cosinor_goodness_of_fit {card} | R Documentation |
Goodness of fit of a cosinor from data that has multiple collections at different timepoints or from multiple cycles. The RSS is partitioned into pure error (SSPE) and lack of fit (SSLOF). An F-test compares the SSPE and SSLOF to detect appropriateness of model.
SSLOF = RSS - SSPE
SSPE = ∑_{i} ∑_{l} ( Y_{il} - \overline{Y}_{i} )^2
The fitted values for each time point are:
\overline{Y}_{i} = \frac{ ∑_{l} Y_{il} }{ n_{i}}
cosinor_goodness_of_fit(object, level = 0.95, ...)
object |
requires cosinor model generated with card::cosinor to calculate statistics. |
level |
confidence level desired |
... |
additional parameters may be needed for extensibility |
f-statistic as result of goodness of fit