Forums
New posts
Search forums
What's new
Articles
Latest reviews
Author list
Classifieds
Log in
Register
What's new
Search
Search
Search titles and first posts only
Search titles only
By:
New posts
Search forums
Menu
Log in
Register
Install the app
Install
Forums
Rifles, Reloading, Optics, Equipment
Reloading
Garmin Xero C1 Pro
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="gregmark24" data-source="post: 3021692" data-attributes="member: 121785"><p>I beg to differ. Garmin calculates it WRONG. First, we're assuming a normal (bell-shaped) distribution. Not a bimodal, triangular, square top distribution, etc. Most of us are shooting smaller samples of data, well under 30, and more likely 5 to 10 shots looking for an average velocity, ES and SD. If one uses the sample SD calculations for smaller samples, (Excel: STDEV) the denominator is sqrt(N-1). For a population, that denominator is sqrt(N). This has a huge effect for the shooter doing small groups. What is worth noting is that as the sample size gets larger and larger towards the "population", the results from STDEV and STDEVP (sample and population) converge with minimal error. Since Garmin doesn't state their method, but uses a population calculation, this is inherently the wrong way to do it. The correct way to do it is to use a Sample SD and let it converge for larger sample sizes or full populations of data. The difference for a set of 30 data points is typically about 0.1 difference in SD between the two methods.</p><p>Also, we did use Excel with STDEV and STDEVP for raw data from LabRadar as well as Garmin, and we got identical results using STDEV vs LabRadar and STDEVP for Garmin.</p></blockquote><p></p>
[QUOTE="gregmark24, post: 3021692, member: 121785"] I beg to differ. Garmin calculates it WRONG. First, we're assuming a normal (bell-shaped) distribution. Not a bimodal, triangular, square top distribution, etc. Most of us are shooting smaller samples of data, well under 30, and more likely 5 to 10 shots looking for an average velocity, ES and SD. If one uses the sample SD calculations for smaller samples, (Excel: STDEV) the denominator is sqrt(N-1). For a population, that denominator is sqrt(N). This has a huge effect for the shooter doing small groups. What is worth noting is that as the sample size gets larger and larger towards the "population", the results from STDEV and STDEVP (sample and population) converge with minimal error. Since Garmin doesn't state their method, but uses a population calculation, this is inherently the wrong way to do it. The correct way to do it is to use a Sample SD and let it converge for larger sample sizes or full populations of data. The difference for a set of 30 data points is typically about 0.1 difference in SD between the two methods. Also, we did use Excel with STDEV and STDEVP for raw data from LabRadar as well as Garmin, and we got identical results using STDEV vs LabRadar and STDEVP for Garmin. [/QUOTE]
Insert quotes…
Verification
Post reply
Forums
Rifles, Reloading, Optics, Equipment
Reloading
Garmin Xero C1 Pro
Top