It is humanly impossible not to make mistakes while analysing data. But identifying and rectifying them is what keeps you from landing in soup. Below is the list of the common mistakes made during data analysis
Cherry picking: It is quite often people end up making wrong inferences with half baked analysis. This happens when people select the results that fit their claim and ignore those that don’t.
Having a vague hypothesis: You cannot form data based on your predictions and theories. A vague hypothesis fails to define your interpretation and analysis of the data.
Correlation and Causation: More than often, correlation is treated as causation. It is one of the most tempting data pitfalls. It is not always necessary that two events are happening because of one another just because they are happening close to each other.
Cobra effect: This occurs when certain incentive results in unexpected negative consequences. Hence, it is important to make sure that no wrong behaviour is encouraged while setting the incentives.
Hawthorne effect: Also known as observer effect occurs when an act of monitoring someone results in the change of the person’s behaviour or productivity.
Gambler’s fallacy: It is a belief that because something has happened more frequently than usual, it’s less likely to happen in future and vice versa.
What are the most common data analysis mistakes you end up doing? Leave us a comment to learn more about data analysis.