Description Usage Arguments Details Value See Also
Generates a new model of class loadInterp (loadInterp-class
)
which can iterpolate among observations of concentration or flux.
1 2 3 4 | loadInterp(interp.format = c("flux", "conc"),
interp.function = linearInterpolation, data, metadata,
retrans.function = NULL, store = c("data", "fitting.function",
"uncertainty"))
|
interp.format |
character. Which sort of observation should the interpolations be done among? |
interp.function |
function. The function to use for interpolation. Pre-defined choices are described in interpolations; additional functions may be defined by the user as long as they adhere to the guidelines given there. |
data |
data.frame. The data to be interpolated |
metadata |
metadata, used to access the appropriate columns of data. At
a minimum, |
retrans.function |
irrelevant to loadInterp and must be NULL. for other models, permits fitting in log or other transformed spaces. |
store |
One or more character strings specifying which information to write within the model. Options are 'data': the original fitting data; 'fitting.function': a fitting function that can produce a new loadComp object from new data (this currently uses the same new data for both regression calibration and interpolation); 'uncertainty': an estimate of uncertainty, which can take some time to compute but will permit creation of uncertainty intervals, etc. in the prediction and aggregation phases. |
loadInterps are simple load models that predict concentration or flux based on one or more preceding and following measurements of flux. The specific interpolation method can be varied; examples include linear, spline, and triangular interpolations. See interpolations for the full list of pre-defined options; others may also be defined by the user.
loadInterps are currently assumed to have normally distributed residuals. An unwitting user might violate this assumption without being caught by the code, so be careful! This assumption is mainly relevant to the calculation of confidence or prediction intervals. Also, where other models such as loadReg and loadLm will retransform predictions back into linear space, loadInterps will not.
A fitted loadInterp model.
Other load.model.inits: loadComp
,
loadLm
, loadModel
,
loadReg2
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.