Types of Error in Hypothesis Testing
According to Lazar, Feng, and Hochheiser (Lazar, 2017), significance testing is a technical process that involves contrasting a null hypothesis (H0) with an alternative hypothesis (H1) to determine the probability of the null hypothesis being true. However, all significance tests are at risk of Type I and Type II errors. Type I errors, also known as “false positives” or α errors, occur when the null hypothesis is mistakenly rejected despite being true. Conversely, Type II errors, also known as “false negatives” or β errors, occur when the null hypothesis is not rejected even though it is false (Rosenthal and Rosnow, 2008).
In general, Type I errors are considered more severe than Type II errors. Statisticians refer to Type I errors as “gullibility” mistakes, as they may lead to a situation worse than the current one. For instance, if a new medication is erroneously believed to be more effective than the current medication, patients may switch to an inferior medication. On the other hand, Type II errors are considered “blindness” mistakes that may result in missed opportunities to improve the current situation. In the medication example, a Type II error would mean that the test fails to identify the new medication as more effective than the current treatment, causing patients to miss out on a better treatment.
For further studying about type I and type II errors watch this video:
Lazar, J. , Feng, J. H., Hochheiser, H. (2017), Research methods in human-computer interaction: Morgan Kaufmann, 2017.