RSS

“Why is reliability important?”

14 Oct

I think there are several reasons why reliability is important, not only in the real world but also in statistics, before I go into more depth, first I need to define the term reliability – it refers to which a measure is stable or consistent and produces similar results when administered repeatedly, behaviour is one of the many examples of a measure.

I will address the reasons in terms of quantitative and qualitative data. While for qualitative results, reliability is elected through the use of statistics, such as the SD; for quantitative results, reliability can be consistent in subsequent tests.  I do not think that reliability is appropriate and does not play an important role in conducting qualitative studies, as these kind of studies focusing on the value and interpretations of experience by the participant. This can be backed up by Caroline Stenbacka, obligated by the complexion of qualitative studies, rather than explaining human experience, they aim at understanding it, which make the reliability of qualitative research difficult to assess.

However on the other hand, for researchers, whether the same measurement process yields the same results is a rather important aim, as this proves and assure them how their results can be as consistent and stable, and can be replicated in the future by others. Poor reliability degrades the precision of measurement and reduces researchers’ ability to keep track on the changes in measurements in studies, and this is why it is important to have reliable results. For example, when carrying out a study that might possibly lead to a theory, however this can be rejected or criticised due to the different inconsistent results that were shown under the same procedure. For Freud’ study, his “Little Hans” case study cannot be reliable if the study was repeated, there is no guarantee that same results could be done under the same condition, however the enrich data could be useful, hence Freud is a well know psychologist even in the 21st century. At this point, I do not think that reliability is that important as it turns out to be in the sense of qualitative data. 

In conclusion, Stenbacka (2001) has suggested that “… a good quality research when reliability is a concept to evaluate quality in quantitative study with a purpose of explaining while quality concept in qualitative study has the purpose of generating understanding …”. This makes me think that the use of reliability has now becoming onto an even more important, and leading role in terms of quantitative results, this has never really strikes me until now. Once people know how reliable research is, it can be helpful for further development of future research, it is also applicable to the real world and can be used widely in different fields, such as educations.

Reference:

http://www.medicine.mcgill.ca/strokengine-assess/definitions-en.html

http://www.encyclopedia.com/topic/Qualitative_Methods.aspx

Advertisements
 
6 Comments

Posted by on October 14, 2011 in Uncategorized

 

6 responses to ““Why is reliability important?”

  1. psuc9d

    October 19, 2011 at 10:17 am

    Hello 🙂

    Your blog was easy to read and very interesting,

    One criticism I would have to make if any, is that reliabilty is needed sometimes in qualitative data, although sometimes it is not needed, qualitative studies still need to be trustworthy in order for them to be credited. I know that reliability is used more effectively when using quantitative research studies, however, qualitative studies still need to be critically evaluated in terms of reliabilty and validity. ”To ensure reliability in qualitative research, examination of trustworthiness is crucial. Seale (1999), while establishing good quality studies through reliability and validity in qualitative research, states that the “trustworthiness of a research report lies at the heart of issues conventionally discussed as validity and reliability” Taken from, http://www.nova.edu/ssss/QR/QR8-4/golafshani.pdf

    I would also add that reliabilty is used in qualitative data but more deeply in the form of ‘dependability’, which is pratically the same thing.

    Happy blogging 🙂

     
  2. saspb

    October 26, 2011 at 3:00 pm

    Hey, really enjoyed reading your blog – some interesting views on the topic of reliability. its hard argue an opposing view on the topic.. as its effectively impossible to suggest that reliability isnt important! all i could suggest that is that quotes from Hyler, Williams, and Spitzer, 1982 (Hyler, S., Williams, J., and Spitzer, R. (1982). Reliability in the DSM-III field trials. Archives of General Psychiatry, 39,1275-1278) could act as another piece of supporting evidence for your blog.. When the DSM was revised in the 1980s it was said that there was “far greater reliability than had previously been obtained with DSM-II”. The fact that the idea of even stronger reliability was met with such positivity and encouragement would suggest the importance of reliability. In this particular example – in terms of diagnosing mental disorders. But of course reliability can be applied to all areas of psychology, particular in qualitative studies (as suggested as above) well done!

     
  3. poeywycheung

    October 28, 2011 at 8:02 pm

    Hi 😀
    I like you blog because it is one of the non-essays like blog I’ve read.
    And you might like to mention a bit about validity because these two ideas are actually linked together. And for a test or research or just like the quantitative and qualitative research or data that you have mentioned, it is essential for it to be both valid and reliable. That validity is measuring what the test intend to measure. Before a test to be valid, it is very important that to make sure it is reliable as well. So you could state like without reliability, a test could not be valid. (It would support your title, why is reliable so important?)

    This is a link to a video(that I just used in my blog as well :P) talking about why is reliability so important ?(to the businesses) http://www.youtube.com/watch?v=dglzO-pzN2c that you could mention reliability is important to our normal daily life as well as researches.

    Overall, it was a good blog, and I look forward for the next ones. 🙂

     
  4. rgjblog

    October 28, 2011 at 11:18 pm

    Hi there, I enjoyed reading your blog!
    I like how you split up reliability for both quantitative and qualitative data. Where you have put, reliability isn’t as important for qualitative data, it would be good here to say why it isn’t. For example when using a qualitative method such as a case study, you cannot gain reliability. This is because case studies are usually found by a single psychologist and one cannot really repeat a case study with the same conditions to see if you gain the same results, as each case is unique. Usually you cannot put a participant in the same conditions, as it would be unethical. Case studies of feral children such as Genie, where a child has lived in unthinkable conditions, such as being locked in a room, being neglected, beaten, not fed properly, cannot be repeated. Here is a link of the case study of Genie: http://www.english.iup.edu/mmwimson/Syllabi/721/Genie.htm

    Where do you draw the line of reliability? When is research classed as reliable and when is it not? Liam Healy cites that “Some argue that an acceptable reliability coefficient is 0.70” whereas “short-term equivalence (two week test-retest) between alternate-forms of the same measure should be in the range 0.65 – 0.80, the same-form retest should be in the range 0.75 to 0.90”. Here is a link, which explains that within psychology, there isn’t a universally accepted specific coefficient: http://www.psychometrics.co.uk/reliability.html

    You could add that reliability is important if a researcher wants to publish their research in a journal such as the British Journal of Psychology (BJP). In order for research to be published in the BJP, research must past the criteria of the peer reviewing body. Such criteria include research being reliable, being retested, being valid etc. By reading an article in the BJP you can trust the research more than say if the research was published in the Daily Mail.

    I know that the blog is about, is reliability important, but I don’t think you can talk about reliability without mentioning validity. As the two often impact on each other and not always separated into two distinct factors. Another important aspect, which you could have touched on is, a researcher’s data has to first be reliable before you can conclude that their procedure is valid. I’m not saying reliability cause validity (neither does validity result in reliability), but without reliability you cannot conclude whether the research is valid, which then results in the research looking poor. Who is going to trust data that is not reliable and you don’t know whether it is valid or not?

    Finally you could conclude by saying, yes reliability is important in quantitative methods of research, however just because a test, a study or questionnaire is reliable, you should bare in mind that this doesn’t assure that the data is significant or correct. A researcher may repeat trials over and over again and get the same results, however, this may be because in every trial they used the same instrument that had a fault in it. Here the results are reliable, but they should not be used as evidence to support the research hypothesis.

    Great blog, it was a hard topic to discuss!

     

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 )

Google+ photo

You are commenting using your Google+ 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 )

Connecting to %s

 
%d bloggers like this: