+ Reply to Thread
Results 1 to 2 of 2

Thread: Mean/St.dev analysis

  1. #1

    Mean/St.dev analysis




    Hello everyone, a pleasure for me to write in the community

    I'm currently looking to understand whether it sounds statistically correct the current way undertaken to study the frequency of bond selling before the natural repayment deadline

    A part from all possible behavioral opportunity single customer may have, I would like to understand whether you agree with current steps proposed and whether you get any hints to apply for a regression analysis without inserting additional info about sex/age/ of stakeholders to then sort of p-value coefficients that would confirm my analysis acceptable.

    What I've been trying to study is whether a specific cluster of financial products (Corporate bonds rather than Government) for which it has been set a defined "exit ratio" (i.e. % of stakeholder who went out from contracts before natural maturity here measured in terms of capital amounts disinvested) it is coherent when compared to the the average (single) mean of each "exit ratio" coming out studying each corporate/government bond behind the cluster created. This maybe not so trivial because the ratio defined for the cluster is affected by ad-hoc specific adjustments e.g. + fixed % to be added to the simple average exc.

    Questions are:
    - would you agree with this analysis as explanatory to prove statistical reasoning of cluster defined ?
    - would you see any possibility of coming out with a p-value analysis for the test above ?
    Attached Files

  2. #2
    Points: 1,777, Level: 24
    Level completed: 77%, Points required for next Level: 23

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Mean/St.dev analysis


    Quote Originally Posted by Talalapunzicher View Post
    Hello everyone, a pleasure for me to write in the community

    I'm currently looking to understand whether it sounds statistically correct the current way undertaken to study the frequency of bond selling before the natural repayment deadline

    A part from all possible behavioral opportunity single customer may have, I would like to understand whether you agree with current steps proposed and whether you get any hints to apply for a regression analysis without inserting additional info about sex/age/ of stakeholders to then sort of p-value coefficients that would confirm my analysis acceptable.

    What I've been trying to study is whether a specific cluster of financial products (Corporate bonds rather than Government) for which it has been set a defined "exit ratio" (i.e. % of stakeholder who went out from contracts before natural maturity here measured in terms of capital amounts disinvested) it is coherent when compared to the the average (single) mean of each "exit ratio" coming out studying each corporate/government bond behind the cluster created. This maybe not so trivial because the ratio defined for the cluster is affected by ad-hoc specific adjustments e.g. + fixed % to be added to the simple average exc.

    Questions are:
    - would you agree with this analysis as explanatory to prove statistical reasoning of cluster defined ?
    - would you see any possibility of coming out with a p-value analysis for the test above ?
    ok, i will add a reply as first to myself. Hope it would helps

    What I'm currently doing is actually to apply a -Difference of means- analysis and seeing whether the delta is below an acceptable level.

    I'm attaching here (hope acceptable under the rules) a link to the Khan academy who lead me to this possible conclusion. A negative remark is of course about the Normality of the distribution that here I'm assuming but that it should not be possible for lapse insurance rate.

    Thanks for your opinion in advance
    Attached Files

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats