Reliability & Validitiy in Research

I hope you enjoyed these fun Santa facts, but have a think… 

Who measured the stats, where did they come from?

Are the findings valid and reliable?? (Ok, probably not as these stats are about an old man in a big red suit from the North Pole..)


Validity refers to whether or not the study is actually measuring what it is intending to measure (Field, 2009). Reaction time is a good example of a valid instrument of measurement, as reaction time intends to measure the time it takes a person to react, and it does exactly this! It would be useless to use a measurement of say an IQ test to try and measure the time it takes someone to react.

Two main types of validity to consider are: internal and external. Internal validity focuses on the researcher testing what they were meant to test, whereas external validity focuses on whether the findings can be generalized.

Other types of validity are:

construct validity introduced by Cronbach and Meehl (1955), construct validity focuses on the degree to which an instrument measures the variables being investigated.

content validity ensures that the method of measurement is reliable and actually measures what it’s supposed to measure.

face validity a type of content validity, ensures the instrument is suitable

predictive validity successful results from previous research predicts of the outcome of future experiments or tests.

*To ensure validity, instruments and methods used during research must first be reliable.*


The purpose of reliability is to show that any significant results found in a piece of research have not been found just by chance and they are more than a one-off finding. A reliable experiment is expected to produce the same results if the study is repeated by other researchers. If the experiment is constantly repeated and the results always appear to be different, the study cannot be considered reliable.

Reliablity and validity work together, if the study doesn’t measure what it is supposed to then the results cannot be accurate. And if the results cannot be accurate and reliable then the study cannot be valid.


4 thoughts on “Reliability & Validitiy in Research

  1. World of Statistics says:

    What an excellent example you have included to aid you in your discussion! I highly agree with you on the note that reliability and validity do indeed work together. In addition, speaking of reliability, take a look at this link: It states that 100% showed results. However, what it fails to disclose to us is the sample size. Therefore, how do we know if the ‘100%’ statistic is significant or not? As a result, it is questionable as to how reliabile this statistic is. Validity is also an important aspect in research because what is the point of conducting research when the findings cannot be generalised to the wider population (external validity)? After all, one of the main purposes of conducting research is to enable us to share our findings with the general population.

  2. exactestimates says:

    It can be argued by extremists in the individual differences approach to psychology that the idea of reliability is unsuitable to the study of humans. This is because they believe human behaviour to be too diverse, and results should not be generalised. They much prefer the case study methodology e.g. Thigpen and Cleckley whereby a complete and informing study is based around one person instead, and that this will be far more beneficial to an individual than a study that generalises their results to a larger population.

Leave a Reply

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

You are commenting using your 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