chemVI: Chemical Variable Importance for Floating Percentile Model...

In RFPM: Floating Percentile Model

Chemical Variable Importance for Floating Percentile Model Benchmarks

Description

Generate statistics describing the relative importance of chemicals among benchmarks generated by FPM

Usage

chemVI(data, paramList, ...)

Arguments

data	data.frame containing, at a minimum, chemical concentrations as columns and a logical Hit column classifying toxicity
paramList	character vector naming columns of data containing concentrations
...	additional arguments passed to chemSig, chemSigSelect, and FPM

Details

The purpose of chemVI is to inform the user about the relative influence of each chemical over the sediment quality benchmarks generated by FPM. Three statistics are generated: chemDensity, MADP, dOR, dFM, and dMCC. The chemDensity statistic (which is also generated by FPM) describes how little a particular chemical's value increased within the floating percentile model algorithm. Low chemDensity (close to 0) means that the value was able to increase substantially within the algorithm without triggering one or more of the criteria for stopping the algorithm (see ?FPM), whereas high chemDensity (close to 1) indicates the final benchmark for that chemical did not float (increase) much before being locked in. In other words, low chemDensity might be interpreted as relatively low importance. We caution against using this metric in isolation, as it is the more difficult to interpret of the three. The MADP statistic (or mean absolute difference percent) is calculated by sequentially dropping each chemical from consideration, recalculating the benchmarks for the remaining chemicals, and then determining how much each benchmark changed (as a percent of the original value). Thus, the MADP is a measure of a chemical's influence over other benchmarks. The dOR statistic is the difference between the overall reliability of benchmarks with all chemicals versus without each chemical. dFM and dMCC are similar to the dOR statistic, but for the Fowlkes-Mallows Index and Matthew's Correlation Coefficient. In any case, larger positive values indicate a greater impact of a chemical on the overall predictive performance of floating percentile model benchmarks. Small values (close to 0) indicate low influence. Larger negative values indicate that the chemical actually adversely impacts toxicity predictions. If there are chemicals with negative values, consider reevaluting the data without the associated chemical or using optimFPM or cvFPM to optimize the overall reliability prior to running FPM and chemVI.

Value

data.frame with 2 columns

See Also

chemSig, chemSigSelect, optimFPM, cvFPM, FPM

Examples

paramList = c("Cd", "Cu", "Fe", "Mn", "Ni", "Pb", "Zn")
chemVI(h.tristate, paramList, testType = "np")
chemVI(h.tristate, paramList, testType = "p")

RFPM documentation built on Oct. 26, 2023, 1:08 a.m.