Linear PD model

[Generated automatically as a Fitting summary]

Model Description

Name:

linear_pd_pop

Title:

Linear PD model

Author:

PoPy for PK/PD

Abstract:

A simple (i.e. no PD compartments) Linear PD Model.

Model consists of a baseline which increases linearly with concentration.

Keywords:

pd; linear; one compartment model

Input Script:

linear_pd_pop_fit.pyml

Diagram:

Comparison

Compare Main f[X]

Variable Name	Starting Value	Fitted Value	Abs Change	Prop Change
f[BL]	15.0000	9.8634	5.1366	0.3424
f[SLOPE]	0.5000	1.0393	0.5393	1.0786

Compare Noise f[X]

Variable Name	Starting Value	Fitted Value	Abs Change	Prop Change
f[PNOISE]	0.0300	0.0148	0.0152	0.5064
f[ANOISE]	0.2000	0.4364	0.2364	1.1819

Compare Variance f[X]

Variable Name	Starting Value	Fitted Value	Abs Change	Prop Change
f[BL_isv]	0.1000	0.0537	0.0463	0.4628
f[BL_isv;SLOPE_isv]	0.0000	0.0062	0.0062	INF
f[SLOPE_isv;BL_isv]	0.0000	0.0062	0.0062	INF
f[SLOPE_isv]	0.0500	0.0403	0.0097	0.1948

Individual simulated (sim) plots

Alternatively see All simulated_sim graph plots

Population simulated (sim) plots

(No population graphs were requested.)

Outputs

Final objective value

178.3795

which required 1.20 iterations and took 70.72 seconds

Fitted f[X] values (after fitting)

f[BL] = 9.8634
f[SLOPE] = 1.0393
f[PNOISE] = 0.0148
f[ANOISE] = 0.4364
f[BL_isv,SLOPE_isv] = [
    [ 0.0537, 0.0062 ],
    [ 0.0062, 0.0403 ],
]

Fitted parameter .csv files

Fixed Effects:

fx_params.csv (fit)

Random Effects:

rx_params.csv (fit)

Model params:

mx_params.csv (fit)

State values:

sx_params.csv (fit)

Predictions:

px_params.csv (fit)

Likelihoods:

lx_params.csv (fit)

Inputs

Input Data:

cx_obs_params.csv

Starting f[X] values (before fitting)

f[BL] = 15.0000
f[SLOPE] = 0.5000
f[PNOISE] = 0.0300
f[ANOISE] = 0.2000
f[BL_isv,SLOPE_isv] = [
    [ 0.1000, 0.0000 ],
    [ 0.0000, 0.0500 ],
]