OPF:MMENKSTZ Statistical Data Processing - Course Information

MMENKSTZ Statistical Data Processing

Extent and Intensity

0/0. 5 credit(s). Type of Completion: zk (examination).

Guaranteed by

prof. RNDr. Jaroslav Ramík, CSc.
Department of Informatics and Mathematics – School of Business Administration in Karvina

Prerequisites (in Czech)

K absolvování předmětu nejsou vyžadovány žádné podmínky a předmět může být zapsán nezávisle na jiných předmětech.

Course Enrolment Limitations

The course is offered to students of any study field.

Course objectives

Following the subject Statistics at bachelor's level to provide further explanation of mathematical statistics, the main findings of this theory and basic statistical methods. Present subject with regard to the application of the economic environment. Get computer skills and learn how to deal with the statistical data using SPSS and Excel on a computer.

Syllabus

• 1. Analysis of variance (ANOVA) - One factor
  2. Analysis of variance - Two and more factors, nonparametric ANOVA
  3. Regression Analysis - One-dimensional, linear
  4. Regression Analysis - One-dimensional, nonlinear
  5. Regression Analysis - Multi-dimensional
  6. Regression Analysis - Multidimensional: Multicolinearity, heteroscedasticity, autocorrelation
  7. Basics of Time Series Analysis
  8. Trend analysis of time series
  9. Analysis of seasonal and random components of time series
  10. Exponential smoothing models of time series
  11. ARIMA models
  12. SARIMA models
  13. Forecasting of time series
  1. Analysis of variance (ANOVA) - One factor
  Independent and dependent factors, assumptions of analysis of variance with one factor. Procedure for the analysis of variance with one factor. The rate of dependence, determinative and correlation ratio.
  2. Analysis of variance - Two and more factors, nonparametric ANOVA
  Analysis of variance with two factors. Assumptions of ANOVA with two factors. Two-factor ANOVA without interaction and interaction. Kruskal-Wallis nonparametric ANOVA.
  3. Regression Analysis - One-dimensional, linear
  What is regression analysis (RA) - a simple, multiple, linear, nonlinear. The essence of simple linear RA - scatter diagram, regression, regression coefficients, adhesion, coefficient of determination, tests of hypotheses.
  4. Regression Analysis - One-dimensional, nonlinear
  Simple linear RA - basic types of nonlinearities, Törnquist curves and their applications in economics.
  5. Regression Analysis - Multi-dimensional
  Multiple linear RA - criterion, predictors, regression hyperplane, the coefficient of determination. Using the VRA for nominal predictors and correlation coefficients. Application examples of the economic area (marketing research).
  6. Regression Analysis - Multidimensional: Multicolinearity, heteroscedasticity, autocorrelation
  Population and sample regression function. Classical multivariate linear regression model. Multicollinearity and its causes. Heteroscedasticity, tests H-S (Park test, Bartley test) and its removal. Autocorrelation (sign test).
  7. Basics of Time Series Analysis
  Types of economic time series. Elemental characteristics of time series. Models of economic time series - decomposition, exponential smoothing, ARIMA.
  8. Trend analysis of time series
  Analytical methods for the determination of trends of time series: regression analysis (least squares method, maximum likelihood method). Synthetic methods: moving averages, exponential smoothing.
  9. Analysis of seasonal and random components of time series
  Analysis of seasonal component: models with constant seasonality with a step trend, with a linear trend. Models of proportional seasonality. Analysis of random component: statistical tests of random component using residues.
  10. Exponential smoothing models of time series
  Exponential smoothing models (simple, Holt, Winters model).
  11. ARIMA models
  Stochastic process and its stationarity. Fundamentals of ARIMA models: models AR, MA, I, ARIMA. Identification of ARIMA model using the autocorrelation function (ACF) and partial autocorrelation function (PACF). Calculation of ARIMA model, model verification, prediction of the ARIMA model.
  12. SARIMA models
  Identification of the SARIMA model using the autocorrelation function and partial autocorrelation function.
  13. Forecasting of time series
  The forecast ex-post and ex-ante, point and interval forecasts. Forecasting in linear regression models. Forecasting in ARIMA and SARIMA models.
  

Language of instruction

Czech

Further Comments

The course can also be completed outside the examination period.

• Enrolment Statistics (recent)
  
• Permalink: https://is.slu.cz/course/opf/winter2014/MMENKSTZ