Questions on the use of Mathematica to construct models for approximating empirical data.

learn more… | top users | synonyms (3)

3
votes
1answer
157 views

NonlinearModelFit: fit a vector-valued function to a data vector

I have a vector of data points: data = 10 Sin[#/10] + RandomVariate@NormalDistribution[] & /@ Range[200]; And I have model that provides the complete ...
1
vote
1answer
109 views

non linear Least Squares with model function given by ODE's

I have to fit to experimental data a model function given by a linear combination of functions y1(t) and y2(t) a1*y1(t) + a2*y2(t) with a1 and a2 ...
0
votes
1answer
80 views

Binomial Regression where n > 1

I am not well versed in Generalized Linear Models, but am trying to use this approach to model some discrete data. I have binomial data where the sample size for each observation is the same size, ...
-1
votes
1answer
83 views

NonlinearModelFit errors and precision

For this problem, I use a data set, which I've made available here. ...
0
votes
0answers
28 views

Fitting problem: InterpolatingFunction can not be localised

I got simple data looking as follows {{541.447, 311752.}, {540.359, 311723.},.. I tried to fit it in mathematica for the first time with a function that usually ...
0
votes
0answers
35 views

Which one will gives best fitting result?

I want to find out the parameters A, B, and C of the ...
0
votes
0answers
63 views

Finding values of a variable fitting a function and minimizing a list of expressions

I am trying to implement bootstrapping (https://en.wikipedia.org/wiki/Bootstrapping_(finance)) of CDS curve. To implement it I am trying to minimize a series of expressions so that each expression is ...
0
votes
0answers
81 views

How to make a twice-differentiable function that approximates some data?

I have some time series data that I would like to approximate with a twice-differentiable function. Each time series has ~10,000 datapoints, so I definitely do not want a function that passes through ...
0
votes
0answers
52 views

Solve an integral equation: to fit the given data with an integral of two functions?

I am trying to find an efficient way to solve the following equation $$h\left(b\right)=\int_{0}^{b}f\left(\frac{b-c}{1-c}\right)\frac{g\left(c\right)}{1-c}dc$$ where for $h(b)$ I have the data ...
0
votes
0answers
46 views

FindFit returning Power::infy: Infinite expression

So, I'm having an issue trying to fit some data to a function with a 2nd order pole. I know there are other functions that fit the data, just fine ... but the model is from the literature, however the ...
0
votes
0answers
59 views

Investigating the correlation between this 2 set of data

The picture below shows the growth of the traffic and the total number of published articles on that website. Which functions can I use to investigate if there is a correlation between them? Both ...
0
votes
0answers
32 views

How to use FindFit to find the parameter in Laplace space(numerically inverting Laplace transforms)

I am trying to find the parameter in Laplace space, and a very simple example is shown below: I have known the solution $y_{laplace}$ in the laplace space is $a/s^2$, and I also have some discrete ...
0
votes
0answers
43 views

Why does ParallelMap throw errors where Map does not?

I am encountering a problem with ParallelMap. I have a call in a large code base, part of which attempts to fit data in parallel using ...
0
votes
0answers
117 views

Decompose Point-Spread Function into Seidel Aberration/Zernike Polynomials

I have measured the point spread function (PSF of a microscope) and I want to quantify it. For that purpose I want to fit my PSF data to the primary Seidel optical aberrations (or Zernike Polynomials, ...
0
votes
0answers
51 views

combining separate data into pairs after reading from excel so I can run regression

I have the following code that reads data from an excel spreadsheet: ...
0
votes
0answers
61 views

Fit a complicated function to a constant with NonlinearModelFit

I wish to fit a complicated parametric function (logder, with lambda parameters) to a constant (L) in order to minimize its dependence with the variable k in a given interval. To do that, I use a ...
0
votes
0answers
49 views

NonlinearModelFit not hunting for good values

I have the following data which come from complex values but I have turned them into a 3D list ...
0
votes
0answers
45 views

How do I add custom deviation when using LinearModelFit?

I have a set of data in the form a list S1={{x,y},{x,y}} etc. I also have a function that calculates a corrected standard deviation in the y direction for ...
0
votes
0answers
80 views

Expand a fitting using FindFit[]

I need to implement multidimensional optimization using FindFit[]. But it's essential to exclude some parameters from the main procedure of optimization and to move on from direct optimization in ...
0
votes
0answers
170 views

Extracting parameters from a fitted function

Let's say I have written a function which performs convolution and returns value calculated for the time, t. ...
0
votes
0answers
46 views

Troubles with FindFit for ODE (elaboration)

I have asked a question Troubles with FindFit for ODE and get a good-working answer from @belisarius. Nevertheless I need to clarify is it possible to define the same model with ...
0
votes
0answers
52 views

Using List/Histogram Data As A Weighted Function?

I have a list of data points that I would like to use as a weighted fucntion. The data represents the number of particles within a bin of a particle distribution. Ultimately I would like to multiply ...
0
votes
0answers
114 views

Non linear curve fit

I am trying to fit a non linear curve to my data which looks like following The code I am using is following. You can see I have six unknown variables ...
0
votes
0answers
72 views

Can not understand the code to join points into line segments

I'm reading the CDF file from Making Formulas… for Everything in wolframalpha blog. It's hard for me to understand the In[17] code of function pointListToLines. I especially want to know what the use ...
0
votes
0answers
207 views

Multi-peak fitting

Suppose we have a data set that looks like this: I have to fit this data to 9 peaks knowing μ and σ beforehand & have to ...
0
votes
0answers
83 views

How to perform a distribution fit test to censored data

With following code I will get an error: ...
0
votes
0answers
68 views

Using FindFit to return a list of possible best fits

Can I use some variant of FindFit that will return a list of the best fit and some worse fits, not just the best fit? This is for a function where the residual function can have several local ...
0
votes
0answers
92 views

Fitting a plane from a set of (x,y,z) values with uncertainties on 3 variables

I would like to fit a plane from a set of measurements (x,y,z) with uncertainties on the 3 variables. Currently I am using the command "LinearModelFit" that computes the best plane but I have a ...
0
votes
0answers
77 views

Convergence Problem using FindFit

I have the following input where there is a convergence problem in the FindFit as shown in the attached figure.The figure shows 2 plots: one of the real data and the other of the fitted line. Any ...
0
votes
0answers
67 views

No real number fitting double exponential in Mathematica

I am trying to fit a double exponential curve to my data, but I got the error saying there are non real number. Also I tried with starting values for my 4 parameters, but this does not work either. ...
0
votes
0answers
54 views

How do I constrain the result of fitting my non-linear model to be greater then 0

fitresulty21 = NonlinearModelFit[ydata21, {funfit[y, σ, A, B, x1, d, d/2], A > 0}, {{x1, 20}, {σ, 3}, {A, 200}, {B, 2000}, {d, 110}}, y]; ...
0
votes
0answers
608 views

histogram fit for probability density

I am trying to fit the (probability density) histogram of some data with the exponential function, but I am having difficulties. My raw data are in file called ...
0
votes
0answers
67 views

Supply parameter values in NormFunction of FindFit

As I understand the input to the NormFunction is a list of residuals. Is there a way to get parameter values into the NormFunction as well? I ran into a problem where the norm depends on the values of ...
0
votes
0answers
283 views

Non linear model fit mathematica

I want to fit experimental data (temp,alpha) to the following equation for calculating k and Ea -Log[alpha]^n = function(k,Ea,temp) However i do not know ...
0
votes
0answers
169 views

NonlinearModelFit with multiple parameters

I am now trying a slightly more complicated model which actually consists of finding the parameters of 2 particles in an Image (I attached an Plot of an image). Although I put very good initial values ...
0
votes
0answers
77 views

Fitting data set with series expansion

I have a function given in a form of a list: ScalarField={{$\epsilon$,$y_1$},..{1,$y_{3000}$}} It is defined in the range $(\epsilon,1)$ (spacing between grid points is homogeneous), where ...
0
votes
0answers
178 views

Using FindFit for step functions

Having used FindFit like so: ...
0
votes
0answers
115 views

Smoothing a function

NDsolve gives me a solution to a certain NL PDE. I want to evaluate the rate of exponential decay of the maxima of the solutions in time. So, I plot ...
0
votes
0answers
97 views

Inconsistent results in fits from NArgMin

EDIT: Just realized I had misspelled "inconsistent." I'm using version 7.0. I'm trying to fit a (noisy) data set to a large-order polynomial. (Just for context: there isn't a model for the ...
0
votes
0answers
336 views

Interpolating function as a model in Mathematica's procedures for fitting

Is it possible to use interpolating function with parameters as a model for NonLinearModel fit (and other integrated methods for fitting)? Similar question was already posted earlier - How do I find ...
0
votes
0answers
151 views

FindFit for dimension reduction?

Given an n-dimensional function, can I use FindFit to produce an approximate (n-k)-dimensional function? Here is a simplified illustration of what I am trying to do. I have $$f(x,a,b,\mu,\sigma) = ...
0
votes
0answers
372 views

Performance in parameter estimation from ParametricNDSolve using varied initial conditions

I have 250 data points from a timecourse exeriment in a list, with columns specifying (1) time, (2-4) initial conditions, (5) absorbance reading. I want to fit 4 parameters (k1, k2, k3, k4) in a DAE ...