Description Usage Arguments Details Value References See Also Examples

Estimation of conditional quantiles using optimal quantization
when `X`

is bivariate.

1 2 3 4 5 | ```
QuantifQuantile.d2(X, Y, alpha = c(0.05, 0.25, 0.5, 0.75, 0.95),
x = matrix(c(rep(seq(min(X[1, ]), max(X[1, ]), length = 20), 20),
sort(rep(seq(min(X[2, ]), max(X[2, ]), length = 20), 20))), nrow = 2, byrow =
TRUE), testN = c(110, 120, 130, 140, 150), p = 2, B = 50, tildeB = 20,
same_N = TRUE, ncores = 1)
``` |

`X` |
matrix of covariates. |

`Y` |
vector of response variables. |

`alpha` |
vector of order of the quantiles. |

`x` |
matrix of values for |

`testN` |
grid of values of |

`p` |
L_p norm optimal quantization. |

`B` |
number of bootstrap replications for the bootstrap estimator. |

`tildeB` |
number of bootstrap replications for the choice of |

`same_N` |
whether to use the same value of |

`ncores` |
number of cores to use. Default is set to 1 (see Details below). |

This function calculates estimated conditional quantiles with a method based on optimal quantization when the covariate is bivariate. The matrix of covariate

`X`

must have two rows (dimension). For other dimensions, see`QuantifQuantile`

or`QuantifQuantile.d`

. The argument`x`

must also have two rows.The criterion for selecting the number of quantizers is implemented in this function. The user has to choose a grid

`testN`

of possible values in which`N`

will be selected. It actually minimizes some bootstrap estimated version of the ISE (Integrated Squared Error). More precisely, for`N`

fixed, it calculates the sum according to`alpha`

of`hatISE_N`

and then minimizes the resulting vector to get`N_opt`

. However, the user can choose to select a different value of`N_opt`

for each`alpha`

by setting`same_N=FALSE`

. In this case, the vector`N_opt`

is obtained by minimizing each column of`hatISE_N`

separately. The reason why`same_N=TRUE`

by default is that taking`N_opt`

according to`alpha`

could provide crossing conditional quantile curves (rarely observed for not too close values of`alpha`

). The function`plot.QuantifQuantile`

illustrates the selection of`N_opt`

. If the graph is not decreasing then increasing, the argument`testN`

should be adapted.This function can use parallel computation to save time, by simply increasing the parameter

`ncores`

. Parallel computation relies on`mclapply`

from`parallel`

package, hence is not available on Windows unless`ncores`

=1 (default value).

An object of class `QuantifQuantile`

which is a list with the
following components:

`hatq_opt` |
A matrix containing the estimated conditional
quantiles. The number of columns is the number of considered values for |

`N_opt` |
Optimal selected value for |

`hatISE_N` |
The matrix of estimated ISE provided by our selection
criterion for |

`hatq_N` |
A 3-dimensional array containing the estimated
conditional quantiles for each considered value for |

`X` |
The matrix of covariates. |

`Y` |
The vector of response variables. |

`x` |
The considered vector of values for |

`alpha` |
The considered vector of order for the quantiles. |

`testN` |
The considered grid of values for |

Charlier, I. and Paindaveine, D. and Saracco, J.,
*Conditional quantile estimation through optimal quantization*,
Journal of Statistical Planning and Inference, 2015 (156), 14-30.

Charlier, I. and Paindaveine, D. and Saracco, J.,
*Conditional quantile estimator based on optimal
quantization: from theory to practice*, Submitted.

`QuantifQuantile`

and `QuantifQuantile.d`

for other dimensions.

`plot.QuantifQuantile`

,
`print.QuantifQuantile`

, `summary.QuantifQuantile`

1 2 3 4 5 6 7 8 9 10 | ```
## Not run:
#(a few seconds to execute)
set.seed(164964)
n <- 1000
X <- matrix(runif(n*2,-2,2),ncol=n)
Y <- apply(X^2,2,sum)+rnorm(n)
res <- QuantifQuantile.d2(X,Y,testN=seq(90,140,by=10),B=20,tildeB=15)
res2 <- QuantifQuantile.d2(X,Y,testN=seq(90,150,by=10),B=20,tildeB=15,same_N=FALSE)
## End(Not run)
``` |

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.