Histograms are a convenient way of summarizing large data sets, but they come with some pretty severe limitations. In particular, histograms are inherently discrete; they are not function we can nicely eveluate at any given point. Kernel density estimate provide another way to visualize a data set that also provide the user a function that is a continuous approximation to the distribution. To use the kernel density estimate calculator below, input your sample data as a comma separated list and hit go! The code will use the square-root choice for the number of bins in the normalized density histogram and compute the optimal kernel bandwith [1]. For your convenience, I have preset the calculator to use the Old Faithful eruption time data [2] consisting of the time (in seconds) of 272 eruptions.
Plot Min: , Plot Max: , Number of Points:
Kernel Bandwidth :
References
[1] B. W. Silverman, Density estimation for statistics and data analysis, Chapman & Hall, London, 1986[2] https://www.stat.cmu.edu/~larry/all-of-statistics/=data/faithful.dat
