It is not appropriate to use
a linear curve fit to the data for such short time periods.
I used Excel's plotting capability to determine regression equations (i.e.,
linear curve fits).
I used Excel plots to determine regression equations (i.e.,
linear curve fits) of balances versus the percentage earnings yield 100E10 / P.
I used Excel to determine regression equations (i.e., straight - line,
linear curve fits).
Not exact matches
I used Excel's plotting function to calculate regression equations (i.e.,
linear, straight - line
curve fits) of the dividend amount at Year 10 and at Year 20 versus the percentage earnings yield 100E10 / P.
You could
fit a
linear trend to the above
curve and also find an increase in the rate — although a
linear trend would not be a great description of what is going on, because the increase in rate is clearly not
linear.
It is indeed quite counter-intuitive to me that the best -
fit quadratic to the synthetic sea level
curve has negative curvature even though a
linear fit to the derivative of that sea level
curve is clearly positive.
The
linear effects that ENSO and volcanic aerosols have on global temperatures are well documented through a multitude of different analyses, including «
curve -
fitting».
One reviewer pointed minor corrections and approved for publication and the 2nd reviewer gave excellent marks but at the end he made a statement saying it can also be
fitted to
linear curve.
While it is possible to consider
fitting an upward
curve to the graph @ 426 in place of the
linear trend, the cause of the increases in Antarctic SIA / SIE would be worth looking at first.
I think, but am not sure, that he is trying to say that his «lagged
linear equation» (ie his fudged
curve fit from his previous article) is the «functional equivalent» of ∆ Ts = λ.
Let's expand the scale for a direct comparison of the
linear fit (in blue) to the smoothed
curve (in red):
You have no physical explanation for your
linear trend, no justification for asserting that there is one, no justification that any trend you claim will continue, and you are ignoring all of the responses you have had over many months that demonstrate that an upward
curve provides a much better
fit.
However, although its simple
linear regression analysis facilities (including polynomials) provides automatically the option for plotting the
fit with CIs for the
fitted line /
curve and for future observations from the same population, I am unsure about these intervals for autocorrelated data — typically time series.
I say only a
linear fit to the data can be accepted as being justifiable for extrapolation of the data because any other
curve is an expression of prejudice.
Richard, for the last time, the trend in atmospheric CO2 levels since 1958 is not
linear, it is slightly exponential with a lot of ups and downs, but no matter what
curve you may use to
fit the real trend, the increase rate per year doubled over the past 40 years.
Actually, you can't forecast anything anyway, because you are
curve -
fitting to something that looks like a mere 1 1/2 cycles of something, without a prediction - capable mechanism, and without anything that cross-checks it to anything outside those 1 1/2 cycles, on top of which the supposed underlying
linear trend might be part of some other cycle and hence not
linear at all,.
and you want to extrapolate your
fitted curve and try to draw out some sort of extra
linear forcing after the 1950's.??
By analogy with certain sets of data that are actually generated by say a quadratic function or other polynomial, there might be sections where the
curve is almost flat and happens to match a
linear fit, but that
linear fit will then diverge from the more complicated reality.
An alternative that ventures into «
curve -
fitting» would be to
fit a
linear regression to the UAH temperatures being used.
Another problem is that the residuals are not randomly distributed for the
linear fit, with at the start and end part of the
curve up to 6 ppm deviation from the
fitted value, and in the middle -3.5 ppm.