scatterplot2.JGR: Draws a scatterplot of bivariate data
In CADStat: Provides a GUI to Several Statistical Methods

Description Details See Also

Creates a scatterplot - a plot displaying the relationship between two variables. A linear regression line or loess smooth can be overlayed.

A scatterplot provides a graphical means of determining the relationship between two variables. Important relationships that can be observed are linear, higher-order polynomial, exponential, or logarithmic. Along with the general pattern, it is possible to qualitatively determine the strength of the relationship. The "closer" or "tighter" the points are to the general shape, the stronger the relationship. A scatterplot is also a useful tool for identifying potential univariate or bivariate outliers (observations that are much larger or smaller than the other data points).

After gaining insight into the general relationship of the variables, a quantitative analysis method may be more easily chosen:

Correlation analysis, which helps determine the strength of the linear relationship between two variables.
Linear regression, which fits a linear model to two or more variables.
Quantile regression, which fits a model to conditional quantiles of the dependent variable rather than to the conditional mean.

User Interface

To create a scatterplot, select "Scatterplot" from the "Analysis Tools" menu. A dialog box will appear that allows the user to enter plotting parameters. Select the data set of interest from the pull-down menu, or browse for a tab-delimited text file. The Data Subsetting tab can be used to select a subset of the data file by choosing a variable from the pull down menu and then selecting the levels of that variable to include. You can hold down the <CTRL> key to select multiple levels. A separate plot will be produced for each unique setting of the subsetting variables. Select a variable to plot on the x-axis and a different variable to plot on the y-axis. A regression fit can be overlaid on the scatterplot. If Linear Regression Line is selected, a straight line fit is drawn. If Loess Smooth is selected, a nonparametric loess fit is drawn. You may change the axes labels and plot title by typing them in the Labels dialog. The output is simply the scatterplot graph with any overlaid fits requested.

To learn about boxplots, see boxplot.

To learn about correlation analysis, see cor.

To learn about linear regression, see lm.

To view the help file for the general R plotting function, see plot.

CADStat documentation built on May 1, 2019, 6:51 p.m.