? on ES / SD
- Thread starter piutemike
- Start date
Help Support Long Range Hunting Forum
So you shot 2 groups sub-MOA..
piutemike,
You should take your loads that shot well at 100 and take to the longer ranges and see what kind of 'Standard Deviation' you get 'out there' on paper.
This all that really matters!
piutemike,
You should take your loads that shot well at 100 and take to the longer ranges and see what kind of 'Standard Deviation' you get 'out there' on paper.
This all that really matters!
Winchester 69
Well-Known Member
- Joined
- Mar 29, 2007
- Messages
- 430
At the whole conversation. Your intuitive observations are correct. SD can be used as the basis for determining what is suspicious data. The progression from that point should be to parse the data, and then to investigate what is discarded. You're backing into SPC. It's the analytical technique that hasn't been refined.
.
goodgrouper
Well-Known Member
I see.
I read something about the SPC being unrefined or not thoroughly "worked out". It went way past what we need to know for reloading purposes but it was interesting.
All I know is that if we use a chronograph to get our loads right and it says the SD is in the single digits on multiple occasions and produces good accuracy, it will usually stack hits on top of each other at distance. This is about as "real world" as it gets and there are no formulas to substitute or equal common sense. If a guy wants to use ES as his correlation in lieu of SD, then that is his prerogative and it will most likely still produce good results.
milanuk
Well-Known Member
So... does anybody here muck around calculating confidence intervals for their mean (average) velocities for comparing the sample mean to the population mean? 
Sorry, just finishing up a Stat 201 class. Being a bit of a type 'A' sort to begin with, and moderately proficient w/ Excel to boot... the class opened up a whole bunch of doors for wasting time analyzing data
Something to keep in mind... even if you have a small E.S. or 'range' of velocities for the shots fired - the E.S. of all the shots fired from your gun (or at least something like 99.7% of them) will likely be described by your average +/- 3x your stdev value. So if you have a E.S. of 10, most people would be happy, and ignore say, the SD of 4 or 5. Guess what. 5 x 6 = 30, and if you fire enough shots, (30 or more), you'll likely find thats more what your 'actual' ES is - 25-30fps - if you're lucky. In my experience, most of us start making excuses (bad batch of primers, chrono on the blink, wrong phase of the moon, etc.) once our velocities start straying from that tight little bundle of joy we started with. The truth can be ugly sometimes, but ignoring it won't make it go away
Sorry, just finishing up a Stat 201 class. Being a bit of a type 'A' sort to begin with, and moderately proficient w/ Excel to boot... the class opened up a whole bunch of doors for wasting time analyzing data
Something to keep in mind... even if you have a small E.S. or 'range' of velocities for the shots fired - the E.S. of all the shots fired from your gun (or at least something like 99.7% of them) will likely be described by your average +/- 3x your stdev value. So if you have a E.S. of 10, most people would be happy, and ignore say, the SD of 4 or 5. Guess what. 5 x 6 = 30, and if you fire enough shots, (30 or more), you'll likely find thats more what your 'actual' ES is - 25-30fps - if you're lucky. In my experience, most of us start making excuses (bad batch of primers, chrono on the blink, wrong phase of the moon, etc.) once our velocities start straying from that tight little bundle of joy we started with. The truth can be ugly sometimes, but ignoring it won't make it go away
Ok, but like offered, it's worthless information with such small samples.
A simple example
Suppose we wished to find the standard deviation of the set of the numbers 4 and 8.
Step 1: find the arithmetic mean (or average) of 4 and 8,
(4 + 8) / 2 = 6. Step 2: find the deviation of each number from the mean,
4 − 6 = − 2 8 − 6 = 2. Step 3: square each of the deviations (amplifying larger deviations and making negative values positive),
( − 2)2 = 4
22 = 4. Step 4: sum the obtained squares (as a first step to obtaining an average),
4 + 4 = 8. Step 5: divide the sum by the number of values, which here is 2 (giving an average),
8 / 2 = 4. Step 6: take the non-negative square root of the quotient (converting squared units back to regular units),
goodgrouper
Well-Known Member
True.............to a point. Past that point, the variations need to be eliminated and the basics need to be on your side before you can even judge the conditions apart from the mechanics.
Here is my $.02 on the Ten shot string.
First, and most importantly the 3050 fps was very fortunate! Had this shot not been recorded, it would still be in your cartridge case and may have been used at long range;
Second, you can't fix a problem that you do not know exists. I bet the first automobile did not have brakes.....the first lawyer on the scene made a bundle on that error
Using just ES the load may be junk, SD & ES makes the whole reloading procedure more consistent assuming you figure out that the neck was tight and you look for that problem in the future.
Lastly, you will never ever know that you have removed all problems until you have fired every round that you will ever shoot. You may figure out the tight neck problem, but then thinned brass will show up, then worn throat, etc..... All you can do is ensure that once you identify a problem you put procedures in place to prevent you from any recurrences.
edge.
First, and most importantly the 3050 fps was very fortunate! Had this shot not been recorded, it would still be in your cartridge case and may have been used at long range;
Second, you can't fix a problem that you do not know exists. I bet the first automobile did not have brakes.....the first lawyer on the scene made a bundle on that error
Using just ES the load may be junk, SD & ES makes the whole reloading procedure more consistent assuming you figure out that the neck was tight and you look for that problem in the future.
Lastly, you will never ever know that you have removed all problems until you have fired every round that you will ever shoot. You may figure out the tight neck problem, but then thinned brass will show up, then worn throat, etc..... All you can do is ensure that once you identify a problem you put procedures in place to prevent you from any recurrences.
edge.
