This unit discusses two crucial steps in experimental research: data cleaning and hypothesis testing. Data cleaning is necessary to identify and correct or remove errors, inconsistencies, and formatting issues in the data collected. The cleaned data must be coded to be interpreted by statistical software, particularly for categorical variables. Hypothesis testing is a statistical analysis that involves testing assumptions about population parameters based on the research hypothesis. A null hypothesis and an alternative hypothesis are formulated, and statistical tests are performed to decide whether to reject or fail to reject the null hypothesis. The discussion in this unit highlights the importance of avoiding too many hypotheses in a single experiment, which increases the complexity and risk of design flaws. Finally, this unit discusses the types of errors in hypothesis testing, such as Type I and Type II errors, and their consequences. Type I errors are more severe than Type II errors as they may lead to a situation worse than the current one. Researchers need to be aware of these errors and their potential consequences when conducting hypothesis testing.
Lazar, J. , Feng, J. H., Hochheiser, H. (2017), Research methods in human-computer interaction: Morgan Kaufmann, 2017.
Rosenthal, R., Rosnow, R., 2008. Essentials of Behavioral Research: Methods and Data Analysis, third ed. McGraw Hill, Boston, MA.
Sauro, J., and Lewis, J. R., (2016). Quantifying the user experience: Practical statistics for user research: Morgan Kaufmann.