I will use
curve fitting for intermediate interest rates, but not for stock allocations.
It is not appropriate to use a
linear curve fit to the data for such short time periods.
From what he's said I think he's using his longer equation that he got
from curve fitting to model output.
We didn't cheat because the customer didn't tell us
what curve fit to use.
Also when you do a least
squares curve fit using the normal equations (the usual method), there is an implicit weighting of the data points proportional to their distance from the center.
Blaming global warming on the movements of other planets is little more than «climastrology» and
curve fitting without a physical basis.
By fitting certain polynomials to the global temperature data, we can find a residual with a 60 year cycle, but only with certain
curve fitting choices.
In both of these cases we have assumed a global \ (\ phi \) parameter, and found it by
polynomial curve fitting of mean vs variance.
I used Excel's
curve fitting capability to fit straight lines to the data and to report the equations (i.e., regression equations) and goodness of fit (R - squared).
The next step will be to calculate some more HSWRxxT2 regression equations to see how well this simple
curve fit performs.
This is not a scientific approach, it's
simply curve fitting (a.k.a. «graph cooking» and «mathturbation») at its worst.
Simultaneous calculation (with other parameters) using the generalised automatic or computer - aided - manual
curve fitting routines;
Correlation is not causation; all L&S have demonstrated in their
unphysical curve fitting exercise is a correlation between their cycles and global temperature.
Without a realistic physical basis, like Spencer before them, all L&S are doing is playing pointless
curve fitting games, and using their results to draw unsubstantiated conclusions.