Closed PaulMelloy closed 2 years ago
Methods of comparing prediction with observations. It can be used now since Adam has done the data wrangling for the model (selected quadrats)
From: Paul Melloy @.> Reply to: IhsanKhaliq/valascotraceR @.> Date: Friday, 12 November 2021 at 7:32 am To: IhsanKhaliq/valascotraceR @.> Cc: Subscribed @.> Subject: [IhsanKhaliq/valascotraceR] Method for assessing optimum model parameters (Issue #6)
I was pondering last night a method for assessing the fit of the model simulation vs the observed.
Assuming we are using the proportion of infected quadrats, we could use the sum of squared residuals to assess the best fit to the mean observed proportion of infected quadrats to the simulated infected quadrats.
Using this as a metric might help automate some permutations on a HPC. To undertake permutations I think we need to make more model parameters available at the trace_asco level. see issue 120 in the ascotraceR repo
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/IhsanKhaliq/valascotraceR/issues/6, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ANBRP5NWTNP2ZWCPWFWAG53ULQY5TANCNFSM5H3MT7GA.
This email (including any attached files) is confidential and is
for the intended recipient(s) only. If you received this email by
mistake, please, as a courtesy, tell the sender, then delete this
email.
The views and opinions are the originator's and do not necessarily
reflect those of the University of Southern Queensland. Although
all reasonable precautions were taken to ensure that this email
contained no viruses at the time it was sent we accept no
liability for any losses arising from its receipt.
The University of Southern Queensland is a registered provider
of education with the Australian Government.
(CRICOS Institution Code QLD 00244B / NSW 02225M, TEQSA PRV12081)
As I already suggested, ROC comes to mind.
Closed via d17e4340dacbba40c39ca3bebe6c1a318b9a47d7
I was pondering last night a method for assessing the fit of the model simulation vs the observed.
Assuming we are using the proportion of infected quadrats, we could use the sum of squared residuals to assess the best fit to the mean observed proportion of infected quadrats to the simulated infected quadrats.
Using this as a metric might help automate some permutations on a HPC. To undertake permutations I think we need to make more model parameters available at the
trace_asco
level. see issue 120 in the ascotraceR repo