#COMPARE HEIGHTS WITH DOT PLOT FULL#
#COMPARE HEIGHTS WITH DOT PLOT CODE#

The first row of plots displays the height variable on the y axis and the variables weight, leafarea, shootarea and flowers on the x axis for each of the four plots respectively. The panels on the diagonal give the variable names. Interpretation of the pairs plot takes a bit of getting used to. # or we could use the equivalent # pairs(flowers) We’ll also introduce an x axis label using the xlab = argument. When we use the formula notation with boxplot() we can use the data = argument to save some typing. For example, let’s plot our weight variable again, but this time see how this changes with each level of nitrogen. If we want examine how the distribution of a variable changes between different levels of a factor we need to use the formula notation with the boxplot() function. If the median line is more or less in the middle of the box (between the upper and lower quartiles) and the whiskers are more or less the same length then you can be reasonably sure the distribution of your data is symmetrical. The neat thing about boxplots is that they not only provide a measure of central tendency (the median value) they also give you an idea about the distribution of the data. We recommend using boxplots in combination with Cleveland dotplots to identify potential unusual observations (see the next section of this Chapter for more details). This doesn’t mean they are unusual, just that they warrant a closer look. Data points that are plotted outside the the whiskers represent potential unusual observations. The dotted vertical lines are called the whiskers and their length is determined as 1.5 x the inter quartile range. The distance between the upper and lower quartiles is known as the inter quartile range and represents the values of weight for 50% of the data.

The upper line of the box is the upper quartile (75 th percentile) and the lower line is the lower quartile (25 th percentile). The thick horizontal line in the middle of the box is the median value of weight (around 11 g). We can also include a y axis label using the ylab = argument.īoxplot(flowers $weight, ylab = 'weight (g)') For example, let’s create a boxplot of the variable weight from our flowers data frame. To create a boxplot in R we use the boxplot() function. Of course, it’s up to you what you do but if you’re tempted to use bar plots just Google ‘dynamite plots are evil’ or see here or here for a fuller discussion. The problem with bar plots (aka dynamite plots) is that they hide important information from the reader such as the distribution of the data and assume that the error bars (or confidence intervals) are symmetric around the mean. We suggest that you try to use boxplots as much as possible when exploring your data and avoid the temptation to use the more ubiquitous bar plot (even with standard error or 95% confidence intervals bars). The reason we love them is their ease of interpretation, transparency and relatively high data-to-ink ratio (i.e. they convey lots of information efficiently).

#COMPARE HEIGHTS WITH DOT PLOT FULL#

Boxplots (or box-and-whisker plots to give them their full name) are very useful when you want to graphically summarise the distribution of a variable, identify potential unusual values and compare distributions between different groups.

OK, we’ll just come and out and say it, we love boxplots and their close relation the violin plot. The top left plot is type = 'l', the top right type = 'b', bottom left type = 'o' and bottom right is type = 'c'. See later in the Chapter for more details about this. We’re just using this to split the plotting device so we can fit all four plots on the same device to save some space.

#COMPARE HEIGHTS WITH DOT PLOT CODE#

Don’t worry about the par(mfrow = c(2, 2)) line of code yet. For example, let’s use our skills from Chapter 2 to generate two vectors of numbers ( my_x and my_y) and then plot one against the other using different type = values to see what type of plots are produced. You can plot just the points ( type = 'p', this is the default), just lines ( type = 'l'), both points and lines connected ( type = 'b'), both points and lines with the lines running through the points ( type = 'o') and empty points joined by lines ( type = 'c'). You can also specify the type of graph you wish to plot using the argument type =. Plot(flowers $shootarea ~ flowers $weight)īoth of these two approaches are equivalent so we suggest that you just choose the one you prefer and go with it.

1.4.2 Integrated developement environements.

Compare heights with dot plot