Welcome to the NavList Message Boards.


A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding

Compose Your Message

Add Images & Files
    Re: Statistical analysis of sight data to improve personal technique
    From: Frank Reed
    Date: 2022 May 10, 09:44 -0700

    Jim Rives, you wrote:
    "And, the graph shows some outliers, which I have left in the analysis.  Can't cherry pick.  
    And, be consistent in the whole analysis approach.  Don't rush.  Record everything and keep it, even if you change them or don't use the data.  It might be just what you need looking back a year later. "

    Good call. Yes, I agree. I mentioned a particularly difficult case in my Lunars workshop on Sunday. If you're shooting a quantity that you know should be changing in one direction, for example a lunar distance that should be slowly rising, or an altitude of a star that should be falling, it's tempting to toss an observation that doesn't match your expected trend. The known trend creates certain expectations about the way in which the observations should change that are hard to ignore.

    Suppose you plan to measure the altitude of Polaris near the bottom of its little circuit around the north celestial pole as it has begun to rise on the right side. You shoot once and get 40° 48.6'. Then you shoot again after some minutes and get 40° 49.3'. After a few minutes more you shoot Polaris again and this time find 40° 48.9'. Wait -- it can't be lower... I've had this thought many times! It's tempting here to ignore the most recent observation and try again without even recording it. But the problem is that we don't know if this observation is actually worse. It may not be the "trend-breaker". It's possible that the previous sight was a bit too high. So keep 'em all and remain "agnostic" about the quality of each individual observation. :)

    Has anyone here tried applying  Chauvenet's Criterion or Peirce's Criterion which I mentioned a few days ago? Any other tricks for tossing outliers?

    Frank Reed

    Browse Files

    Drop Files


    What is NavList?

    Join NavList

    (please, no nicknames or handles)
    Do you want to receive all group messages by email?
    Yes No

    You can also join by posting. Your first on-topic post automatically makes you a member.

    Posting Code

    Enter the email address associated with your NavList messages. Your posting code will be emailed to you immediately.

    Email Settings

    Posting Code:

    Custom Index

    Start date: (yyyymm dd)
    End date: (yyyymm dd)

    Visit this site
    Visit this site
    Visit this site
    Visit this site
    Visit this site
    Visit this site