Type I error is known as rejecting the null hypothesis whenin fact it is true (false positive). Type II error on the other hand is knownas the null hypothesis not being rejected when in fact the hypothesis is true.Both type I and type II errors should be a concern to researchers because it isvery hard to detect and cannot be avoided. Researchers do have a chance of decreasingthese type of errors if they decided to make their studies with a much moresmaller sample size.

A real life example would be when patients are taking an HIVtest that has an accuracy rate of 99.9%. This implicates that the tests wouldnot give a false answer. But, as we are aware tests might show a false negativereading which is why duplicate tests are required. Type I error can be seen inthis case by stating that the null hypothesis is that the patient is not HIVpositive. The hypothesis would actually state that the patient does carry thevirus but due to a type I error it would indicate that the patient has thevirus when they do not. Therefore, this would cause a false rejection of thenull hypothesis. Type II error in this case would indicate that the patient isfree of HIV when they are not. The type II error in this case is more seriousbecause the null hypothesis has been wrongly rejected causing it to be adangerous diagnosis.


When testing a hypothesis there are two possibilities, typeI (having an effect) or type II (having no effect) (Field, 2012).  Type Ierror is equivalent to a false positive, and a type II error is a falsenegative.  A false positive is when a test is performed and shows aneffect, when there is none. A false negative is the opposite, when a test isperformed and shows no effect, when in fact there is an effect (Andale, 2015).

An example of Type I and Type II error in the real worldwould be in a study using pre-employment assessments to accurately predicthiring suitable and productive employees.  Type I error in the study wouldbe hiring applicants that are inapt (hiring an applicant you should haverejected). Type II error would result in the denial of an applicant that mayhave been a good fit for the position (rejecting an applicant you should havehired).  From this hypothetical study, it is clear that type I error canbe more damaging in this type of situation because the employer is hiring anapplicant with potential red flags. Hiring someone that may not have the properqualifications, is emotionally unstable, etc. could have a devastating effecton the company and its employees.  A type II error is more ideal in thissituation because it is a false negative so this selection error usually goesunnoticed when compared to a type I error. In general, applicants selected fromthe type II error pool are less likely to have a negative impact on thecompany; however, the employer could miss out on a great hire.

Leave a Reply

Your email address will not be published. Required fields are marked *