Abstract
Much experimental SE research involves testing a hypothesis regarding a relationship or difference between two variables. Typically, a null hypothesis (H0) of a zero correlation or no difference between the means of the two populations is posited. The standard way of reporting results from such statistical hypothesis testing is by presenting p-values or information about the rejection or acceptance of H0.
Chapter PDF
Similar content being viewed by others
Keywords
- Median Effect Size
- Statistical Hypothesis Testing
- Effect Size Measure
- Effect Size Reporting
- Zero Correlation
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Dybå, T., Kampenes, V.B., Sjøberg, D.: A Systematic Review of Statistical Power in Software Engineering Experiments. Information and Software Technology 48(8), 745–755 (2006)
Kampenes, V.B., et al.: A Systematic Review of Effect Size in Software Engineering Experiments. Simula Research Laboratory, work in progress.
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this chapter
Cite this chapter
Dybå, T. (2007). The (Practical) Importance of SE Experiments. In: Basili, V.R., Rombach, D., Schneider, K., Kitchenham, B., Pfahl, D., Selby, R.W. (eds) Empirical Software Engineering Issues. Critical Assessment and Future Directions. Lecture Notes in Computer Science, vol 4336. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71301-2_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-71301-2_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71300-5
Online ISBN: 978-3-540-71301-2
eBook Packages: Computer ScienceComputer Science (R0)