# Data Analysis in Management

- Credits: 5
- Ending: Examination
- Range: 2P + 2C
- Semester: winter
- Year: 2
- Faculty of Business Management

## Teachers

## Included in study programs

**Teaching results**

Knowledge:

• The student will acquire in-depth knowledge of application procedures and the correct choice of specific analytical methods, implemented through freely available open source software that are used in successful companies. This will be reflected in his practical knowledge of applied management research of internal and external company environment.

Competence:

• In knowledge of common statistical methods, ability to apply them and to be adequately choose the right method for the problem.

• In understanding the structure, format and content of information provided by management analyses, scientific articles, research reports commonly used in modern organizations managed on the basis of data, knowledge and know-how.

• To be able to create a complete proposal for obtaining new primary data from internal (corporate) and external sources, successfully implement this proposal in the field and bring to the management the required structured information as a basis for decision-making. Subsequently, propose steps and procedures of recommendations based on the results of the analysis.

• He will gain orientation and understanding of the topic to such an extent that he will subsequently be able to search for and study new methods, apply them and understand their results and interpret them correctly.

Skill:

• Install open source statistical software and prepare the file and data in the required structure for analysis, then select the right analytical method / test to apply to solve a specific business problem and then be able to run a wide range of relatively demanding analytical / statistical analysis, set them up specific parameters and conditions, understand the results, know how to interpret them correctly and write them in an internationally accepted standard form.

• They will acquire skills that will allow them to find a new statistical / analytical method, study its application, interpretation of results and then use it in practice.

• Successfully masters the process of identifying literature related to the problem.

• The relationship between the methodology used and the possibilities of subsequent analysis and the output of the analysis. When research is needed and when we can rely on existing information.

• The process of identifying and correct definition of the problem. Determining the type of analysis, determining variables, setting research goals, questions

**Indicative content**

Thematic definition of lectures:

1. The importance of data and analysis for the creation of information and subsequent knowledge as a basis for quality decision-making and for the success of the company.

2. Scientific theory and applicable practical significance of theory.

3. Population, sample, probability, sampling, probability distribution.

4. Creating new specialized questionnaires and other measuring tools according to scientific principles and using existing ones.

5. Presentation of practical recommendations and skills needed to search for data in scientific databases and professional databases.

6. Assumptions and hypotheses created from them.

7. Regression analysis: hierarchical and logistical, conditions for application, practical usage.

8. Structural equation modeling (SEM). Explanation of the method.

9. Mediation as an extension of regression analysis.

10. Moderation as an extension of regression analysis.

11. Reduction of the number of variables using exploratory factor analysis.

12. Confirmatory factor analysis (CFA).

13. The importance of systematic studies and meta-analyzes as carriers of knowledge.

Thematic definition of exercises:

1. Presentation of the installation of current versions of open source software used for statistical / data analysis (JAMOVI, JASP and PSPP).

2. Data distribution.

3. Calculation of effect size by Cohen's d, Person's r for parametric and nonparametric tests.

4. Probability of phenomena and its distribution.

5. Measurement of relationships between variables according to the type of variable (variations of relationships between types of variables.

6. Regression analysis and conditions for the application of regression analysis (multicollinearity, homoskedasticity, etc.) and overall validation of regression models.

7. Hierarchical regression analysis creation of hierarchical regression models.

8. Structural modeling.

9. Mediation as an extension of regression analysis and its calculations.

10. Moderation as an extension of regression analysis and its calculations.

11. Exploratory factor analysis (EFA).

12. Confirmatory factor analysis (CFA).

13. Meta-analysis.

**Support literature**

Basic literature:

1. FIELD, Andy. Discovering statistics using IBM SPSS statistics. Thousand Oaks : SAGE, 2013. 952 strán. ISBN 9781446249178.

2. PERVEZ, Ghauri – GRØNHAUG, Kjell – STRANGE, Roger. Research methods in business studies. Cambridge : Cambridge University Press, 2020. 300 s. ISBN 978-1108708241.

3. ADAMS, John - HAFIZ TA, Khan – RAESIDE, Robert. Research methods for business and social science students. India : SAGE Publications, 2014. 304 s. ISBN 978-8132113669.

Supplementary literature:

1. BOWERMAN, Bruce. Business Statistics in Practice: Using Data, Modeling, and Analytics. New York : McGraw-Hill Higher Education, 2016. 912 s. ISBN 978-1259549465.

2. MOORE, David et al. The practice of statistics for business and economics. New York : WH Freeman, 2016. 767 s. ISBN 978-1319109004.

**Syllabus**

Thematic definition of lectures: 1. The importance of data and analysis for the creation of information and subsequent knowledge as a basis for quality decision-making and for the success of the company. Creation of information from data and subsequent knowledge from information and modern management based on data analysis. Transforming ideas into a research problem. 2. Scientific theory and applicable practical significance of theory. Research categorization: exploratory research, descriptive research, causal research. Summaries of research outputs as a systematic review study and meta-analysis. Experimental, quasi-experimental and correlation design of research, design of case studies. Action - based research. Research plan. Experimental design. 3. Population, sample, probability, sampling, probability distribution. Basic types of sampling and the differences between them: random sampling, deliberate sampling, snowball sampling, quota, proportional, and stratified sampling. Data distribution. Central limit theorem. Selection error, systematic error. Probability of occurrence of phenomena and its distribution. 4. Creating new specialized questionnaires and other measuring tools according to scientific principles and using existing ones. Asking questions. Interview principles and possible biases. Group interviews and focus groups. In-depth interview. Telephone interview. Internet surveys. Qualitative research. Content analysis. Observation. Free associations. Determination of sample size. Pilot research. Construct, criterion, predictive, content, ecological validity. Objectivity at collection and objectivity of the measuring tool. 5. Presentation of practical recommendations and skills needed to search for data in scientific databases and professional databases. Internal and external data. Theoretical anchoring of the problem. 6. Assumptions and hypotheses created from them. Principles and logic in verifying the null hypothesis. Practical recommendations for creating and formulating hypotheses, common mistakes. Significance level in case of hypotheses. 7. Regression analysis: hierarchical and logistical, conditions for application, practical usage. Validation of regression analysis. Comparison of regression models. 8. Structural equation modeling (SEM). Explanation of the method. 9. Mediation as an extension of regression analysis. Explanation of basic principles of mediation. The difference between mediation and moderation. Graphic representation of mediation models. Direct, indirect and overall effect. Presentation and graphical interpretation of results. 10. Moderation as an extension of regression analysis. Choice of mediation or moderation according to theoretical and logical expectations and assumptions. Creation of independent moderation models and their combinations with mediation models. Model evaluation and model interpretation. 11. Reduction of the number of variables using exploratory factor analysis. Exploratory factor analysis (EFA). Factor identification process, factor loading, scree plot. 12. Confirmatory factor analysis (CFA). Verification of existing measuring instruments using confirmatory factor analysis. 13. The importance of systematic studies and meta-analyzes as carriers of knowledge. Comparison of these types of studies. Advantages of meta-analysis over systematic study. Data preparation for meta-analysis. Thematic definition of exercises: 1. Presentation of the installation of current versions of open source software used for statistical / data analysis (JAMOVI, JASP and PSPP). Description and descriptive analysis of quantitative data. PivotTables, chi square distribution. Graphic display. 2. Data distribution. Shapiro-Wilk test, Kolgomorov Smirn test, graphical presentation of data distribution. Bar graphs with confidence intervals, definition of the whole data set and determination of the examined sample. Investigation of phenomena in homogeneous and small data files and vice versa in large and heterogeneous data files. Suitable methods and their limits 3. Calculation of effect size by Cohen's d, Person's r for parametric and nonparametric tests. Interpretation of effect size. Mutual conversion. 4. Probability of phenomena and its distribution. Practical calculation. Statistical versus material significance. Error α, error β. 5. Measurement of relationships between variables according to the type of variable (variations of relationships between types of variables: nominal with nominal, ordinal, interval, etc.) and according to the normality of data distribution. Relationships measured by the following methods (Cramer V, Lambda, Phi, Gamma, Eta, Spearman's rho). 6. Regression analysis and conditions for the application of regression analysis (multicollinearity, homoskedasticity, etc.) and overall validation of regression models. Durbin-Watson test, Cook distances, residual graphs. Calculation of multicollinearity. 7. Hierarchical regression analysis creation of hierarchical regression models. The process of creating models and subsequent comparison of models according to specific parameters. Logistic regression analysis for: a) two outputs, b) n outputs, c) with ordinal output. 8. Structural modeling. Explanation of principles, creation of structural models, evaluation and comparison of models according to the its parameters. Design and preparation of a structural model. 9. Mediation as an extension of regression analysis and its calculations. Graphic representation of mediation models. Direct, indirect and total effect, calculation and reporting. Presentation of results and graphical interpretation of results. 10. Moderation as an extension of regression analysis and its calculations. Choice of mediation or moderation according to theoretical and logical expectations and assumptions. Creation of combined mediation and moderation models. Model evaluation and model interpretation. 11. Exploratory factor analysis (EFA). Selection of method parameters based on theoretical assumptions. Selection of a suitable method of factor extraction. Possibilities of selection of rotation factors (Varimax, Quartimax, Promax, Oblimin, Simplimax) Bartett's sphericity test, KMO test, scree plot. 12. Confirmatory factor analysis (CFA). Difference between EFA and CFA. Model parameters and their interpretation as: chi square test, comparative fit index (CFI), Tucker Lewis Index (TLI), Root mean square error of approximation (RMSEA), Akaike's Information Criterion (AIC). 13. Meta-analysis. Meta-analysis calculation and its interpretation. Meta-analysis based on correlation coefficients, means (differences in means) effect sizes. Presenting the results of meta-analysis.

**Requirements to complete the course**

40 % seminar work, 60 % written exam

**Student workload**

130 hours (participation in lectures 26 h, participation in seminars 26 h, preparation for seminars 26 h, preparation for credit paper 20 h, preparation for exam 32 h)

**Language whose command is required to complete the course**

Slovak

Date of approval: 11.03.2024

Date of the latest change: 14.05.2022