Data Analytics III

All None Speichern

• Good QUANTITATIVE question Clear, Focused, Allows the writer to take an arguable position but does not leave room for ambiguity, Avoids the "all-about" questions, Empirically addressable, SOmething that you are interested in or care about
• QUANTITATIVE methods Numbers & measurable. Answer questions on relationships with an intention to explain, predict, and control a phenomena. Functions: Identify a cause, quantify the effect of a cause, predict outcomes, explain, test, and refine theory or hypothesis.
• QUALITATIVE methods Data like words & observations --> may be unstructured. Used to answer relatively openended questions on experiences, interpretations, or complex processes. Functions: Understand, process, explore, interpret, create foundation for theory.
• HYPOTHESIS A proposed explanation/attemt to describe. Statement that is true or false. Can't say true/false, just accept/reject hypothesis.
• THEORY A statemenmt about HOW a set of constructs are related to each other explaining a broad phenomenon. ("how", "when", "why")
• CONSTRUCT / CONCEPT Abstract category in your theory which cannot be measured directly, e.g. "brand awareness".
• RESEARCH DESIGN About HOW data are collected and analysed
• Four main types of QUANTITATIVE RESEARCH DESIGNS Descriptive. Correlational. Quasi-Experimental. Experimental.
• Descriptive Explore the characteristics of samples and population. (What is)
• Correlational Explores the relationship between variables using statistical analyses. Snapshot of many variables at a single point in time, or by using repeated measures at different points in time. (what influences)
• Quasi experimental Focusing on cause-effect relationship among variables, without having the possibility to perform manipulation. (What influences)
• Experimental (also called: True experiment or Lab experiment) The researcher manipulate the independent variable --> Gets control of all variables except for the one being manipulated (indep.var). --> Able to observe variation occuring after the only manipulation. (What influences)
• CAUSALITY An important driver of research design.
• 3 conditions must be met for CAUSALITY: 1. The cause must PRECEDE (gå före) the effect. 2. The cause & effect should CORRELATE. 3. Aöö other explanations of the cause-effect relationship must be RULED OUT (tertium quid).
• CORRELATION Variables happens to have matching patterns.
• CAUSATION The value of Y depends on the value of X.
• Strengths of Quantitative methods - Viewed as scientifically objective and rational. - Useful for testing, validating and refining already constructed theories. - Fast analysis. - Replication.
• Weaknesses of Quantitative methods - Variability of data quantity. - Fairly narrow settings. - Be aware of 3 sources of biases (vinklar): you, the respondent, the method.
• LECTURE 2 :)

All None Speichern