Background
Example: revisiting the PAQUID cohort example
Methods
Statistical context
Model
Maximum test and minimum P-value procedures
Score test
Dichotomous and Box-cox Transformations
Categorical transformations
Significance level correction
Bonferroni method
Resampling based methods
Permutation test procedure
Parametric bootstrap procedure
Results
Simulation study
Dichotomous transformations
Number of transformations |
c
1
|
c
2
|
c
3
|
…
|
c
9
|
---|---|---|---|---|---|
1 |
q
1/2
| ||||
2 |
q
1/3
|
q
2/3
| |||
3 |
q
1/4
|
q
2/4
|
q
3/4
| ||
⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
9 |
q
1/10
|
q
2/10
|
q
2/10
| … |
q
9/10
|
Categorical transformations with same number of classes
Number of transformations | ||
---|---|---|
1 |
q
1/3
|
q
2/3
|
2 |
q
1/4
|
q
3/4
|
3 |
q
1/4
|
q
1/2
|
4 |
q
1/2
|
q
3/4
|
5 |
q
2/5
|
q
4/5
|
6 |
q
1/5
|
q
3/5
|
7 |
q
3/5
|
q
4/5
|
8 |
q
1/5
|
q
2/5
|
9 |
q
1/5
|
q
4/5
|
10 |
q
2/5
|
q
3/5
|
Various categorical transformations
Number of transformations |
…
| ||||
---|---|---|---|---|---|
1 |
q
1/2
| ||||
2 |
q
1/3
|
q
2/3
| |||
⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |
9 |
q
1/10
|
q
2/10
| … |
q
9/10
| |
10 |
q
1/11
|
q
2/11
| … |
q
9/11
|
q
10/11
|
Robustness of resampling methods
Example: revisiting the PAQUID cohort example
Discussion
Conclusion
Appendix
CPMCGLM
has been developed in R, an open source statistical software available at http://www.r-project.org. The methods presented in this paper are available in the main function CPMCGLM()
for Probit, Logit, Linear, and Poisson models. Briefly, the user can specify the transformations tested: Box-Cox, dichotomous or categorical transformations. Two options are possible for defining the cutpoints of the dichotomous and the categorical transformations: the user can either specify them, or the program will automatically use the strategy based on the quantile presented in the simulation study.CPMCGLM
function on a simulated dataset: