# Regression Lines

### From Grapheme wiki

## Contents

### Overview

Regression analysis aims to create a mathematical model that can be used to predict the values of a dependent variable based upon the values of an independent variable.

A regression analysis involves one (or more) independent variables and one dependent variable the values of which are assumed to depend by the independent variables. In the simplest of the cases, a regression only involves an independent and a dependent variable and can be used in conjunction with scatter plot.

The simplest regression model assumes a linear relationship between variables, thus resulting in a straight-line or linear relationship. Clearly arbitrary mode complex regression models can be defined. Most commons are based on polynomial, exponential or trigonometric expression.
Regression models are often fitted using the least squares approach, but they may also be fitted in other ways, such as by minimizing the error between predicted points and real values with different norms (as with least absolute deviations regression).
Detailed descriptions on the most commonly used regression models can be found here:

• https://en.wikipedia.org/wiki/Linear_regression

• https://en.wikipedia.org/wiki/Nonlinear_regression

### Use cases

Typical examples of regressions are so called trend-lines. A trend line represents the trend of a dependent variable against an independent one. It tells whether a particular data set (say stock prices) have increased or decreased over positive variations of the independent variable, typically the period of time. Trend lines are sometimes used in business analytics to show changes in data over time. This has the advantage of being simple allowing to interfere consequences for a particular action or event.

### Within Grapheme

To create a *Regression Line* within Grapheme, click on **2D Charts** → **Scatter** from the toolbar of the Chart Explorer. Assign a name to the data series, select the *Source Table* and the *View* of the table containing the desired data sets. Select which columns should be used to define the X and Y axes.

Click on the **New Regression Line** icon, move to the series selector on the left side of the wizard and click on the regression series.

Access the Regression Line editor by clicking on the icon next to the Y column selector, a wizard will guide the user in the selection of the regression algorithm and corresponding setting options.