LD50 i.c. | QMRA wiki

Description

**Goodness of fit and model selection**
Model	Deviance	Δ	Degrees of freedom	χ²_0.95,1 p-value	χ²_0.95,m-k p-value
Exponential	1.34	0.99	2	3.84 0.32	5.99 0.512
Beta Poisson	0.35	0.99	1	3.84 0.32	3.84 0.554
Exponential is preferred to beta-Poisson; cannot reject good fit for exponential.

**Optimized k parameter for the exponential model, from 10000 bootstrap iterations**
Parameter	MLE estimate	Percentiles
Parameter	MLE estimate	0.5%	2.5%	5%	95%	97.5%	99.5%
k	2.4E-05	1.00E-13	1.00E-13	7.23E-06	5.47E-05	5.81E-05	7.44E-05
ID50/LD50/ETC*	2.89E+04	9.32E+03	1.19E+04	1.27E+04	9.58E+04	6.92E+12	6.92E+12
*Not a parameter of the exponential model; however, it facilitates comparison with other models.

Parameter histogram for exponential model (uncertainty of the parameter)

Exponential model plot, with confidence bounds around optimized model

# of Doses

3.00

Μodel

LD50/ID50

2.89E+04

Dose Units

Response

Exposure Route

Contains Preferred Model

2.4E-05

Agent Strain

scrapie strain C506M3

Experiment ID

251

Host type

Description

**Goodness of fit and model selection**
Model	Deviance	Δ	Degrees of freedom	χ²_0.95,1 p-value	χ²_0.95,m-k p-value
Exponential	14.5	12.6	4	3.84 0.000382	9.49 0.00576
Beta Poisson	1.92	12.6	3	3.84 0.000382	7.81 0.589
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.