S3 methods for manipulating eDist objects.

S3 methods for manipulating eDist objects

# S3 method for class 'eDist'
logLik(object, ...)

# S3 method for class 'eDist'
AIC(object, ..., k = 2)

AICc(object)

# S3 method for class 'eDist'
AICc(object, ...)

# S3 method for class 'eDist'
vcov(object, ..., corr = FALSE)

BIC(object)

# S3 method for class 'eDist'
BIC(object, ...)

MDL(object)

# S3 method for class 'eDist'
MDL(object, ...)

# S3 method for class 'eDist'
print(x, ...)

# S3 method for class 'eDist'
plot(x, ...)

Arguments

object,: x An object of class eDist, usually the output of a parameter estimation function.
...: Additional parameters
k: numeric, The penalty per parameter to be used; the default k = 2 is the classical AIC.
corr: logical; should vcov() return correlation matrix (instead of variance-covariance matrix).
x,: A list to be returned as class eDist.
plot: logical; if TRUE histogram, P-P and Q-Q plot of the distribution returned else only parameter estimation is returned.

Note

The MDL only works for parameter estimation by numerical maximum likelihood.

References

Myung, I. (2000). The Importance of Complexity in Model Selection. Journal of mathematical psychology, 44(1), 190-204.

Author

A. Jonathan R. Godfrey, Sarah Pirikahu, and Haizhen Wu.

Examples

X <- rnorm(20)
est.par <- eNormal(X, method ="numerical.MLE")
logLik(est.par)
#> [1] -32.29877
AIC(est.par)
AICc(est.par)
#> [1] 69.30341
BIC(est.par)
#> [1] 70.58899
MDL(est.par)
#> [1] 35.24907
vcov(est.par)
#>               mean            sd
#> mean  7.399685e-02 -6.130990e-08
#> sd   -6.130990e-08  3.699843e-02
vcov(est.par,corr=TRUE)
#>               mean            sd
#> mean  1.000000e+00 -1.171743e-06
#> sd   -1.171743e-06  1.000000e+00
print(est.par)
#> 
#> Parameters for the Normal distribution. 
#> (found using the  numerical.MLE method.)
#> 
#>  Parameter     Type  Estimate      S.E.
#>       mean location 0.2499489 0.2720236
#>         sd    scale 1.2165266 0.1923498
#> 
#> 
plot(est.par)