Sadržaj predavanja

• 1. Podaci1. DataTypes of data, variables and observations.
  Mjerne skale podataka, varijable, observacije.
• 2. Kvalitativni podaci 2. Qualitative data Descriptive statistics: frequency table, bar chart, contingency table, independence of qualitative variables.
  Deskriptivne statistike, tablica frekvencija, stupčasti dijagram, kontingencijska tablica, nezavisnost kvalitativnih varijabli.
• 3. Kvantitativni podaci 3. Quantitative data Histogram, descriptive statistics, box-plot, independence of quantitative variables, scatter plot, correlation.
  Histogram, deskriptivne statistike, box-plot, nezavisnost kvantitativnih varijabli, dijagram rasipanja, korelacija.
• 4. Nezavisnost kvantitativne i kvalitativne varijable 4. Independence of a quantitative and a qualitative variable Parallel box-plots, dot plot.
  Paralelni box-plotovi, točkasti dijagrami.
• 5. Uzorkovanje 5. Sampling Concept of a population and a sample, probability distributions, parameters of a distribution, sampling distribution.
  Koncepti populacije i uzorka, vjerojatnosne razdiobe, parametri razdioba, razdioba uzorkovanja.
• 6. Procjena parametara6. Estimating parameters Paradigms, methods, efficiency, bias.
  Paradigma, metode, nepristranost, konzistentnost, učinkovitost.
• 7. Pripasavanje razdiobe 7. Fitting distributions Chi-square test, qq plot, Kolmogorov Smirnov test.
  Hi-kvadrat test, qq dijagram, Kolmogorov-Smirnov test.
• 8. Modeli za kvalitativne varijable 8. Models for qualitative variables Contingency table and chi-square test, log-linear model.
  Kontingencijska tablica i hi-kvadrat test, log-linearni model.
• 9. Opći linearni model9. General linear model T-test, linear regression, ANOVA, ANCOVA, common framework, design of experiments, fixed and random effects.
  T-test, linearna regresija, ANOVA, ANCOVA, zajednički okvir, dizajn eksperimenta, fiksni i slučajni efekti.
• 10. Generalizirani linearni model 10. Generalized linear model Logistic and Poisson regression.
  Logistička i Poissonova regresija.
• 11. Multivarijatne metode 11. Multivariate methods Correlation matrix, MANOVA, canonical correlation, canonical discriminant analysis.
  Korelacijska matrica, MANOVA, kanonička korelacija, kanonička diskriminacijska analiza.
• 12. Redukcija dimenzionalnosti 12. Dimension reduction Principal components analysis, common factor analysis. Application in text mining: latent semantic indexing.
  Analiza glavnih komponenti, zajednička faktorska analiza. Primjer u rudarenju tekstualnih dokumenata: latentno semantičko indeksiranje.
• 13. Udaljenosti / sličnosti13. Distances/similarities Distance/similarity matrix, cluster analysis, multidimensional scaling.
  Matrica udaljenosti / sličnosti, klaster analiza, multidimenzionalno skaliranje.
• 14. Klasifikacija podataka 14. Data classification K-nearest neighbors, decision trees, support vector machines.
  K-najbližih susjeda, stable odlučivanja, metoda potpornih vektora (engl. Support vector machines).

Osnovna literatura

• 1. de Veaux RD, Velleman PF, Bock DE (2009) Intro Stats (3. izdanje). Boston: Pearson Education Inc. ISBN-13: 978-0-321-50045-8
• 2. Kalton G (ur.) (1983) Introduction to Survey Sampling. Sage Publications, Inc. ISBN-13: 978-0803921269
• 3. Milliken GA, Johnson DE (1984) Analysis of Messy Data, Volume I: Designed Experiments. Chapman & Hall. ISBN-13: 978-0-412-99081-6
• 4. Milliken GA, Johnson DE (1989) Analysis of Messy Data, Volume II: Nonreplicated Experiments. Chapman & Hall. ISBN-13: 978-0-412-06371-8
• 5. Milliken GA, Johnson DE (2001) Analysis of Messy Data, Volume III: Analysis of Covariance. Chapman & Hall. ISBN-13: 978-1-584-88083-7
• 6. McCulloch CE, Searle SR, Neuhaus JM (2008) Generalized, Linear, and Mixed Models (2. izdanje, Wiley Series in Probability and Statistics). Wiley-Interscience.
• 7. Izenman AJ (2008) Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning. Springer. ISBN-13: 978-0387781884
• 8. I.H. Witten, E. Frank (2000) Data Mining,Practical Machine Learning Tools and Techniques with Java Implementations, Morgan Kaufmann, ISBN 1-55860-552-5
• 9. T.M. Mitchell (1997), Machine Learning, McGraw-Hill

Dopunska literatura

• 1. Converse JM, Presser S (1986) Survey Questions: Handcrafting the Standardized Questionnaire. Sage Publications, Inc. ISBN-13: 978-0803927438
• 2. Skrondal A, Rabe-Hesketh S (2004) Generalized Latent Variable Modeling: Multilevel, Longitudinal, and Structural Equation Models. Chapman and Hall/CRC. ISBN-13: 978-1584880004
• 3. Cowpertwait PSP, Metcalfe AV (2009) Introductory Time Series with R. Springer. ISBN-13: 978-0387886978
• 4. Ostini R, Nering ML (ur.) (2005) Polytomous Item Response Theory Models (Quantitative Applications in the Social Sciences). Sage Publications, Inc. ISBN-13: 978-0-761-93068-6
• 5. Simon JL (1997) Resampling: The New Statistics (2nd edition). Resampling Stats. ISBN-13: 978-0534217204 http://www.resample.com/content/text/index.shtml
• 6. Hoaglin DC, Mosteller F, Tukey JW (ur.) (2000) Understanding Robust and Exploratory Data Analysis. Wiley-Interscience. ISBN-13: 978-0471384915
• 7. Aldenderfer MS, Blashfield RK (1984) Cluster Analysis. Sage Publications, Inc. ISBN-13: 978-0803923768
• 8. Lynch SM (2009) Introduction to Applied Bayesian Statistics and Estimation for Social Scientists. New York: Springer. ISBN-13: 978-1441924346
• 9. Gwet KL (2010) Handbook of Inter-Rater Reliability (2. izdanje) Advanced Analytics, LLC. ISBN-13: 978-0970806222
• 10. Duda RO, Hart PE, Stork DG (2001) Pattern Classification, 2. izdanje, John Wiley and Sons, ISBN 0-471-05669-3
• 11. Berry MJA, Linoff G (2000) Mastering Data Mininbg: The Art and Science of Customer Relationship Management, 2. izdanje, John Wiley and Sons, ISBN 0-471-33123-6

Slični predmeti

• University of Pittsburgh School of Information Science Graduate programme Informations Science and Technology. Intermediate analytical course in applied statistical methods: vector and matrix notation, multiple correlation and regression, T and F distributions, analysis of variance, planned comparisons and post hoc comparisons, analysis of covariance, and nonparametric techniques. Utilizes SPSS statistical programming package.
• University of Pittsburgh School of Information Science Graduate programme Informations Science and Technology. Introduction to data-mining techniques, including data preprocessing, data-mining primitives, association rules, decision trees, cluster analysis, classification and machine learning, data visualization, and data warehousing. Detailed applications from a wide variety of domains.
• University of Hawaii The Department of Information and Computer Sciences and the Library and Information Science Program in the College of Natural Sciences, the School of Communications in the College of Social Sciences, and the Department of Information Technology Management in the Shidler College of Business. Interdisciplinary Ph.D. program in Information and Communication Sciences. Introductory statistics in education and social sciences. Topics include probability distributions; sampling distributions; hypothesis testing using t-tests, correlation, simple regression, ANOVA; and applications in research. (Meets PhD common inquiry methods requirement or elective.)
• University of Hawaii The Department of Information and Computer Sciences and the Library and Information Science Program in the College of Natural Sciences, the School of Communications in the College of Social Sciences, and the Department of Information Technology Management in the Shidler College of Business. Interdisciplinary Ph.D. program in Information and Communication Sciences. The analysis and interpretation of behavioral science data using common statistical software packages. (Crosslisted as SW 652).
• University of Hawaii The Department of Information and Computer Sciences and the Library and Information Science Program in the College of Natural Sciences, the School of Communications in the College of Social Sciences, and the Department of Information Technology Management in the Shidler College of Business. Interdisciplinary Ph.D. program in Information and Communication Sciences. Advanced application of general linear model to complex problems of data analysis. Relation of analysis of variance and covariance to regression analysis. Non-linearity and treatment of missing data. Class requires basic statistics.
• University of Hawaii The Department of Information and Computer Sciences and the Library and Information Science Program in the College of Natural Sciences, the School of Communications in the College of Social Sciences, and the Department of Information Technology Management in the Shidler College of Business. Interdisciplinary Ph.D. program in Information and Communication Sciences. Theory and method of factor analysis and related methods of multivariate analysis.
• University of Hawaii The Department of Information and Computer Sciences and the Library and Information Science Program in the College of Natural Sciences, the School of Communications in the College of Social Sciences, and the Department of Information Technology Management in the Shidler College of Business. Interdisciplinary Ph.D. program in Information and Communication Sciences. Multivariate forms of multiple linear regression, analysis of variance and co-variance. Multiple discriminant analysis, canonical correlation, and principal-components analysis are discussed.