Variables | *P*(*s*(*i*,*j*))=1 | *P*(*s*(*i*,*j*))=0 | Total |
---|

*y*=case | *a* | *N*_{1}−*a* | *N*_{1} |

*y*=control | *x*−*a* | *N*_{0}−(*x*−*a*) | *N*_{0} |

Total | *x* | *N*−*x* | *N* |

*x* is the number of samples whose *P*(*s*(*i*,*j*)) take value 1. *a* has the same interpretation as *x* but restricted to cases.