Jump to content

Mann Whitney U Test


JoeT22

Recommended Posts

I'm doing my psych ia right now and i remember my teacher mentioning something like you must include or use a test (inferential stats), and one of the test that my team has written down to use was the mann whitney U test. 

 

I've been looking online and researching about it and i tried putting in my own scores and data, it just gave me the central tendency and dispersion stats... i saw on some pdfs that the teacher had given me about some p value, or z score and the critical U value.. but i'm completely confused and i don't really understand it. could anyone explain these to me please?

 

What is, or how do i properly use the mann whitney U test and how do i incorporate it into my psych ia?!

 

ps. quick help pls? and reply soon i hope! my ia is due in just about a week :(

pss. this is my very first forum.. i'm not sure if i'm using or doing it correctly :/

 

Thank you so much!

Link to post
Share on other sites

I used the Mann Whitney U test in my IA, and you use it when your experiment is an 'independent measures' design, which means that the 2 groups you tested consisted of different participants. i.e. the people in group 1 were different to the people in group 2. In some experiments, the same participants are used in different situations and they wouldn't use this test. Here is a website that explains it: https://statistics.laerd.com/spss-tutorials/mann-whitney-u-test-using-spss-statistics.php

 

To do my calculations, I just used an online calculator because as far as I know, you don't have to state in your paper how you calculated your

results, you just have to say what they were. This one is pretty simple to use: http://www.socscistatistics.com/tests/mannwhitney/default2.aspx

 

The most important factor in your results is the p value: all you have to know is that if the p value calculated is less than 0.05 then your results are statistically significant, which means that basically your independent variable influenced your dependent variable. If the p value is more than 0.05, then your results are not statistically significant, and you can't therefore conclude that your IV influences your DV.

 

Another thing you need to know is if your experiment is 'one tailed' or 'two tailed'. A 'one tailed' test means that you have a directional hypothesis, which is a hypothesis that predicts that the IV will increase/decrease the DV - i.e. you know what to expect from the experiment. A 'two tailed' test means you have a non directional hypothesis, which is hypothesis that predicts that the IV will influence a change in the DV, but you don't know how (i.e. you can't predict if it will increase or decrease etc.). 

 

Examples: 

 

Directional Hypothesis: Boys will perform significantly better on the IB Psychology exam than girls.

Non-Directional Hypothesis: There will be a difference in performance on the IB Psychology exam between boys and girls.

 

Notice that in the second hypothesis, no clear distinction was predicted as in the first.

 

Last but not least, you need to know how to state your results. Your results should be stated in the appendix and this is how they should look like:

 

Mann-Whitney: = (insert value calculated from website), n1 = (insert number of people in group one), n2 = (insert number of people in group 2), = (insert value calculated from website), p (< or >) 0.05, one/two tailed.

 

I've attached my psychology IA which, if I remember correctly, received a 6. I hope this helps and good luck on your IA! :)

psychology coursework.docx

Edited by sameera95
  • Like 1
Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...