Regression model for multiple data sets

Hi, I have 54 cases of data with 6 independent variable which i have extracted from my simulations. one of my variables is the range which is simply 720-1440 but the other variables are assigned values for my simulation. I'm having a hard time finding the suitable regression method which allows me to find the expression for the parameter expressed by the variables.If someone could point me toward the right direction that would be much appreciated

[Sam Chak]

Hi @Amir Hessari

Can you attach a sample of the data?

This may help to suggest a suitable regression method.

[Amir Hessari]

X is always the given values, but V1-V5 change per case. Basicaly each case that values of V1-V5 a whole graph is generated were x and y values are the X and Y respectively and I'm looking find the relation between the changes in V1-V5 and Y value

Answer 1

[Akshat Dalal]

Hi Amir,

I understand that you have multiple independent variables and want a suitable regression method to fit your model. When dealing with multiple independent variables, you can use multivariate regression methods to determine the expression for the parameter. Here are a few possible approaches to consider:

1. Multiple Linear Regression: If you have multiple independent variables and a single dependent variable, multiple linear regression can be a good starting point. This method models the relationship between the independent variables and the dependent variable as a linear equation. You could refer the following documentation to learn more: https://www.mathworks.com/help/stats/regress.html
2. Polynomial Regression: If the relationship between the independent variables and the dependent variable is nonlinear, you can consider polynomial regression. This method extends linear regression to fit a polynomial equation to the data. You could refer the following documentation to learn more: https://www.mathworks.com/help/matlab/ref/polyfit.html
3. Ridge Regression: If you have many independent variables and multicollinearity among the variables, ridge regression can be useful. This method adds regularization to the regression model to handle multicollinearity and prevent overfitting. You could refer the following documentation to learn more: https://www.mathworks.com/help/stats/ridge.html
4. Lasso Regression: This method also adds regularization to the regression model. It is like Ridge regression, and both often yield better results than traditional linear regression models. You could refer the following documentation to learn more: https://www.mathworks.com/help/stats/lasso.html

I hope this helps.