Search Results

Sounds like a "waffle chart" -- here's one R implementation. In general you can make such a chart with a scatterplot of square markers placed in a grid. …

Stephen Few (unsuccessfully) addressed this issue in a 2007 article, Dashboard Confusion Revisited and suggested the term "faceted analytical display": A “faceted analytical display” is a set of i …

The xspline function offers a generalization of Catmull-Rom splines, which sounds like what you want. From the examples:

Here's a quick R attempt starting with your code. ############################# # Hough transform: # for each point find slopes and intercepts that go through the line ############################# …

Something like these quartile bands may work. You can add more quantiles if more detail is needed, but sometimes less is more. The quartiles will be enough to get a sense of the spread and the skewnes …

You can automate the process within JMP using the JSL (JMP Scripting Language). Start by selecting Script > Save to Script Window from the analysis contextual red-triangle menu. That will give you a s …

If you check the source (tar.gz), you can see how the plot is made by gbm.step. Most of the settings, like the labels and colors, are hard-coded. But it's possible to suppress the generated plot and m …

With three numbers of disparate sizes you may be better off with a table instead of a graph. If you have to transform, you're starting to loose some of the benefit of visual encoding, especially for p …

In JMP, these are called Profilers or Profile Plots: Not sure about R, but I found a CV question involving a similar R plot using a function called "profile". …

It looks like your times are growing linearly, so it seems reasonable to extrapolate from a linear model, as commenter Zheyuan Li suggests. The caveat is that who know what really happens after 100 …

This is an interesting data set to try to represent graphically, partly because it's not really categorical. Both 3-level factors are ordinal and there is possible interplay between them (presumably, …

No, a ternary plot is only able to collapse three dimensions into two because the third variable is dependent on the other two. z = 100% - x - y. Instead, you might try a 2D scatter plot for two of y …

Such extreme p-values occur more often in fields with very large amounts of data, such as genomics and process monitoring. In those cases, it's sometimes reported as -log10(p-value). See for example, …

You mean you don't want a line plot like this? :) Time is a natural for the X axis and line plots. Here's a better view using a small multiples approach. Sometimes it helps to order the panels …

Your Feature variable with 64 different feature combinations (or 63 if you don't count the empty one) is equivalent to 6 independent binary variables. So, adding k, you have 7 factors and 2 responses. …