How do you know whether your findings are valid?

Hello ladies and gentlemen and welcome to the first post on my blog, this
week I will try and answer the question, “How do you know whether your
findings are valid?”
Without further ado, here we go.

First of all you need to ensure yourself that the instrument you are
using actually measures what it is set out to measure. If you are to measure how
long a distance is in centimeters, don’t use an instrument that measures inches
as the outcome would not be correct, and if someone were to repeat the
experiment the results would not be the same. Therefore, make sure you’re using
the correct instrument so that the outcome is valid.

Measurements can also only be valid if there are no other factors than
the ones that we are trying to measure. If we are to try a lying detector that
measures the skin conductivity or heart rate (assume that lying increases your heart
rate). We must also take into account that there are other factors that will
increase your heart rate and skin conductivity, such things as sexual arousal, anxiety,
anger and other strong emotions. Using an instrument that measures heart rate,
to see if someone is lying may therefore not be the best method to detect a
lie. For this to work you have to make sure that all other factors are removed,
but not all of them can be.

For an instrument or a study to be valid you also need it to be reliable
(I will not be discussing reliability in depth). For an instrument to be
reliable the results you receive must be similar with no anomalies,
disregarding how many times you repeat the experiment.

So, to actually be able to say something is valid, you must first know
its reliable, and to know something is reliable you must do the experiment
several times, with different objects (or participants) over a long period of
time, with different factors.

I hope you’ve enjoyed reading this, and I hope that I was able to answer
the topic so that everyone can understand what I’m talking about!

Good luck with your blogs and I’ll see you guys next time!

”Insanity is doing the same thing over and
over again and expecting different results.”

Albert Einstein

Field.A (2009) Discovering statistics using SPSS, 3rd Ed.. London: Stage


11 comments on “How do you know whether your findings are valid?

  1. ihmsl says:

    I enjoyed your blog it was very creative, my only point of constructive criticism would be that sometimes less is more your response could be summarised in one short paragraph for example:-
    “To say something is valid, you must first know its reliable and we can only presume results are reliable when repeating the experiment produces those very same results or data”.

    • Thank you for your comment! Yes Sometimes less Is more, but i wasn’t sure if I were able to explain everyting so that it was understandable. So maybe i overdid it just to be sure 🙂
      I will definately take that criticism into account for the next blog entry!

  2. ajkayaker says:

    I would say that you have a good basis for a premise of validity and reliability, particularly on the isolation of variables and retesting. In response to the quote from Einstein I would urge you to look up fractal patterns, and the Mandelbrot set. Those will truly show insanity!

    • Is a “good basis” another way of saying that you think my way to write about the topic was too simple ?;P I tried to keep it simple, yet comprehensive, not going to deep and end up writing an Essay.
      I Will look up Fractal patterns and the Mandelbrot set, sounds intressting!

      • ajkayaker says:

        ‘Good basis’ means what it says, that the post is good, but can be improved, possibly by either showing conflicting ideas or by more elaboration on points. Not a criticism, more saying you’ve taken at least one step in the right direction.

      • I did not get offended in any way dear fellow psychology student ^^, You are right that i could have shown some conflicting ideas, and maybe done a more in-depth explainations with different examples, but the blog, in my opinion would have been too long for anyone to bother reading it 🙂 Next time i will develop my own ideas that try and support my own thesis using facts…or other mens/womens theories at least;)
        I thank you for your feedback and i appriciate your reply 😀

  3. psuf10 says:

    Hey Tim

    This is a very good first attempt. Throughout you use a wide range of very good examples and have explained very well. However even thought your depth is good your breath of the question is limited due to you only talk about one way that you can know that you findings are valid. Also how do you know? what happens if you use as in your example a lying detector and your heart rates goes up when you see a hot girl, according to the experiment it means your lying even if you are telling the truth making the experiment invalid. I think that no matter how hard you try there will be external factors which will make the experiments results slightly invalid. By the way I love the quote at the end.

    • Yes, as far as i know there is no such thing as a 100% accurate lie detector. Unless you’re named Cal lightman and spent 40years of your life studying peoples faces*
      Of coruse the will always be some cases that makes the results “slighty invalid” within psychology. Because every person is slightly different. That is why, in my opinoin you do a quantitative research including lots and lots of testsubjects, to increase the chances of its validity ( or at least see if it is valid at all) Lets say that, you did a survey/study and a strong majority acctully turns out to support your hypothesis – Would you say that information is valid?

      * Cal Lightman is a fictional character in the series fictional Lie To Me, played my Tim Roth. The sciene behind the series is based on the research by Dr Paul Ekman. Who Acctually did study faces for 40 years.
      I love his work and if you ever get the chance, watch the series and/or read Dr Paul Ekmans work.

      • psuf10 says:

        I totally agree with you. There is no way that results would be 100% accurate. However what I do think is that scientists will do all they can to minimize the external stimuli to the experiment to make the experiment as fair as possible. This would make the results very close to 100% accurate especially, as you pointed out, when you increase the subject pool. You ask for another way to increase the validity of the information,, well another way would try and get a wide range of different subjects. In the case of people, to increase the trying to cover most of the aspects of the population including different ages, different genders, social upbringing and original ethnicity. I hope this answers your question

  4. fjwbu says:

    Your beginning was very interesting, in fact the structure of the whole post was. It was an easy post to follow and understand. Your use of examples made it clear to understand as well. I think it was good that you addressed the potential down falls in research that you have to be careful of in regards to validity, though you don’t say how you would counteract them. I think it was good that you touched on other relevant areas, reliability, without loosing sight of the point of the post/ actual topic.
    The only issues I had readlly was that i feel you could have gotten a bit more indepth with the topic and used more referencing. Otherwise, very concise, nicely done 🙂

  5. hicp3 says:

    Hi, I enjoy reading your blog, as it is very clear and organized. I find it interesting when you said about the lying detector that measures the heart rate and how sexual arousal and anxiety could actually alter the outcome of the experiment. So I guess it is important to avoid an experimenter and a participant having an opposite gender, due to those factors you mentioned.

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 )

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