Depending on the statistical power desired, a sample size of 7 or 8 is generally considered a good starting point for determining whether or not samples (a shot, or shot group in this case) are an accurate representation of the true mean. This is why 5 shot groups are a weak indicator of a barrels precision (it’s true mean/population mean).
Great points Molon!
At the 1992 Barcelona Olympics, USA Shooting Team members Launi Meili and Robert Foth won the gold and silver medals in the three-position rifle events. The Olympians used the new Federal Gold Medal ammunition to aid them in obtaining their victories. This was the first time in more than 30 years that an American won an Olympic medal in one of the small bore shooting events while using American-made ammunition.
It’s interesting to note that pertaining to the accuracy/precision development and multifaceted testing of the Federal ammunition that helped the US Olympians win gold and silver medals in Barcelona, Federal’s Director of Product Engineering, Dave Longren, had this to say:
“The standard test string was three 10-shot groups, with the most attention paid to the 30-shot composite. When you’re working at this level, the traditional five 5-shot group test simply doesn’t give you statistically valid results.”
…
More is always better for sure (except a few cases). I need to sift though my old lectures, but I used to have some informative graphs detailing the exponential gains in statistical significance, by increasing sample size. One quirk is that if you take enough samples of anything, you can essentially drift towards significance as you go up in N. If I remember correctly this is due to the increasing degrees of freedom.
The analysis of shot-groups is not simply a matter increasing sample size. It’s not a one dimensional problem. It’s a two dimensional problem (x and y components of each shot) that requires determining how many shots are needed to capture the radial dispersion.
…
Have you tried one yet?
When are we going to just simply “default sticky” Molon’s T/E posts…?
There’s just something very wrong about continuing to lose this in the mists of history among lube discussions (sorry…)
Please? Someone?
Either that or show me the error of my ways.