InfluentialPoints.com
Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site

 

 

Simple scatterplots and 'fitted' lines using R

Scatterplots

R can produce a simple scatterplot, for variable y on x using these instructions:

Giving:

 

The simplest way to fit a straight line

The simplest way to get R to add a fitted line to a scatterplot is to use the following instructions - which perform what is known as a 'linear regression'. We consider why they work in Unit 12. Note, this assumes x and y contain the same number of values, and none are missing (=NA).

Giving:

 

If you feel this line is not a very good 'fit' to these data, it is because their spread is very uneven. One way to solve this is to rescale the values in variables x and y.

A more complicated way to add a 'fitted line'

To rescale the data and fit a line using R's 'linear modelling' function, we could use the following instructions: Note, these instructions are more complicated than those above because they also use distinctive variable names - and provide headings for the graph.

Giving:

 

Another way to add a 'fitted line'

The following instructions use the calculator formula to fit a line to the rescaled data:

Giving: