| Name: |
Web-based simulator for sample size and power estimation in animal
carcinogenicity studies
|
| Objective: |
A Web-based statistical tool for sample size and power estimation in animal carcinogenicity
studies is developed. Given the design parameters, the program computes statistical
power for detecting a dose-related trend in the
occurrence of a tumor of interest in the presence of competing risks. By varying the sample size
the program can be used to determine the required sample size for achieving sufficient power.
It is designed for rodent
tumorigenicity assays that have either a single terminal sacrifice or multiple sacrifices. It
is applicable for studies on occult tumors for which the time to tumor onset is not directly
observable.
|
| Authors: |
Hojin Moon,
J. Jack Lee,
Hongshik Ahn and
Rumiana Nikolova
|
| Input Parameters: |
- Number of dose groups
- Type of experiment with number of sacrifices
- Dose metric in each group
- Sample size per group
- Sacrifice time points
- Number of sacrificed animals at each interval
- Tumor onset probability in the control group
- Distribution of tumor onset
- Hazard ratio between each dose group and a control group
- Competing risks survival rate in each group
- Lethality parameter to determine lethality rate in the control
- Level of a one- or two-sided test
- Number of simulation runs
|
| Output: |
- Average tumor rate per dose group
- Average competing risks survival rate per dose group
- Average lethality per dose group
- Average death rate with information on tumors and sacrifices per dose group
- Simulated power
|
| Reference: |
"Web-based Simulator for Sample Size and Power Estimation in Animal
Carcinogenicity Studies"
Hojin Moon, J. Jack Lee, Hongshik Ahn and Rumiana Nikolova
Journal of Statistical Software, 7(13), 1-36, 2002.
|