Join 
72,195
 other iSixSigma newsletter subscribers:
WEDNESDAY, APRIL 26, 2017
Font Size
Topic Which Test Do I Use to Find if There Is a Correlation in My Data?

Which Test Do I Use to Find if There Is a Correlation in My Data?

Home Forums General Forums Tools & Templates Which Test Do I Use to Find if There Is a Correlation in My Data?

This topic contains 3 replies, has 2 voices, and was last updated by Profile photo of Chris Seider Chris Seider 1 month, 2 weeks ago.

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • #541466 Reply

    Hi everyone,

    I have a problem to solve – I feel that a team is taking unplanned leaves just by extending their planned leaves.

    For example, if someone has planned and applied for vacation on 9th and 10th of March then they are sending an email or text message saying they will be on leave for 13th also. I have seen this happen for over last 6 months from a majority of the resources in a team.

    I have 6 months worth data for this in the below format. There are four columns.

    Resource Name | Planned Leave Date | Unplanned Leave Date | Is Adjacent to Planned?

    My Business problem is that I want to prove that there is an association between the unplanned leaves and planned leaves.

    I do not know what I should use to prove this statistically – Chi Square Test for association (because my data is discrete?)

    OR should I look at it as binary data (The “Is Adjacent to Planned Leave?” flag) and just go by the Mode? i.e., the more “Yes” to that flag proves that the team members are taking unplanned leaves by extending planned leaves. They should avoid this and plan better next time so the delivery is not impacted.

    How do I go about this? Any pointers please?

    #542411 Reply

    Chi squared is a good place to start. Also, see if you can graphically display your data so you’re not just quoting p-values. :)

    #542415 Reply

    not just quoting p-values

    haha that is the best advice ever. I remember reading, what p-value tells us is only the statistical solution. We need to translate that into the Business solution.

    May I know why you suggested for Chi Squared over the simple mode?

    Thank you!

    #542769 Reply

    Chi-sq is used for frequency data (counts). @rbutler can give even more reasons–he’s more exact in replies than myself.

    @flower07 Thanks for the compliment. Great handle, fyi.

Viewing 4 posts - 1 through 4 (of 4 total)

Register Now

  • Stop this in-your-face notice
  • Reserve your username
  • Follow people you like, learn from
  • Extend your profile
  • Gain reputation for your contributions
  • No annoying captchas across site
And much more! C'mon, register now.

Reply To: Which Test Do I Use to Find if There Is a Correlation in My Data?
Your information:






5S and Lean eBooks
GAGEpack for Quality Assurance
Six Sigma Statistical and Graphical Analysis with SigmaXL
Six Sigma Online Certification: White, Yellow, Green and Black Belt
Lean and Six Sigma Project Examples
Six Sigma Online Certification: White, Yellow, Green and Black Belt

Find the Perfect Six Sigma Job

Login Form