Glory be! The ratio! (OoP)
ksnidget <ksnidget@aol.com>
ksnidget at aol.com
Wed Jan 15 15:31:12 UTC 2003
Tabouli asks
>The length of these books seems to be going up exponentially. In fact... this
>sounds like a mission for David. There must be some mathematical way to check
>whether the page count best fits an exponential curve, mustn't there?
Well at the risk of displaying my inner geek in public.
Using the following data (page numbers for earlier books taken
from the Bloomsbury shop online web site)
1 190
2 256
3 317
4 636
5 768
And then plotting them on a spreadsheet
Exponential fit yields an equation of
y = 123.84e raised to the 0.3704x
R2 = 0.9598
R2 is a measure of how well it fits
A linear fit trendline gives
y = 153.6x - 27.4
R2 = 0.9171
So Exponential fits so far better than linear
A second order polynomial fit gives
y = 27.857x2 - 13.543x + 167.6
R2 = 0.9593
Which is almost as good as the exponetial fit.
Because they are easier for me to solve quickly I'll
just give the expected page numbers for the linear
and the polynomial assuming the trend continues.
linear polynomial
6 894 1089
7 1048 1438
Ksnidget <who really needs to get back to her FTIR spectra>
More information about the HPFGU-OTChatter
archive