norm_lin_dataset_sim: Generate simulated observations following a linear model with...

In NicolasEDubois/anaval: Validation of analytical methods

Description

Generate simulated observations following a linear model with normal random error.

Usage

norm_lin_dataset_sim(MyDOE, intercept = 0, slope = 1, SDrun = 10,
  SDrep = 10, biais = 0)

Arguments

MyDOE	is a data.frame with 6 columns (RunTechnician, ConcentrationLabel,+ ConcentrationValue, CalibCurve, ReplicateNumber, Responses). This data.frame is produced by a DOE generating function.
intercept	the intercept of the linear model.
slope	the slope of the linear model.
SDrun	the standard deviation between analytical runs.
SDrep	the standard deviation between replicates (within an analytical run).
biais	the bias between the true values and the simulated data.

Value

The output is a data.frame with 6 columns (RunTechnician, ConcentrationLabel, ConcentrationValue, CalibCurve, ReplicateNumber,Responses). Responses column is filled with the simulated data following a linear model with normal random error.

See Also

DOE generating functions such as calib_doe DOE_Run_Repl_Conc

Examples

MyDOE <- calib_doe(nRun = 2, nCalibCurvesPerRun = 3, nrepCalib = 5,
  ConcVect = c(0,50, 100, 125, 150, 175, 200))
CalibDs <- norm_lin_dataset_sim(MyDOE, intercept = 1, slope = 2, SDrun=1.5,
 SDrep=3, biais = 0)

 monDOE = DOE_Run_Repl_Conc(nRun = 3, nreplicates = 2, ConcVect = c(0, 50, 100, 125,150, 175, 200 ),
  Threshold='NaN', factorlist=c('RunTechnician','ConcentrationLabel','ConcentrationValue',
  'ReplicateNumber','Status','Response'))
 TPL <- norm_lin_dataset_sim(monDOE, intercept = 1, slope = 2, SDrun=1.5, SDrep=3, biais = 0)

NicolasEDubois/anaval documentation built on May 7, 2019, 6:18 p.m.