1. SylabUZ
2. Faculty of Computer Science, Electrical Engineering and Automatics
3. winter term 2019/2020
4. E-business - First-cycle Erasmus programme
5. Fundamentals of business analytics

Generate PDF for this page

Fundamentals of business analytics - course description

Aim of the course

• expose students  to advanced quantitative and qualitative data analysis procedures
• develop skills of using statistical software in data analysis
• develop skills of analysing and forecasting time series

 

Prerequisites

Save changes

Data analysis fundamentals

Scope

Statistical software for business analytics. Elements of using JMP software: data tables; graphs; reports; scripts; formula editor; simulation techniques; descriptive statistics and statistical inference. Elements of using the SAS system: elements of the language; data step; data processing; proc step; global expressions; graphics; basic statistical procedures; debugging. Using Enterprise Guide. Fundamentals of using the R system: elements of R language, programming, data processing and visualization.

Analysis of dependence between quantitative variables. Linear regression model. Properties of least-squares estimators. Regression model diagnostics. Outliers, leverage points and influential observations. Transformations to achieve linearity. Logistic regression.

Analysis of variance. One-way analysis. F-test for ANOVA. Relations to regression analysis. Multiple comparisons. Two-way analysis.

Analysis for qualitative variables. Testing hypotheses for one variable. Testing uniformity. Testing independence for two random variables.

Random sampling from a finite population. Representative method. Estimators of population parameters for various sampling schemes.

Monte Carlo method. Generation of pseudo-random numbers. Estimation of distribution parameters using the Monte Carlo method. Permutation tests.  Bootstrap method.

Rank methods. Comparison of feature distribitions in two populations. Tests for pairwise comparisons. Rank tests for independence. Comparison of feature distributions in many populations. Rank methods for linear regression.

Dimensionality reduction methods. Principal component analysis. Factor analysis. Components defined by the user.

Time series analysis and forecasting. Aggregation and interpolation of time series. Exponential smoothing without seasonality. Confidence intervals for the forecasts. Exponential smoothing in forecasting for time series with seasonality. Exponential smoothing vs, parametric models AR, MA, ARMA, ARIMA. Models with hidden components.

 

Teaching methods

Lecture - conventional lecture.
Labs - laboratory exercises using SAS software.

Learning outcomes and methods of theirs verification

Outcome description	Outcome symbols	Methods of verification	The class form

Assignment conditions

Recommended reading

1. Daniel T. Larose (2008): Data Mining Methods and Models, Wiley-IEEE Press
2. Geoff Der, Brian S. Everitt (2015): Essential Statistics Using SAS University Edition, SAS Institute Inc., Cary, NC
3. Venkat Reddy Konasani, Shailendra Kadre (2015): Practical Business Analytics Using SAS, Apress, New York
4. Gregory Lee (2015): Business Statistics Made Easy in SAS, SAS Institute Inc., Cary, NC
5. Anders Milhøj (2013): Practical Time Series Analysis Using SAS, SAS Institute Inc., Cary, NC
6. Sandra Schlotzhauer (2009): Elementary Statistics Using SAS, SAS Institute Inc., Cary, NC

Further reading

Notes

Modified by prof. dr hab. inż. Dariusz Uciński (last modification: 11-12-2019 22:34)