symbolic.r: The Symbolic Correlation

In jjt7549/intervalreg: Regression for Interval-valued Data

Description

The symbolic correlation coefficient, r, proposed by Billard(2007, 2008) and applied to the regression problem by Xu(2010), measures the correlation between the predicted values and the observed values.

Usage

symbolic.r(model)

Arguments

model

imcmuni or imcmtn object, etc..

References

Billard(2007, 2008). Sample covariance functions for complex quantitative data

Xu(2010), Symbolic Data Analysis: Interval-Valued Data Regression

Examples

set.seed(2017)
x1_L = rnorm(30, 3, 0.01) - rnorm(30, 0, 0.01)
x1_U = rnorm(30, 3, 0.01) + rnorm(30, 3, 0.01)
x2_L = runif(30, 1.5, 3) - runif(30, 0, 1)
x2_U = runif(30, 1.5, 3) + runif(30, 1, 2)
y_L = x1_L + x2_L
y_U = x1_U + x2_U
temp <- as.data.frame(cbind(y_L, y_U, x1_L, x1_U, x2_L, x2_U))
m1 <- imcmtn(cbind(y_L, y_U) ~ x1_L + x1_U + x2_L + x2_U, data = temp, b = 100)
symbolic.r(m1)

jjt7549/intervalreg documentation built on May 19, 2019, 11:40 a.m.