Binary Logistic Regression Curve

25 次查看（过去 30 天）
Jonathan Moorman
Jonathan Moorman 2020-7-2
回答： Aditya Patil 2020-8-17
Hello! I am trying to create a logistical regression curve for my binary data in Figure 3. Is this possible to do in MATLAB, and if so, how could it be done? My code is below? Thanks
%Figure 2 Graphing
scatter(FactoredLength, FactoredAmplitude,5,'filled')
hold on
coefficients = polyfit(FactoredLength, FactoredAmplitude, 1);
xFit = linspace(min(FactoredLength), max(FactoredLength), 1000);
yFit = polyval(coefficients , xFit);
plot(xFit, yFit, 'r-', 'LineWidth', 2);
xlabel('Factored Length')
ylabel('Probability')
grid on;
hold off
figure
% Making data binary
Probability = ((exp(log10(FactoredAmplitude)))./(1+exp(log10(FactoredAmplitude))));
yHat(Probability > app.ThreshHoldValueEditField.Value) = 1;
yHat(Probability < app.ThreshHoldValueEditField.Value) = 0;
%Figure 3 Graphing
scatter(FactoredLength,yHat)
xlabel('Factored Length')
ylabel('Probability')

请先登录，再回答此问题。

采纳的回答

Aditya Patil
Aditya Patil 2020-8-17
Use the fitglm function to fit logistic regression model to data. Check the following code for example,
% Create random data
x = rand(100, 1);
y = x > 0.5;
y(1:50) = x(1:50) > 0.3; % To avoid perfect seperation
% Fit model
mdl = fitglm(x, y, "Distribution", "binomial");
xnew = linspace(0,1,1000)'; % test data
ynew = predict(mdl, xnew);
scatter(x, y);
hold on;
plot(xnew, ynew);
This will give following output.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Statistics and Machine Learning Toolbox 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by