Quadratic model:
A quadratic model is a variant of mathematical model utilized in statistics, and multiple fields to describe the relationship between dependent and independent variable by fitting a quadratic equation. This is a form of polynomial regression where the relationship between the variables is modeled as a quadratic function.
The general form of a quadratic model is as follows:
y= ax2+bx+c
In this equation:
- y represents the variable which is dependent
- x represents the variable which is independent
- a , b and c are constants and are not equal to 0(zero)
Quadratic models are applied when there is a relationship in between the dependent and independent variables is not linear but rather follows a curved, U-shaped, or parabolic pattern. Once the model is fitted, it can be used for making predictions or understanding the relationship between the variables.
Overfitting:
Overfitting erupts when a model learns disturbance in the training data, resulting to poor performance on unseen data. It results in insufficient data. Preventing overfitting includes simplifying the model, collecting more data, selecting relevant features, using regularization, it also includes cross-validation. This results in minimal generalization to new and unseen data.