Population Two Compartment Model with AOB transformation and Inter-subject Variance

[Generated automatically as a Tutorial summary]

Model Description

Name:

iv_two_cmp_ab_isv

Title:

Population Two Compartment Model with AOB transformation and Inter-subject Variance

Author:

PoPy for PK/PD

Abstract:

Population One Compartment Model and Inter-subject Variance

Keywords:

two compartment model; iv_two_cmp_ab; additive noise; AOB transform

Input Script:

iv_two_cmp_ab_isv.pyml

Diagram:

Comparison

True objective value

1849.1957

Final fitted objective value

1848.3458

Compare Main f[X]

Name	Initial	Fitted	True	Abs. Error	Prop. Error
f[AOB]	2.62	3.21	2.32	8.95e-01	38.59%
f[ALPHA]	1.31	0.244	0.414	1.69e-01	40.95%
f[BETA]	0.191	0.0267	0.0363	9.59e-03	26.44%

Compare Noise f[X]

Name	Initial	Fitted	True	Abs. Error	Prop. Error
f[ANOISE_STD]	100	5…	5	2.59e-03	0.05%

Compare Variance f[X]

Name	Initial	Fitted	True	Abs. Error	Prop. Error
f[AOB_isv]	2.62	0.97	2.62	1.65e+00	62.95%
f[AOB_isv;ALPHA_isv]	0	0	0	0.00e+00	inf
f[AOB_isv;BETA_isv]	0	0	0	0.00e+00	inf
f[ALPHA_isv;AOB_isv]	0	0	0	0.00e+00	inf
f[ALPHA_isv]	0.262	1.25	1.17	7.79e-02	6.65%
f[ALPHA_isv;BETA_isv]	0	0	0	0.00e+00	inf
f[BETA_isv;AOB_isv]	0	0	0	0.00e+00	inf
f[BETA_isv;ALPHA_isv]	0	0	0	0.00e+00	inf
f[BETA_isv]	0.0382	0.181	0.171	1.02e-02	5.96%

Outputs

Fitted f[X] values (after fitting)

f[AOB] = 3.2136
f[ALPHA] = 0.2443
f[BETA] = 0.0267
f[AOB_isv,ALPHA_isv,BETA_isv] = [
    [ 0.9699, 0.0000, 0.0000 ],
    [ 0.0000, 1.2487, 0.0000 ],
    [ 0.0000, 0.0000, 0.1810 ],
]
f[ANOISE_STD] = 4.9974

Generated data .csv file

Synthetic Data:

synthetic_data.csv

Gen and Fit Summaries

• Gen: Population Two Compartment Model with AOB transformation and Inter-subject Variance (gen)

• Fit: Population Two Compartment Model with AOB transformation and Inter-subject Variance (fit)

Inputs

True f[X] values (for simulation)

f[AOB] = 2.3187
f[ALPHA] = 0.4137
f[BETA] = 0.0363
f[AOB_isv,ALPHA_isv,BETA_isv] = [
    [ 2.6180, 0.0000, 0.0000 ],
    [ 0.0000, 1.1708, 0.0000 ],
    [ 0.0000, 0.0000, 0.1708 ],
]
f[ANOISE_STD] = 5.0000

Starting f[X] values (before fitting)

f[AOB] = 2.6180
f[ALPHA] = 1.3090
f[BETA] = 0.1910
f[AOB_isv,ALPHA_isv,BETA_isv] = [
    [ 2.6180, 0.0000, 0.0000 ],
    [ 0.0000, 0.2618, 0.0000 ],
    [ 0.0000, 0.0000, 0.0382 ],
]
f[ANOISE_STD] = 100.0000