iSixSigma

Which Hypothesis Test Should I Use?

Six Sigma – iSixSigma Forums General Forums Tools & Templates Which Hypothesis Test Should I Use?

Viewing 7 posts - 1 through 7 (of 7 total)
  • Author
    Posts
  • #55733

    S Nandy
    Participant

    Which Hypothesis test should I run for PRE/POST or Before/After test in which Y and X both are continuous and my target is median .

    0
    #201415

    MBBinWI
    Participant

    @Snandy – why should we do your homework for you? Why don’t you propose an answer and your reasons why it is correct and we will tell you where you are right/wrong.

    0
    #201437

    First you will need to check the normality test. You will need to know if the data are normal or not normal.
    After you will need to check if the two situations are different using leneve’s test or f-test, you can use the igual variances test on the minitab.
    And if the data will be differents you can check if the medians or medianas are igual or not, for this case you can use de moodstest in the nonparametric data in minitab too.

    0
    #201439

    I recomend you to use minitab software , it is so easy to use and has a good assintent . there you will find a help and a step by step is very easy to use. I recomend minitab 17 is more complete.
    Good luck with your work.

    0
    #201465

    Mike Carnell
    Participant

    @Snandy If you will Google Hypothesis Testing Flow Chart and then click on images you will find a plethora of hypothesis testing flow charts. Most make it much more complicated that it actually is. The original of this was written in 1995 with Miguel Hernandez and I sitting on the floor in the Barcelona Spain Hilton preparing to teach Analyze to a Spanish & Italian class during the Allied Signal deployment. We had French simultaneous translators so communication was suboptimized with the 4 languages in constant use. The flow chart was meant to simplify the thought process. Numerous people have tried to enhance it with all kinds of information but if you just focus on the basic blocks you will have what you need.

    Fos gave you the basic thought process Normality > variance test > centrality test (Mean or median). You do in this order because of what you need to answer the next tools assumptions.

    0
    #201538

    Chris
    Participant

    Sandy, can we have some more info ie your variables and the hypothesis? Continuous / Continuous usually lends itself to regression, however with Before and After data you can run a 2-Sample T-Test or Mood’s Median to see if your data is different for your Y with your X now being Before/After.

    0
    #201563

    Chris Seider
    Participant

    FOS, depending on the test, you don’t need to check the normality of X or Y (e.g. regression).


    @Snandy
    why are you interested in Medians?

    0
Viewing 7 posts - 1 through 7 (of 7 total)

You must be logged in to reply to this topic.