progress DA and range rules. Linear and quadratic discriminating function. Option signs. Adjustment threshold point. Diagram territorial map. Found solving and achieved tightness fitting. Logistic regression LR: Principles of method and progress logistic regression. Estimates of parameters and their statistical significance and reading. Quality evaluation and found solving and achieved tightness fitting. Cluster analysis CLU: Principles of cluster analyses. Measurement similarity and distance. Fitness standardization data. Criteria for appreciation qualities analysis to the clusters, distance and resemblance objects. Hierarchic sequence analysis. Dendrograms hierarchical clustering. Fuzzy clustering. Clustering method nearest centres- medoids. Tightness fitting under the course of construction clusters. Surveying objects range unit spectrum MDS: Principles of method and progress range unit spectrum. Metric and no metric method MDS. Found solving and achieved tightness fitting. Correspondence analysis CA: Principles of method and progress of correspondence analyses. Found solving and achieved tightness fitting. Reading results.
|
|
Learning activities and teaching methods
|
|
Monologic (reading, lecture, briefing), Laboratory work
|
|
Learning outcomes
|
The application of computer oriented statistical methods in scientific and technical fields enables not only the use of information hidden in data but also the creation of models, optimizations, and possible solutions. It is a multi-disciplinary movement on the frontier of the scientific disciplines of statistics and informatics. The goal of multivariate data processing is to classify data according to many variables and to find hidden structure and interrelationship among these variables. The objective is to find a way of condensing the information contained in a number of original variables into a smaller set of variables with a minimum loss of information. The objective is to classify a sample of entities into a small number of mutually exclusive groups based on the similarities among the entities.
Independent creativ knowledge of evoluation of really experimental data.
|
|
Prerequisites
|
Knowledge basic statistical methods one - dimensional data.
|
|
Assessment methods and criteria
|
Oral examination, Home assignment evaluation
Self work with statistical software.
|
|
Recommended literature
|
-
HEBÁK, P. a kol. Vícerozměrné statistické metody (1). Praha: Informatorium, (2004), ISBN 80-7333-025-3..
-
HEBÁK, P. a kol. Vícerozměrné statistické metody (3). Praha: Informatorium, (2007), ISBN 978-80-73333-001-9..
-
MELOUN, M.; MILITKÝ, J. Kompendium statistického zpracování dat. Praha: Academia (2006), ISBN 80-200-1396-2..
-
MELOUN, M.; MILITKÝ, J. Statistical analysis of experimental data. In press..
-
MELOUN, M.; MILITKÝ, J. Statistická analýza experimentálních dat. Praha: Academia (2004), ISBN 80-200-1254-0..
|