apca: Absolute Principal Component Analysis (APCA)

In kralljr/handles: HANdles Detection Limits when Estimating Sources

Description

apca performs APCA on daily PM2.5 constituent concentrations

Usage

apca(x, ...)

## Default S3 method:
apca(data, tots = NULL, nsources = NULL, adjust = NULL,
  mdl = NULL, cut = 1, type = "apca", mons = NULL, i = NA,
  print = F, ...)

Arguments

data	data frame of daily constituent concentrations with date as first column
tots	vector of total concentrations (total PM2.5) for each day. If null, uses rowSums(data)
nsources	number of sources. If null, uses number of eigenvalues of the correlation matrix greater than one.
adjust	method to adjust censored concentrations below minimum detection limits (MDLs). If null, uses complete case data
mdl	either a vector of mdls corresponding to each constituent or a matrix of mdls corresponding to each constituent and each day.
cut	cutoff for eigenvalues. Only used if nsources is NULL
type	Source apportionment method (apca or mapca)
mons	vector of monitors corresponding to data
i	monitor number (for printing)
print	whether to print monitors without temporal variability

Details

This is a function to estimate PM2.5 source profiles and daily PM2.5 source concentrations from PM2.5 constituent concentrations observed at ambient monitors (e.g. EPA Chemical Speciation Network). Works on dataframe where the first column is date and all subsequent columns are concentrations of chemical constituents. See Thurston and Spengler (1985, Atmospheric Environment)

Examples

data(nycdat)
data(nycmdl)
#fix data totals
pm <- nycdat$PM25
whPM <- which(colnames(nycdat) == "PM25")
nycdat <- nycdat[, -whPM]
whPM <- which(colnames(nycmdl) == "PM25")
nycmdl <- nycmdl[, -whPM]
apca(nycdat)
apca(nycdat, tots = pm)
apca(nycdat, mdl = nycmdl, adjust = "substitute")

kralljr/handles documentation built on Dec. 6, 2019, 3:39 p.m.