To expand on my comment that Thunder’s PE Data is much more detailed and useful, here is a table of starting and ending Length (in inches) at an even percentage distribution for: data including contributors that made any entries (inclusive) or more than one entry (exclusive).
—————-inclusive —————— | ———— exclusive ———————
— pop - start L - pop —— end L — pop —- start L - pop —— end L
100.0% — 1.000 - 100.0% — 1.000 - 100.0% — 1.000 - 100.0% — 1.000
_97.5% — 4.750 — 97.5% — 5.000 — 97.5% — 4.800 — 97.5% — 5.250
_95.0% — 5.000 — 95.0% — 5.125 — 95.0% — 5.000 — 95.0% — 5.520
_92.5% — 5.188 — 92.5% — 5.400 — 92.5% — 5.250 — 92.5% — 5.813
_90.0% — 5.300 — 90.0% — 5.500 — 90.0% — 5.300 — 90.0% — 6.000
_87.5% — 5.500 — 87.5% — 5.600 — 87.5% — 5.500 — 87.5% — 6.000
_85.0% — 5.500 — 85.0% — 5.750 — 85.0% — 5.500 — 85.0% — 6.125
_82.5% — 5.500 — 82.5% — 5.875 — 82.5% — 5.500 — 82.5% — 6.250
_80.0% — 5.708 — 80.0% — 6.000 — 80.0% — 5.688 — 80.0% — 6.299
_77.5% — 5.750 — 77.5% — 6.000 — 77.5% — 5.750 — 77.5% — 6.377
_75.0% — 5.800 — 75.0% — 6.000 — 75.0% — 5.750 — 75.0% — 6.500
_72.5% — 5.900 — 72.5% — 6.000 — 72.5% — 5.800 — 72.5% — 6.500
_70.0% — 6.000 — 70.0% — 6.125 — 70.0% — 5.900 — 70.0% — 6.563
_67.5% — 6.000 — 67.5% — 6.250 — 67.5% — 6.000 — 67.5% — 6.688
_65.0% — 6.000 — 65.0% — 6.299 — 65.0% — 6.000 — 65.0% — 6.750
_62.5% — 6.000 — 62.5% — 6.390 — 62.5% — 6.000 — 62.5% — 6.750
_60.0% — 6.063 — 60.0% — 6.500 — 60.0% — 6.000 — 60.0% — 6.800
_57.5% — 6.125 — 57.5% — 6.500 — 57.5% — 6.100 — 57.5% — 6.890
_55.0% — 6.250 — 55.0% — 6.500 — 55.0% — 6.125 — 55.0% — 7.000
_52.5% — 6.250 — 52.5% — 6.614 — 52.5% — 6.250 — 52.5% — 7.000
_50.0% — 6.300 — 50.0% — 6.700 — 50.0% — 6.250 — 50.0% — 7.000
_47.5% — 6.496 — 47.5% — 6.750 — 47.5% — 6.250 — 47.5% — 7.000
_45.0% — 6.500 — 45.0% — 6.750 — 45.0% — 6.375 — 45.0% — 7.100
_42.5% — 6.500 — 42.5% — 6.875 — 42.5% — 6.500 — 42.5% — 7.125
_40.0% — 6.500 — 40.0% — 7.000 — 40.0% — 6.500 — 40.0% — 7.240
_37.5% — 6.600 — 37.5% — 7.000 — 37.5% — 6.500 — 37.5% — 7.250
_35.0% — 6.700 — 35.0% — 7.000 — 35.0% — 6.500 — 35.0% — 7.284
_32.5% — 6.750 — 32.5% — 7.063 — 32.5% — 6.625 — 32.5% — 7.375
_30.0% — 6.750 — 30.0% — 7.125 — 30.0% — 6.750 — 30.0% — 7.500
_27.5% — 6.900 — 27.5% — 7.250 — 27.5% — 6.750 — 27.5% — 7.500
_25.0% — 7.000 — 25.0% — 7.250 — 25.0% — 6.800 — 25.0% — 7.500
_22.5% — 7.000 — 22.5% — 7.375 — 22.5% — 6.900 — 22.5% — 7.600
_20.0% — 7.050 — 20.0% — 7.500 — 20.0% — 7.000 — 20.0% — 7.750
_17.5% — 7.200 — 17.5% — 7.500 — 17.5% — 7.000 — 17.5% — 7.750
_15.0% — 7.250 — 15.0% — 7.625 — 15.0% — 7.125 — 15.0% — 7.870
_12.5% — 7.500 — 12.5% — 7.750 — 12.5% — 7.250 — 12.5% — 8.000
_10.0% — 7.500 — 10.0% — 7.875 — 10.0% — 7.500 — 10.0% — 8.000
__7.5% — 7.750 —- 7.5% — 8.000 —- 7.5% — 7.500 —- 7.5% — 8.250
__5.0% — 7.938 —- 5.0% — 8.250 —- 5.0% — 7.750 —- 5.0% — 8.500
__2.5% — 8.250 —- 2.5% — 8.500 —- 2.5% — 8.000 —- 2.5% — 8.800
__0.0% - 13.000 —- 0.0% - 13.000 —- 0.0% — 9.770 —- 0.0% — 9.999
And attached are two graphs to visualize the data - inclusive and exclusive.
These are common ways I split the data. There are benefits to both, I think, given that you can never really assume why someone only ever made a single entry. Maybe they never tried PE, maybe they never committed to a regular routine, maybe they never grew, maybe they did grow, but never reported it. That doesn’t mean those entries aren’t valuable. You can take any assumption you choose and have data to support it. The inclusive set also gives us a bigger data set when we just want to look at predictions for the general populations.
No matter how invalid my idea is, I often compare my stats to the exclusive ending measurements. In the universe of scenarios, one can speculate that more small guys come to Thunder’s than large ones, which would mean the greater population must be larger than our data. I use that perspective in estimating my size to that prediction of a population. Some might call it a “worst case scenario”. I call it motivation. :-)