Research Tips
Replicating Research
Repeating all or part of a previously conducted research project has significant benefits:
- Replication, like triangulation, increases confidence in results. Standard tests for statistical significance allow for a small possibility that results, such as differences between groups, occurred by chance. While the probability of this is normally set to be quite low (typically 1 in 20 for market research), the likelihood of something that appears to be a significant result but isn’t occurring by chance in two consecutive studies is much lower still (1 in 400 if the level for each individual study is set to 5%).
- Replicating research periodically over time makes it possible to identify time-based trends.
- Replicating a given piece of research with a different population (for example, customers in a different geographic area) makes it possible to see the extent to which the results generalize to other populations.