0
$\begingroup$

enter image description here

I fitted simulation data with Gaussian fitting curve,

data25=Import["Downloads/n3/dmde_n3_e102_b25.dat", {"Data", {All}, {1, 2}}];
model25[c_] = ampl Evaluate[PDF[NormalDistribution[x0, sigma], c]]; 
fit = FindFit[data25, model25[c], {ampl, x0, sigma}, c]
g25 = Plot[{model25[c] /. fit}, {c, -1, 6}, Axes -> {False, True, False}, PlotRange -> {{-1, 6}, {0.0, 1.0}}] 

However, the simulation data show great deviation from the fitted curve. I want to know how much Sigma should have deviated.

$\endgroup$

closed as off-topic by corey979, MarcoB, happy fish, bbgodfrey, garej May 4 at 14:06

  • The question does not concern the technical computing software Mathematica by Wolfram Research. Please see the help center to find out about the topics that can be asked here.
If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Please provide the data! $\endgroup$ – Anton Antonov Apr 16 at 9:29
  • $\begingroup$ you can upload the data here: pastebin.com $\endgroup$ – Epsilon Apr 16 at 9:30
  • 2
    $\begingroup$ The fit looks OK. It seems to minimize the residuals of the single Gaussian. Obviously, the model is not suitable, i.e. a single Gaussian doen't fit the data. $\endgroup$ – Markus Roellig Apr 16 at 13:48
5
$\begingroup$

I am not sure what this part of the question means:

I want to know how much Sigma should have deviated.

I assume by finding a good fit using relatively few Gaussians OP would be able to find the desired answer.

I extracted the data from the image following this post: https://blog.wolfram.com/2012/01/04/how-to-count-cells-annihilate-sailboats-and-warp-the-mona-lisa/ .

Here is the data:

data = {{222.833, 224.833}, {220.188, 221.125}, {217.5, 
  221.5}, {216.773, 218.227}, {221.346, 217.962}, {213.5, 
  217.5}, {215.625, 215.375}, {212.786, 213.286}, {209.5, 
  211.3}, {211.625, 209.375}, {218.5, 206.}, {228.206, 
  203.912}, {223., 201.}, {207.147, 199.971}, {227.063, 
  200.125}, {229.2, 198.1}, {207.921, 195.395}, {208., 191.}, {231.98,
   183.86}, {235., 184.5}, {205.409, 182.409}, {234.676, 
  180.559}, {236.833, 175.833}, {240.115, 174.654}, {200.071, 
  170.929}, {197.029, 170.147}, {236., 171.}, {200.55, 165.8}, {236.5,
   167.}, {238.5, 161.5}, {193.5, 157.5}, {287., 156.}, {195.5, 
  153.5}, {148.147, 151.971}, {192.241, 153.352}, {243.63, 
  150.37}, {290., 151.}, {192.214, 148.595}, {187., 148.}, {152.5, 
  145.5}, {190.643, 144.857}, {187.885, 143.808}, {142.115, 
  143.577}, {146.5, 143.3}, {180.833, 142.667}, {243.5, 
  143.}, {287.375, 142.75}, {151.5, 142.5}, {294.5, 142.5}, {139.5, 
  141.167}, {281.615, 140.346}, {187.25, 140.813}, {277.583, 
  140.25}, {258.9, 138.9}, {137.9, 137.9}, {156., 138.}, {179.409, 
  138.318}, {190.125, 138.063}, {247.625, 138.375}, {275.8, 
  138.3}, {290.5, 138.5}, {186.5, 137.5}, {286.362, 
  138.293}, {158.625, 136.375}, {265., 136.5}, {297.5, 
  136.7}, {271.833, 133.542}, {283.658, 134.5}, {188., 134.}, {295., 
  134.3}, {164.5, 133.25}, {176.5, 133.5}, {259.857, 
  132.643}, {281.643, 131.929}, {138.6, 131.3}, {168.222, 
  131.333}, {251., 129.}, {297.5, 129.5}, {301.026, 
  128.553}, {136.786, 127.69}, {275.056, 127.778}, {265.833, 
  125.5}, {297.206, 126.088}, {174.25, 125.}, {269., 125.5}, {165.8, 
  125.4}, {181.5, 124.458}, {135.978, 123.152}, {177.132, 
  123.5}, {259.409, 123.318}, {268.5, 123.}, {299.944, 
  123.056}, {132.5, 121.192}, {257.944, 121.167}, {136.3, 
  119.5}, {300.761, 119.152}, {134.318, 115.318}, {303.833, 
  115.352}, {132.167, 113.389}, {305.5, 112.}, {302.591, 
  111.136}, {130., 110.786}, {132.5, 109.5}, {305.808, 
  109.423}, {128.423, 107.192}, {132., 106.5}, {306.643, 
  106.571}, {306.397, 103.086}, {122.206, 92.7353}, {309.654, 
  91.0385}, {118.583, 85.1667}, {118.167, 80.9667}, {114.773, 
  80.2273}, {315.5, 80.}, {114.109, 71.1087}, {328.167, 
  71.5833}, {101.3, 69.18}, {106.5, 69.7857}, {109.9, 70.3}, {324.577,
   69.1923}, {337.038, 68.3462}, {97.5, 67.}, {106.727, 
  66.0909}, {327.917, 67.25}, {92.9286, 66.0714}, {88., 65.}, {344.5, 
  65.5}, {350.1, 65.1}, {101.643, 63.5}, {353.5, 64.5}, {359., 
  64.5}, {67.5, 63.5}, {364.5, 63.5}, {95.8684, 63.4474}, {98.2143, 
  62.3571}};

  ListPlot[data]

enter image description here

Then I applied the procedure described in this answer using Gaussian bases instead of a Sin/Cos one.

The obtained fit is:

qFunc

(* 61.406 E^(-(1/800) (-290 + x)^2) + 49.9485 E^(-((-290 + x)^2/12800)) + 
 118.492 E^(-(1/800) (-220 + x)^2) + 17.5995 E^(-((-220 + x)^2/12800)) + 
 53.521 E^(-(1/800) (-150 + x)^2) + 64.2894 E^(-((-150 + x)^2/12800)) *)

Here is a plot of the data and the fit function:

Show[{ListPlot[data, PlotRange -> All], 
  Plot[qFunc, {x, Min[data[[All, 1]]], Max[data[[All, 1]]]}, PlotStyle -> Red,
    PerformanceGoal -> "Quality"]}]

enter image description here

(Note that the good fit is obtained with OP's image red points, not OP's data.)

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.