iSixSigma

t-test vs. paired t

Six Sigma – iSixSigma Forums Old Forums General t-test vs. paired t

Viewing 17 posts - 1 through 17 (of 17 total)
  • Author
    Posts
  • #38616

    AB
    Participant

    I was hoping that someone would be able to explain when I would use the t-test and when to use the paired t-test.  I am having a hard time to properly define matched data.  Any help with examples would be greatly appreciated.
     

    0
    #115829

    Chas
    Participant

    Suppose you had 40 samples and 2 measurement sites. In one case, you randomly assign 20 samples to each site. You would use a t-test for the analysis. However, if you split all 40 samples and have each site measure each sample, you would use a paired t-test for the analysis.
    In a t-test, the sample are completely indepdendent across the study factor. In a paired t-test, the sample are not independent across the study factor.

    0
    #115874

    NS
    Participant

    Here is an example that will hopefully illustrate the point:
    (1) You have a group of people.  You measure the level of oxygen in their bloodstream.  You then give each person a pill.  You re-measure the level of the oxygen in their bloodstream.  Here it would be valid to use a “paired t-test” as you can match “before and after” for person A, for person B, for person C, etc.  This is much more powerful than just doing a “t-test” for the 2 samples (before and after).  Each person may react differently to the pill, but the “paired t-test” will remove this variation, and allow you to focus on the difference between each individual person.
     

    0
    #115879

    Plastic
    Participant

    Good example.
    Plastic

    0
    #116338

    Carlos Ponce
    Participant

     All,

    I agree with all examples but there is another characteristic that you can use  to identify if you can use, or not, a paired test. It’s the correlation because all the time that you are using the paired test you are testing the same sample after and  before an event.

    So, if you  are measuring the same “ piece” after and before an event you can expect a strong correlation between the data.

    In the other hand, when you are using the t test (no paired) the data are independent, so you can not expect  a relevant correlation as in the first case.
     
    Antonio Carlos Ponce
     
     

    0
    #116347

    Winders
    Member

    A t-test is used for analyzing measurements taken before and after a process change or improvement.  For example, you measure 30 pieces and the data shows a mean shift problem so you make improvements/changes to the process.  You now take another sample of pieces and measure them after the changes.  You would use a t-test to analyze the results.  With a paired t-test you are measuring the same parts before and after a process.  For example, you measure 10 pieces before they are e-coated and measure those same 10 pieces after they are e-coated then you would use a paired t-test to analyze the data.  Hope this helps.

    0
    #117568

    Gutierrez
    Participant

    I have similar question. If for example, I have 40 samples:
    10 adult male10 adult female10 teenage boys10 teenage girls
    and I give them a pill, and measure the effect of the pill before and after. What can I conclude if I use T-test, and what if I use Paired T? Is it right to say that if my T-test is significantly different, the pill has a significant effect on the population of interest, whereas if my Paired T is significantly different, it is also having significant effect on the population of interest??
    Also:
    1. Is it wrong to use both tests at the same time? 2. Do I need p-value or F-test for further testing?
    Thank you very much.
    Best regards,
    Alex

    0
    #117569

    Ankit Jhingan
    Participant

    Hi,
    This is a good question as sometimes its dificult to assume the kind of test that should be conducted for a given sample data.
    In this case, first of all, define Hypothesis statement in which define, Ho which is the status quo and define Ha which is the statement you are trying to prove.
    If P value 0.05, fail to reject Ho.
    In this case conduct t-test as it will be a fair test of the distribution of the sample data.
    I would prefer to use MINITAB software for all the calculations but since I don’t know which software you are using so really can’t suggest on that.
    Sincere Regards
    Ankit Jhingan

    0
    #117571

    Gutierrez
    Participant

    Hi,
    Thank you for your reply. I’m not really worried about calculations, because I’m sure minitab, SPSS or even Excel are pretty much the same. I was more concern about what we could conclude from using T-Test and Paired T for the example I gave.
    Anyone care to enlighten us?Alex

    0
    #117574

    walden
    Participant

    Please review the following link.  It is overly simplified, but it should help. http://home.clara.net/sisa/pairwhlp.htm.  A paired T-test is basically a repeated measures design used as a conservative measure of variance.  If your n is small with large variability between cases, then you should use a paired test.
    Chris
     

    0
    #117602

    faceman
    Participant

    If you take a measurement on each individual then give them the pill then do the same measurement then I would use the paired t because it will ‘block’ the variability between subjects as to whatever characteristic you are measuring.  Let’s say it is a blood pressure pill.  I assume that there is pretty big variation in your test subjects when it comes to blood pressure.  With an unpaired t test all that variation ends up as error (thusly masking a potential significant effect).  A paired t is going to look at the differences between each subjects’ before and after blood pressure.  An unpaired t will compare the before and after means.  All that variation between subjects doesn’t diminish the paired t’s ability to detect a difference in before and after.
     
    I suppose that you could run an F to see if the pill increased or decreased variance in blood pressure.
     
    Good luck,
    faceman

    0
    #117604

    faceman
    Participant

    This is from a previous post.
    I have similar question. If for example, I have 40 samples:
    10 adult male10 adult female10 teenage boys10 teenage girls
    and I give them a pill, and measure the effect of the pill before and after. What can I conclude if I use T-test, and what if I use Paired T? Is it right to say that if my T-test is significantly different, the pill has a significant effect on the population of interest, whereas if my Paired T is significantly different, it is also having significant effect on the population of interest??
     
    I think a paired t test is best to detect the effect of the pill, but what if I want a paired ANOVA method (if such a thing exists) that would test for the interaction between the levels of adult male, adult female, etc and the pill?  What method will do that?
    Thanks in advance,
    faceman

    0
    #117629

    walden
    Participant

    If you use SPSS, you can run a repaeated measures with group as a 4 level between subjects variable.
    Chris
     

    0
    #117631

    Mikel
    Member

    To all of the real statisticians – go back to the back corner of your respective buildings and get out of the way of the real work.

    0
    #117634

    walden
    Participant

    Stan,
    As much as you post on the forum, I didn’t think you ever left your office. Of course since you do live in your office, how bout’ providing a little helpful info when some one asks. If more people validated there initial finding before they implemented a project, there would not be so many revamped processes.
    Chris
     
     

    0
    #117654

    ong
    Member

    Another question:Can you use the paired t-test across different species?
    For example, if you were to test if two species of plants
    had different pigments levels by testing pigment levels in
    both species at set altitude levels. In other words, can you
    correctly pair the two different species at the same
    altitiudes to test if they in fact have different pigment
    levels?Or, would you run a 2 sample t-test over the entire range
    of altitudes?Any help greatly appreciated!!

    0
    #132109

    Nishanth
    Participant

    Ankit,
    Call me or message me .Now you must have got an idea as what we are  upto. I made a file which consists of cell numbers ,the numbers you can’t even imagine.If i don’t receive a call or a mail in 24 hours time everything will go to where it needs to .
    BTW ** Your suggestion worked for me*** Hope to talk to you soon.
     
    Thanks,
    Nishanth
     
     
     

    0
Viewing 17 posts - 1 through 17 (of 17 total)

The forum ‘General’ is closed to new topics and replies.