The histogram, or relative frequency, plot is the most commonly used in risk analysis. It is produced by grouping the data generated for a model's output into a number of bars or classes. The main advantage of a histogram plot is how easy it is to read the realistic range of the variable, its rough location, and any peaks.
The density plot is similar to the histogram, but a smoothing algorithm is used to create a curve, with an area under the curve standardized to 1, so it's useful when overlaying multiple outputs.
These figures allow us to easily recognize common distributions such as the Normal and Uniform, and we can see whether a variable is skewed.
| Discrete | Continuous | Density |
|---|---|---|
|
|
|
This section discusses the following:
Difficulty of interpreting the vertical scale
Effect of varying number of bars
Plotting a variable with discrete and continuous elements
Relationship between cdf and density (histogram) plots
