Description
mice/ Strain 74/81 data
Dose Dead Survived Total
200 0 10 10
4000 1 9 10
5E+04 12 0 12
4E+05 16 0 16

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 2.34 -0.00145 3 3.84 
1 		7.81 
0.506
Beta Poisson 2.34 2 5.99 
0.311
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
0.5% 2.5% 5% 95% 97.5% 99.5%
k 6.48E-05 5.45E-05 5.45E-05 5.45E-05 9.71E-05 9.71E-05 1.24E-04
ID50/LD50/ETC* 1.07E+04 5.57E+03 7.14E+03 7.14E+03 1.27E+04 1.27E+04 1.27E+04
*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
4.00
Μodel
exponential
LD50/ID50
1.07E+04
Dose Units
CFU
Response
death
Exposure Route
inhalation
Contains Preferred Model
k
6.48E-05
Agent Strain
strain 74/81
Experiment ID
242
Host type
mice
Description
Guinea pigs/ Philadelphia 1 strain data 
Dose Infected Non-infected Total
1 0 4 4
5 4 10 14
50 17 1 18
100 8 0 8

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 0.582 0.000479 3 3.84 
0.983 		7.81 
0.9
Beta Poisson 0.582 2 5.99 
0.748
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
0.5% 2.5% 5% 95% 97.5% 99.5%
k 5.99E-02 3.26E-02 3.90E-02 4.18E-02 1.11E-01 1.31E-01 1.57E-01
ID50/LD50/ETC* 1.16E+01 4.42E+00 5.28E+00 6.25E+00 1.66E+01 1.78E+01 2.13E+01
*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
4.00
Μodel
exponential
LD50/ID50
1.16E+01
Dose Units
CFU
Response
infection
Exposure Route
inhalation
Contains Preferred Model
k
5.99E-02
Agent Strain
Philadelphia 1
Experiment ID
241
Host type
guinea pig
Description
Human/ S. meleagridis strain III data 
Dose Infected Non-infected Total
158000 1 5 6
1.5E+06 5 1 6
7680000 6 0 6
1E+07 5 1 6

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 7.81 5.51 3 3.84 
0.019 		7.81 
0.0501
Beta Poisson 2.3 2 5.99 
0.316
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 8.85E-01 1.78E-01 2.91E-01 3.68E-01 1.40E+03 1.71E+03 8.24E+03
N50 5.24E+05 4.71E+04 1.20E+05 1.92E+05 1.19E+06 1.39E+06 1.90E+06

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.

beta Poisson model plot, with confidence bounds around optimized model

# of Doses
4.00
Μodel
beta-Poisson
N50
5.24E+05
LD50/ID50
5.24E+05
Dose Units
CFU
Response
infection
Exposure Route
oral (with eggnog)
Contains Preferred Model
a
8.85E-01
Agent Strain
strain III
Experiment ID
240
Host type
human
Description
Human / S. meleagridis strain I data
Dose Infected Non-infected Total
12000 3 3 6
24000 4 2 6
52000 3 3 6
96000 3 3 6
155000 5 1 6
3E+05 6 0 6
720000 4 1 5
1150000 6 0 6
5.5E+06 5 1 6
2.4E+07 5 0 5
5E+07 6 0 6

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 71.8 63.8 10 3.84 
1.33e-15 		18.3 
1.98e-11
Beta Poisson 7.99 9 16.9 
0.535
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 3.89E-01 1.23E-01 1.74E-01 2.01E-01 1.12E+00 1.91E+00 3.82E+02
N50 1.68E+04 7.98E+01 1.08E+03 2.27E+03 4.78E+04 5.71E+04 7.49E+04

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.

beta Poisson model plot, with confidence bounds around optimized model

# of Doses
11.00
Μodel
beta-Poisson
N50
1.68E+04
LD50/ID50
1.68E+04
Dose Units
CFU
Response
infection
Exposure Route
oral (with eggnog)
Contains Preferred Model
a
3.89E-01
Agent Strain
strain I
Experiment ID
238
Host type
human
Description
Human/Salmonella newportmodel data ]
Dose Infected Non-infected Total
152000 3 3 6
385000 6 2 8
1350000 6 0 6

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 0.16 -3.32e-05 2 3.84 
1 		5.99 
0.923
Beta Poisson 0.16 1 3.84 
0.689
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
0.5% 2.5% 5% 95% 97.5% 99.5%
k 3.97E-06 1.75E-06 2.16E-06 2.32E-06 7.36E-06 9.04E-06 1.27E-05
ID50/LD50/ETC* 1.74E+05 5.45E+04 7.67E+04 9.41E+04 2.98E+05 3.20E+05 3.97E+05
*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
exponential
LD50/ID50
1.74E+05
Dose Units
CFU
Response
infection
Exposure Route
oral
Contains Preferred Model
k
3.97E-06
Agent Strain
*Salmonella newport*
Experiment ID
235
Host type
human
Description
Human/ Salmonella anatum strain II data [4]
Dose Positive stool culture No positive stool culture Total
89000 5 1 6
448000 4 2 6
1040000 6 0 6
3.9E+06 4 2 6
1E+07 6 0 6
2.39E+07 5 1 6
4.45E+07 6 0 6
6.73E+07 8 0 8

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 62.8 54.2 7 3.84 
1.84e-13 		14.1 
4.22e-11
Beta Poisson 8.6 6 12.6 
0.198
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 2.3E-01 3.63E-02 5.29E-02 6.00E-02 5.51E-01 6.70E-01 1.40E+00
N50 4.91E+03 2.59E-10 2.73E-08 4.91E-06 8.72E+04 1.23E+05 2.29E+05

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.

beta Poisson model plot, with confidence bounds around optimized model

# of Doses
8.00
Μodel
beta-Poisson
N50
4.91E+03
LD50/ID50
4.91E+03
Dose Units
CFU
Response
positive stool culture
Exposure Route
oral (with eggnog)
Contains Preferred Model
a
2.3E-01
Agent Strain
strain II
Experiment ID
233
Host type
human
Description
Human/ Salmonella anatum strain I & II pooled data [4]
Dose Positive stool culture No positive stool culture Total
12000 2 3 5
24000 3 3 6
66000 4 2 6
89000 5 1 6
93000 1 5 6
141000 3 3 6
256000 5 1 6
448000 4 2 6
587000 4 2 6
860000 6 0 6
1040000 6 0 6
3.9E+06 4 2 6
1E+07 6 0 6
2.39E+07 5 1 6
4.45E+07 6 0 6
6.73E+07 8 0 8

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 138 119 15 3.84 
0 		25 
0
Beta Poisson 18.9 14 23.7 
0.168
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 3.18E-01 1.35E-01 1.71E-01 1.92E-01 5.70E-01 6.66E-01 9.56E-01
N50 3.71E+04 1.40E+03 5.50E+03 8.86E+03 8.82E+04 1.00E+05 1.30E+05

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.

beta Poisson model plot, with confidence bounds around optimized model

# of Doses
16.00
Μodel
beta-Poisson
N50
3.71E+04
LD50/ID50
3.71E+04
Dose Units
CFU
Response
positive stool culture
Exposure Route
oral (with eggnog)
Contains Preferred Model
a
3.18E-01
Agent Strain
strain I
Experiment ID
232, 233
Host type
human
Description
Human / Salmonella anatum strain I data
Dose Positive stool culture No positive stool culture Total
12000 2 3 5
24000 3 3 6
66000 4 2 6
93000 1 5 6
141000 3 3 6
256000 5 1 6
587000 4 2 6
860000 6 0 6

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 20.5 11 7 3.84 
0.000922 		14.1 
0.00457
Beta Poisson 9.53 6 12.6 
0.146
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 2.91E-01 9.77E-04 9.77E-04 4.11E-02 1.68E+00 5.36E+00 1.20E+03
N50 4.44E+04 6.74E-02 8.03E+02 4.15E+03 1.64E+05 6.89E+06 9.07E+07

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.

beta Poisson model plot, with confidence bounds around optimized model

# of Doses
8.00
Μodel
beta-Poisson
N50
4.44E+04
LD50/ID50
4.44E+04
Dose Units
CFU
Response
positive stool culture
Exposure Route
oral (with eggnog)
Contains Preferred Model
a
2.91E-01
Agent Strain
strain I
Experiment ID
232
Host type
human
Description
diabetic rat and 316c strain 
Dose DEATH NOT DEATH Total
3000 6 4 10
3E+04 7 3 10
3E+05 7 3 10
3E+06 10 0 10
3E+07 10 0 10

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 43.4 39 4 3.84 
4.25e-10 		9.49 
8.61e-09
Beta Poisson 4.39 3 7.81 
0.222
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 500 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 2.65E-01 7.56E-02 1.30E-01 1.54E-01 4.94E-01 5.69E-01 8.88E-01
N50 2.27E+03 7.58E-02 1.50E+01 5.32E+01 8.62E+03 1.11E+04 1.74E+04
Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.
Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters.
beta Poisson model plot, with confidence bounds around optimized model
beta Poisson model plot, with confidence bounds around optimized model
# of Doses
5.00
Μodel
beta-Poisson
N50
2.27E+03
LD50/ID50
2.27E+03
Dose Units
CFU
Response
death
Exposure Route
intraperitoneal
Contains Preferred Model
a
2.65E-01
Agent Strain
316c
Experiment ID
23
Host type
diabetic rat
Experiment Dataset
Description
Model data for Shigella flexneri (2a, strain 2457T) in the human 
Dose Illness Not illness Total
180 9 27 36
5000 28 21 49
1E+04 52 36 88
1E+05 14 10 24

 

Goodness of fit and model selection
Model Deviance Δ Degrees 
of freedom		 χ20.95,1 
p-value 		χ20.95,m-k 
p-value
Exponential 154 153 3 3.84 
0 		7.81 
0
Beta Poisson 1.69 2 5.99 
0.429
Beta-Poisson fits better than exponential; cannot reject good fit for beta-Poisson.

 

Optimized parameters for the beta-Poisson model, from 10000 bootstrap iterations
Parameter MLE estimate Percentiles
0.5% 2.5% 5% 95% 97.5% 99.5%
α 1.35E-01 9.86E-04 1.22E-02 6.85E-02 2.06E-01 2.22E-01 2.58E-01
N50 3.11E+03 5.09E+01 4.31E+02 9.64E+02 7.49E+03 9.14E+03 1.89E+04

 

Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters
Parameter scatter plot for beta Poisson model ellipses signify the 0.9, 0.95 and 0.99 confidence of the parameters
beta Poisson model plot, with confidence bounds around optimized model
beta Poisson model plot, with confidence bounds around optimized model
# of Doses
4.00
Μodel
beta-Poisson
N50
3.11E+03
LD50/ID50
3.11E+03
Dose Units
CFU
Response
illness
Exposure Route
oral (in milk)
Contains Preferred Model
a
1.35E-01
Agent Strain
2a (strain 2457T)
Experiment ID
223
Host type
human
Experiment Dataset
Subscribe to