Type One and Type Two Errors…

When testing a hypothesis there are two possibilities: an effect and no effect. Accuracy is the most important element in psychology, therefore we only accept a result when there is 95% confidence in the effect and only 5% chance results could occur if there was no effect. However even if we’re 95% confident, there is still a chance we can get it wrong! Type One Error and Type Two Errors are the two mistakes we can make:

  1. A Type One Error is when we believe that there is an effect but in reality there isn’t one, this is known as the α level. It is when we wrongly accept the experimental hypothesis and reject the null hypothesis, when it is actually true. This is the worst type of error because false conclusions could do lots of damage e.g. incorrect diagnoses.
  2. A Type Two Error is the opposite; it is when we believe there is no effect when in reality there is. This is most common with small test statistics. The maximum acceptable probability of a type two error is 20%, this is called the β level. In summary, a type two error occurs when we wrongly reject the experimental hypothesis, and accept the null hypothesis when it is false. This is the best type of error to make because no damage is done, the only disadvantage is that nothing good comes of it either e.g. new findings.

An illustration of type one and type two errors in the real world is Rosenhan’s on being sane in insane places study (1973). The study aimed to test whether psychiatrists could reliably diagnose whether a person was insane or not. There was two parts to this study:

  • In the first part of the study, pseudopatients arranged an appointment at the hospital and pretended to be insane. These patients were admitted to the psychiatric ward and labelled as insane, this is an example of a type one error because they were being diagnosed incorrectly.
  • In the second part of the study, Nurses were told that pseudopatients would be trying to enter the hospital however this was a lie. Because nurses believed pseudopatients would enter the hospital, they failed to diagnose many patients that were really insane.  A type two error was made because they failed to diagnose individuals.

From both parts of Rosenhan’s study, it is clear that both type one and type two errors can have a big impact in the real world. But is it more damaging to wrongly diagnose an individual or to fail to diagnose an individual? From the study it is clear that type one errors are the most damaging; diagnosing an individual wrongly can cause all sorts of problems such as hospitalisation, administration of medication and labelling, all of which have a profound negative impact on an individual’s life. Failing to diagnose an individual can have negative impacts for the individual and society, but this impact is not as negative as wrongly diagnosing a person is, as the undiagnosed individual can make another appointment for further diagnosis.

In conclusion, when considering Type One and Type Two Errors, I believe that type one errors are the most damaging in both research and real life because they cause harm rather than just failing to do good.

References:

Andy Field Textbook – Discovering Stats Using SPSS – 3rd Edition

Rosenhan, D.L. (1973) On being sane in insane places. Science, 179. 250-58

Advertisements

41 thoughts on “Type One and Type Two Errors…

  1. baw8 says:

    i agree that type one error is more harmful to individuals as no one likes to be blamed for something they have not done. in research it is the same saying an effect has occurred when it has not can cause many problems such as other researcher trying to repeat the experiment hoping to find the same result which is a waste of the researcher time and money if money is involved as they will not find what they want to find. i feel though that type two error is still bad as failing to report an effect when there is one can be harmful.like in your example if a patient is not diagnosed as insane that person could end up with really problem as well as their diagnosis was not identified. i feel that both type one and type two errors are as important as each other.

  2. saspb says:

    Hey, this was a really nicely written blog – very clear and easy to follow. It’s hard to find anything to argue against as such as this isnt particularly a topic of opinion.
    Both Type 1 errors and Type 2 errors are factors that every researcher must take into account when conducting a study and whilst replication can minimise the chances of these errors occuring, this is not always possible : for example in observational methods or of course quasi-experiments, these are awfully difficult to repeat.
    Some statitions are also now adopting a Type 3 errors which is where the null hypothesis was rejected for the wrong reason. In an experiment, a researcher will firstly suggest a hypothesis and perform their research, after analysing the results statistically, the null is rejected.The problem being that there may be some relationship between the variables, but it could be for a different reason than stated in the hypothesis.

    http://www.experiment-resources.com/type-I-error.html#ixzz1n1QoI1F7

  3. psuc3d says:

    Hello, I really enjoyed your blog! I would just like to mention that although I do think that Type I errors are pretty bad, I don’t think that Type II errors simply fail to do something good. To take a real life example, if a jury were making a decision on the guilt/innocence of a person and made a Type II error, they would be letting the criminal go and walk free despite being guilty. In this case i think that Type II errors are worse but in the example you gave, I completely agree that Type I would have been more dangerous. I think that perhaps the seriousness of the error is dependent on the situation. Think link http://intuitor.com/statistics/T1T2Errors.html explains really well the both types of error within the Justice System. Looking forward to your next blog!

  4. psud63 says:

    Really good explanation of the differences between type 1 and type 2 errors. I do agree with you that type 1 errors are more harmful in research and in the real world as they have the worse implications. You could have possibly included how researchers can reduce the chances of a type 1 and type 2 error occurring.
    Type 1 errors can be avoided by reducing the significance level; e.g if a researcher lowers the significance level, from say 0.05 to 0.01, the chance of the results occurring from chance and causing a type 1 error falls from 5% to 1%.
    Type 2 errors are the opposite and can be avoided by increasing the significance level in order to avoid the chance of rejecting a true alternative hypothesis.

    http://www.investopedia.com/exam-guide/cfa-level-1/quantitative-methods/hypothesis-testing.asp#axzz1n1qjxeli

  5. fr4nw says:

    I agree that type I errors can be damaging, particularly when applied in real world scenarios such as incorrectly diagnosing somebody and the effect this could have on someone’s life. Therefore I can see how this would relate to areas such as mental health and how individuals are diagnosed using the DSM (IV) manual and so the diagnostic tools in this manual would need to be backed up by research that had little chance of a type I error. However as it is important that we find appropriate treatment for individuals with mental health disorders, so that they do not harm themselves or others, is it not important that we do not dismiss someone who has a mental disorder? This could be possible if research showed a characteristic / behaviour to not be linked to a mental heath disorder when in reality it is. As a result I feel that making sure individuals do not go undiagnosed and that they receive appropriate treatment is just as important and therefore making a type II error is just as damaging as making a type I error.

  6. psud22psych says:

    Very well done blog, I presume the main aim of the blog was to describe and compare type one and type two errors to see which is worse. I agree with the conclusion that a type 1 error is worse especially in the short term and can cause a lot of damage. A way to expand though could’ve been to describe methods on how to avoid committing this cardinal sin 😉 For example , Nosek, Banaji and Greenwald (2002), suggested that especially with regard to internet research rigorous controls should be put in place to remove extraneous variables which reduces the chance of a type 1 or 2 error as you are more likely (but not guranteed) to get more variance in your scores.

  7. intangible says:

    I was basically wondering if you ever thought of switching the design of your website? Its very well written; I enjoy what you have got to say. But maybe you could add a little more in the way of written content so people might connect with it better. You have got an awful lot of wording for only having one or two photographs. Maybe you can space it out better?

  8. I have got one recommendation for your web site. It appears like at this time there are a few cascading stylesheet issues while opening a number of web pages inside google chrome as well as internet explorer. It is working okay in internet explorer. Probably you can double check this.

  9. like i said says:

    Dude. This blog is amazing! How do you make it look like this ?

  10. Just to let you know your site appears a little bit strange on Firefox on my netbook with Linux .

  11. going here says:

    This blog has a lot of very helpful information on it! Thanks for informing me!

  12. go here says:

    fairly helpful stuff, in general I imagine this is worthy of a book mark, many thanks

  13. I have got one idea for your website. It looks like right now there are a handful of cascading stylesheet issues while opening a number of web pages in google chrome and safari. It is functioning alright in internet explorer. Perhaps you can double check this.

  14. this month says:

    This is often a fantastic site, would you be interested in making time for an interview about just how you made it? If so e-mail me personally!

  15. Do you might have a spam problem on this website; I also am a blogger, and I was asking yourself your situation; we now have created some nice approaches and we are looking to trade options with other people, be sure to fire me an e-mail if serious.

  16. The look for your site is a little bit off in Epiphany. Even So I like your website. I might have to use a normal web browser just to enjoy it.

  17. How do you make your blog look this cool. Email me if you can and share your wisdom. !

  18. I have got one suggestion for your webpage. It appears like there are a few cascading stylesheet problems while launching a number of web pages inside google chrome and firefox. It is running fine in internet explorer. Probably you can double check this.

  19. I appreciate your wp design, where did you get a hold of it?

  20. I Am Going To have to return again whenever my course load lets up – however I am getting your Feed so i can go through your web blog offline. Cheers.

  21. It seems to me that this web site doesnt download in a Motorola Droid. Are other folks getting the exact same issue? I enjoy this blog and dont want to have to miss it any time Im gone from my computer.

  22. Even though I genuinely like this post, I believe there was an punctuational error close to the end from the third sentence.

  23. How do you make a site look this sick!? Email me if you can and share your wisdom. Id be thankful.

  24. You should really control the responses listed here

  25. I tried viewing your website on my mobile phone and the page layout does not seem to be correct. Might want to check it out on WAP as well as it seems most mobile phone layouts are not really working with your site.

  26. If you dont mind, exactly where do you host your web site? I am looking for a very good host and your webpage seams to be fast and up almost all the time

  27. Im having a little issue. I cant get my reader to pick up your rss feed, Im using yahoo reader by the way.

  28. Have you given any kind of consideration at all with converting your current site in to Chinese? I know a small number of translaters here that might help you do it for no cost if you want to contact me personally.

  29. Im having a small issue. I cant get my reader to pick up your feed, Im using google reader by the way.

  30. I believe one of your ads initiated my internet browser to resize, you may well want to put that on your blacklist.

  31. silver hair says:

    How did you make your blog site look this cool. Email me if you get the chance and share your wisdom. Id appreciate it.

  32. Just to let you know your web-site appears a little bit unusual on Firefox on my computer with Linux .

  33. Almost all of the remarks on this website dont make sense.

  34. When I initially commented I clicked the “Notify me when new comments are added”
    checkbox and now each time a comment is added I get several emails with the same comment.

    Is there any way you can remove me from that service? Thanks!

  35. back surgery says:

    Hello! I just wanted to ask if you ever have any issues
    with hackers? My last blog (wordpress) was hacked and I ended up losing several weeks of hard
    work due to no data backup. Do you have any methods to protect against hackers?

  36. Evelyn says:

    You post interesting content here. Your website deserves much more visitors.
    It can go viral if you give it initial boost, i
    know useful service that can help you, simply search in google:
    svetsern traffic tips

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: