Skip to contents

This function runs the survival regression which is the concentration estimation method of WRTDS. It uses sample data from the data frame Sample. It does the estimation for a set of data points defined by two vectors: estPtYear and estPtLQ. It returns an array of results for the estimation points. The array returned contains yHat, SE and ConcHat (in that order). yHat is the expected value of log(concentration), SE is the standard error of log(concentration) and ConcHat is the expected value of concentration.

Usage

runSurvReg(estPtYear, estPtLQ, DecLow, DecHigh, Sample, windowY = 7,
  windowQ = 2, windowS = 0.5, minNumObs = 100, minNumUncen = 50,
  verbose = TRUE, interactive = NULL, edgeAdjust = TRUE,
  run.parallel = FALSE)

run_WRTDS(estY, estLQ, localSample, DecLow, DecHigh, minNumObs, minNumUncen,
  windowY, windowQ, windowS, edgeAdjust)

Arguments

estPtYear

numeric vector of Decimal Year values at the estimation points

estPtLQ

numeric vector of ln(Q) values at the estimation points, must be the same length as estPtYear

DecLow

number specifying minimum decimal year (left edge of the estimated surfaces).

DecHigh

number specifying maximum decimal year (right edge of the estimated surfaces).

Sample

dataframe created for EGRET analysis

windowY

numeric specifying the half-window width in the time dimension, in units of years, default is 7

windowQ

numeric specifying the half-window width in the discharge dimension, units are natural log units, default is 2

windowS

numeric specifying the half-window with in the seasonal dimension, in units of years, default is 0.5

minNumObs

numeric specifying the miniumum number of observations required to run the weighted regression, default is 100

minNumUncen

numeric specifying the minimum number of uncensored observations to run the weighted regression, default is 50

verbose

logical specifying whether or not to display progress message

interactive

logical deprecated. Use 'verbose' instead

edgeAdjust

logical specifying whether to use the modified method for calculating the windows at the edge of the record. The modified method tends to reduce curvature near the start and end of record. Default is TRUE.

run.parallel

logical to run bootstrapping in parallel or not

estY

numeric decimal year values at the estimation point

estLQ

numeric ln(Q) values at the estimation point

localSample

"Sample" data frame from the eList.

Value

resultSurvReg numeric array containing the yHat, SE, and ConcHat values array dimensions are (numEstPts,3)

Examples

eList <- Choptank_eList
estPtYear<-c(2001.0,2005.0,2009.0)
estPtLQ<-c(1,1,1)
Sample <- getSample(eList)
DecLow <- Sample$DecYear[1]
DecHigh <- Sample$DecYear[nrow(Sample)]
resultSurvReg <- runSurvReg(estPtYear,estPtLQ,
                            DecLow,DecHigh,Sample,
                            run.parallel = FALSE)
#> Survival regression (% complete):
#> 33 	66 	
#> Survival regression: Done