Question

Model building: What plot will you generate to motivate that following model will be

appropriate to fit to the data

a) Linear Regression

b) Logistic Regression

c) Time series

Answer 1

LINEAR REGRESSION:

A data model expressly describes a relationship between predictor and response variables. Linear regression fits an information model that's linear within the model coefficients. The most common variety of regression could be a least-squares work, which can fit both lines and polynomials, among other linear models.
Before you model the affiliation between pairs of quantities, it is a good idea to perform correlation analysis to establish if a linear relationship exists between these quantities. Be aware that variables will have nonlinear relationships, which correlation analysis cannot detect. For more information, see Linear Correlation.
The MATLAB Basic Fitting UI helps you to suit your information, so you can calculate model coefficients and plot the model on top of the data. For associate example, see Example: Using Basic Fitting UI. You also will use the MATLAB polyfit and polyval functions to suit your information to a model that's linear within the coefficients. For an example, see Programmatic Fitting.
If you wish to suit information with a nonlinear model, transform the variables to make the relationship linear. Alternatively, attempt to work a nonlinear perform directly exploitation either the Statistics and Machine Learning Toolbox nlinfit perform, the improvement Toolbox lsqcurvefit perform, or by applying functions within the Curve Fitting Toolbox™.
This topic explains how to:
Perform simple linear regression using the \ operator.
Use correlation analysis to work out whether or not 2 quantities area unit associated with justify fitting the information.
Fit a linear model to the data.
Evaluate the goodness of work by plotting residuals and searching for patterns.
Calculate measures of goodness of work R2 and adjusted R2

Fitting Data with Curve Fitting Toolbox Functions:
The Curve Fitting tool cabinet code extends core MATLAB practicality by enabling the subsequent data-fitting capabilities:
Linear and nonlinear parametric fitting, including standard linear least squares, nonlinear least squares, weighted least squares, constrained least squares, and robust fitting procedures
Nonparametric fitting
Statistics for determining the goodness of fit
Extrapolation, differentiation, and integration
Dialog box that facilitates data sectioning and smoothing
Saving match ends up in numerous formats, as well as MATLAB code files, MAT-files, and space variables