Items tagged with curvefitting

Hi all,

I tried to fit my data (x,y) with a model by using Minimize the Chisquare. By example the model is y=a*x+b, Chisquare is (y-yexp)^2. And I performed a function Minimize(Chisquare) to have a and b.

I need to extract the error of parameter like a±aerror, and b±berror.

Thank you for your helps,

Best regards,

 

 

 

 

Hello! 

I got a set of data imported from excel which is of the size 2001x2. I've use DataPlot to plot the graph of this data but I can't seem to find a way to integrate it. I've used BSplineCurve to make the discreate values continious but I cant seem to integrate this new curve. Can someone please give me a solution or an alternative way to find an approximative way to find the area under the curve.

Thanks

I am trying to model a disease. The equation is as follows:

S*X - f(X,S,Sp) = 100

I have data for S, I have data for X and I have data for f(X,S,Sp) however I want to find an equation for f(X,S,Sp) that has the best fit with the data because I need to use it later on in my calculation. If anyone is intrested S is the sensitivity of the blood test, Sp is the specificity of the blood test. This means that X*(1-Sp) is the number of false positives.

I currently dont have access to Maple hence I am doing all my modeling in excel 2016. So I am severly limited because excel is useless at algebra.

Maple.xlsx

I have a data point set:

relativní_tlak:=<0.063018,0.078419,0.119628,0.159668,0.199865>:

ads_mnozstvi:=<0.001467443666,0.001528693055,0.001659939952,0.001774105924,0.001883866808>:

I wanna make the least square fit with function in form of:

bet:=(x/(1-x))/((1/(a*b))+(((b-1)/(a*b))*x)):

also the command looks like:

with(Statistics):bet_nejmensi_ctverce:=NonlinearFit(bet,relativní_tlak,ads_mnozstvi,x,parameternames=[a,b],output=parametervector);

I found out the least square fit is not correct using the near-zero values in 'ads_mnozstvi' vector (the parameters have no physical sense).

The correct a,b values can be obtained when 'ads_mnozstvi' values are multiplied by 1000. The correct a,b values thus are:

[1.56257913677048,108.232791649022]

Why Maple cannot make correct fit with near-zero values?

updated:

with(CurveFitting);
f := PolynomialInterpolation([[0, x0],[1, x1],[2, x2],[3, x3],[4, x4]], x);
f2 := solve(f=y,x);
area1 := int(f, x=0..1);
with(student):
area2 := trapezoid(f2[1], x = 0..1);
with(CurveFitting);
f := PolynomialInterpolation([[0, x0],[1, x1],[2, x2],[3, x3]], x);
f2 := solve(f=y,x);
area1 := int(f, x=0..1);
with(student):
area2 := trapezoid(f2[1], x = 0..1);

 

i use 5 points trapezoid got RootOf  in result,

only 4 points is acceptable

 

when i try 5 points, there is no problem, but when more points such as

30 points, got RootOf for c sharp code

 

moreover, i got a problem when i copy the area1 result into 

visual studio c# code, it has error Integral Constant is too large

 

with(CurveFitting);
f := PolynomialInterpolation([[0, x0],[1, x1],[2, x2],[3, x3],[4, x4],[5, x5],[6, x6],[7, x7],[8, x8],[9, x9],[10, x10],[11, x11],[12, x12],[13, x13],[14, x14],[15, x15],[16, x16],[17, x17],[18, x18],[19, x19],[20, x20],[21, x21],[22, x22],[23, x23],[24, x24],[25, x25],[26, x26],[27, x27],[28, x28],[29, x29]], x);
f2 := solve(f=y,x);
area1 := int(f, y=0..1);
with(student):
area2 := trapezoid(f2[1], x = 0..1);
with(CodeGeneration):
CSharp(area1, resultname = "area1");
CSharp(area2, resultname = "area2");

i find area2 has

Warning, the function names {RootOf, Sum} are not recognized in the target language
Warning, precedence for Range unspecified
Warning, cannot translate range
area2 = RootOf((System.Double) (19276689540529530246975515949293568 * x3 - 2626509155780373903082144116707328 * x2 + 239680950855919251544490932629504 * x1 -

Hi

In attached mw file I have a equation that "a" is in unknown parameter. X and Y are matrixes of data. How can I calculate the "a" parameter?

Best regard

question.mw

I have 101 point with very low value

and I'm trying to get the best curve that fits that points. I have tryed with a polynomial interpolator but the curve is not very good. I have also tried with an exponential but an error ocurrs. 

Error, (in Statistics:-ExponentialFit) dependent values must evaluate to positive numbers

 

Can anyone help me? Any ideas? How can I find the best curve fitting?

 

Thanks.

Given some points, how do I find the polynomial/exponential function best matches them?

points are:[[1030, 0], [380, 34], [270, 73], [240, 150], [85, 700], [22, 2000], [12, 5000]]

And here is a image too.

Points

                                                                                 

Hi everybody,

I have some experimental data from an oscillating system (time domaine) and I would like to get an approximation of the damping ratio (zeta). I have already try to use the half-power band width method with the vibrationdata Matlab package designed by Tom Irvine. But I would like to double-check the result with another method.

I found several methods in this paper and I would like to try to do the curve fitting method with the Curve Fitting Toolbox of Maple or Matlab (R2014b) (2.2.2 Curve fitting in the paper). data.txt

It's the first I use this Toolbox with a custom equation, so, I do not really know how to do it with my sample data.

Can anybody help me with this ? I have attached the .txt file sample data to this post.

Cheers

Hello everyone,

 

I have a set of data that I have imported in Maple.  When I plot the data, I can see that there are two sine waves in it.  It is a plot of radial velocity of a star versus time.  This is about a reflex motion of a star with an orbiting planet.  We will set that there is only one planet.

I would like to extract those two sine waves.  I am including that *.csv file that I imported in Maple that you can download at this address.

https://www.dropbox.com/s/4f4j5xm565je30x/Tyr_rv9_Maple.csv?dl=0

This is not for an exam but it is for a course in February and this will be very helpful and I want to share this file.  I can predict that there will be more than one planet but it is the idea that is important.

 

Thank you in advance for your help.

 

--------------------------------------
Mario Lemelin
Maple 2015 Ubuntu 14.04 - 64 bits
Maple 2015 Win 10 Pro - 64 bits messagerie : mario.lemelin@cgocable.ca téléphone :  (819) 376-0987

I have used data and the curve fitting procedure to find a curve and I now have to put error bars on the graph to complete my task? I know that there is an errorplot function but I cant seem to find a way to do it with the curvefitting thing?

 

I have attached the whole worksheet, I hope someone can help! Thanks Detectors_Tutorial.mwDetectors_Tutorial.mw

 

Even if there was some method of exporting the graph to another medium that would also be very helpful

 

Hi everyone

I'm trying to solve the following system of ODE equations for my end paper and since I'm new with maple I couldn't find a way to do it. Can anyone Plz help me? I need to fit a curve to the result and gain a symbolic equation.

Here are the equations I need to solve

d^2*Y(x)/dt^2 = 500000*Y(x)*exp(-10/T(x))+d*Y(x)/dt

d^2*T(x)/dt^2 = 10*(-100000*Y(x)*exp(-10/T(x)))+d*T(x)/dt

with the follwoing boundary conditions:

Y(0)=1 , Y'(0)=0, T(0)=0 , T'(0)=0

I need to plot Y and T and then find then do the curve fitting thing.

I really appreciate your help.

I have a maple proc for which I would like to find parameters to fit data I have. The proc has an 'if' statement in it, and when I try to use the CurveFitting function 'NonlinearFit' function, I'm getting an error.

Is there a curve fitting function that can be used with procs with 'if' statements in them?

Thanks. 

Hi!

This question is related to http://www.mapleprimes.com/questions/204419-Derivatives-Of-Splines-Are-Not-Defined and http://www.mapleprimes.com/questions/42114-Problem-With-Spline-Integrating , however I have not been able to apply the solutions given there to my problem.

I have a set of points given by

and certain function value points given by

where e1 is the function I am approximating.


Using

I come up with my piecewise function.

When I do diff(e4,x), however, the points at the nodes show "float(undefined) x=0.2..."(the node).

As it turns out, the value of the derivative on the left of the node is not equal to that of the right side by a factor of 10^(-7), in other words, numerically unimportant but high enough for maple to realise it is not the same number. How could I tell Maple that I am happy choosing, for example, the value given by the function on right side of the node?

I welcome any suggestions.

Many thanks in advance.

Ok guys this is the problem i have a matrix wich is really the result of a semivariogram so it is like this 
plot([[0, 0], [1, 1], [2, 3], [3, 5], [4, 7], [5, 8], [6, 9], [7, 10], [8, 10.5], [9, 10], [10, 9.8], [11, 9.8], [12, 10.5], [13, 10.89], [14, 11.2], [15, 10.6], [16, 9.85], [17, 9.45], [18, 9.77], [19, 10.15], [20, 10.7], [21, 10.04], [22, 10], [23, 10.85], [24, 10.7], [25, 10.94], [26, 10.81], [27, 10.33]])thi is my semivariogram so i have to find the best model and fit it to it, i can't just throw a polynomial it has to be
spherical= h:= C((3/2)*x/a-(1/2)*x^3/a^3) 
expotencial=Upsilon := C(1-exp(-x/a))
Lineal= y:= p*x
or y:=p*x^a

so i want the maple to show me the variogram plot and the i select wich one of the models i will apply.
the problem is that i don't know how to apply the models so started something that could maybe lead to the values of C and A for the spherical and the xpotencial becouse the others too are easy.
------------------------------------------------------------------.--------------------------------------------------------
restart;
with(plots);
with(CurveFitting);
m3 := Matrix([[0, 0], [1, 2], [2, 5], [3, 7], [4, 10], [5, 14], [6, 15], [7, 15.4], [8, 15.8], [9, 16], [10, 16.4]]);
plot(m3);
Upsilon := C(1-exp(-x/a));
Upsilon := C((3/2)*x/a-(1/2)*x^3/a^3);
for C to 16 do
for a to 100 do
for x to 11 do
H := m3(x, 2);
R[C, a, x] := abs(Upsilon-H)
end do
end do
end do;
for r to 16 do
for j to 100 do
N[r, j] := sum(R[r, j, X], X = 1 .. 11);
if N[r, j] < 55 then
print(r, j)
end if
end do
end do;
k := 14*(3/2*((1/16)*xx)-(1/2)*xx^3/16^3);
multiple(plot, [m3, color = "Green"], [k, xx = 0 .. 11, color = "Blue"])
----------------------------------------------------------...................---------------------------------------
so in this code i rest the values of the model and the values of the matrix for differents C and a so i pick the min of the Sum to see wich C and a give me the min value but i didn't work quite well first is difficult to get the C and a and sometimes the new curve is just not similir to the semivariogram (Matrix) please help i tried 
k := NonlinearFit(C((3/2)*x/a-(1/2)*x^3/a^3), X, Y, x)
and 
k:=LeastSquares`(m3, v, curve = C*(1-exp(-x/a)))
but they don't let me because they aint linear on the parameters
please help 
if you are interested in this topic here is what i am trying to do but explained really well is for geological matters
http://www.kriging.com/PG1979/index.htm#Chapter_2+Part1

if want to help me use this matrix 
m3:= Matrix([[0, 0], [1, 1], [2, 3], [3, 5], [4, 7], [5, 8], [6, 9], [7, 10], [8, 10.5], [9, 10], [10, 9.8], [11, 9.8], [12, 10.5], [13, 10.89], [14, 11.2], [15, 10.6], [16, 9.85], [17, 9.45], [18, 9.77], [19, 10.15], [20, 10.7], [21, 10.04], [22, 10], [23, 10.85], [24, 10.7], [25, 10.94], [26, 10.81], [27, 10.33]])
for that matrix the spherical model is the best i know

goodbye

1 2 3 Page 1 of 3