Binary combinations were tested as well, and the interaction effects were evaluated following the isobole method.
The effects of categorical covariates were tested as binary covariates; the effects of continuous covariates were modeled using a normalized power model.
For technical reasons (linearized SCM), hepatic dysfunction was tested as two separate binary covariates (i.e., mild vs. moderate/severe, and mild/moderate vs. severe).
The predictive value of the biomarkers as continuous variables was tested by linear regression and binary logistic regression analyses, and their sensitivity and specificity were tested in a binary classification test by χ analysis.
In this test, polymorphic locus was treated as a binary dependent variable (polymorphic = 1, monomorphic = 0) using logit link function.
In these tests, amplification success was treated as a binary dependent variable (successful amplification = 1, failed amplification = 0), SSR type and primer site as factors, and other parameters as covariates.
Because the FBA simulation result is treated as a binary test (growth or no-growth), gene deletions that strongly affect growth on minimal media without producing a completely lethal phenotype must be defined either as experimentally essential or as experimentally nonessential.
As with the symptom data, the neuro-cognitive test data were analyzed with Pfiesteria exposure treated as a binary variable and then as levels of exposure.
We tested a binary (yes/no) indicator for use of anti-inflammatory medications, as well as separate indicators for inhaled corticosteroids with versus without leukotriene receptor antagonists.
We also tested a binary indicator for prescribed daily use of short- or long-acting bronchodilators as controller medications.
