ppcc: The Probability Plot Correlation Coefficients Plot
In AUMath-AdvancedR2018/StatEngPlots: PPCC Plot

ppcc() takes a vector of data x and finds correlation coefficients between x and a guessed distribution for several different shape values. The function ppcc() returns a plot of the correlation coefficients against the shape parameters and return the highest correlation and the best estimated shape parameter. The supported distributions are: Weibull, Normal, Log-Normal, Poisson and Exponential.

1	ppcc(x, distribution = "weibull", minshape = 1, maxshape = 10, steps1 = 30, steps2 = 30, plots = FALSE, brks = 70, bandw = "nrd0", returncor = FALSE))

`x`	The datavector to be analyzed.
`distribution`	The guessed distribution. Supported distributions are: Weibull, Normal, Log-Normal, Poisson and Exponential. Default is set so Weibull.
`minshape`	The minimum shape value to use. Default set to 1.
`maxhsape`	Tha maximum shape value to use. Default set to 10.
`steps1`	The total number of correlation coefficients to calculate between `minshape` and `maxshape`. `steps1` is not used in the Weibull case if the shape parameter is smaller than 1. Default set to 30.
`steps2`	The same as `steps1`, but `steps2` is only used in the Weibull case if the shape parameter is smaller than 1. Default set to 30.
`plots`	If set to `TRUE`; returns a histogram with the estimated density and the true density for the best estimated shape parameter. Default is set to `FALSE`.
`brks`	The number of breaks in the histogram, which is returned when `plots` is set to `TRUE`. Default is set to 70.
`bandw`	The smoothing bandwidth which `R` uses when estimating the density of `x`. Important: use the \itemppcc() function more than once with `plots = TRUE` and find the best bandwidth, if the results are very unusual. Default is set to "nrd0".
`returncor`	If set to `TRUE`, hte `ppcc()` function returns a matrix with the used shape parameters and the corresponding correlation coefficients. Deafult is set to `FALSE`.

# Simulate a Weibull distributed dataset:
x = rweibull(1000, 2)
# Use the ppcc() function to find the best shape parameter:
ppcc(x)

# Simulate a Poisson distributed dataset:
x = rpois(1000, 3)
# Use th ppcc() function to estimate the best lambda:
ppcc(x, distribution = "poisson")
# Get a histogram with the estimated density and the true density for the best estimated lambda:
ppcc(x, distribution = "poisson", plots = TRUE)