Skip to main content
Advertisement

< Back to Article

Fig 1.

Creation of three-way interaction effect columns.

More »

Fig 1 Expand

Fig 2.

Matrix compression.

Given a full matrix (a), we reduce it to the indices of non-zero entries (b), then the compressed difference between these (c). Arrows represent transitions between different representations.

More »

Fig 2 Expand

Fig 3.

Running time on an increasing number of threads.

Note that performance initially decreases with only a small number of threads on a second NUMA node. Tests were performed using two Intel Xeon Gold 6244 CPUs.

More »

Fig 3 Expand

Fig 4.

Overall receiver operating characteristic curves for all p = 4, 000 data sets.

More »

Fig 4 Expand

Table 1.

Overall AUROC for simulated data sets.

More »

Table 1 Expand

Fig 5.

Running times for each method using large p = 4, 000 data sets.

Note that time is shown on a log scale.

More »

Fig 5 Expand

Table 2.

Mean time taken (s) for simulated data sets.

More »

Table 2 Expand

Fig 6.

Receiver operating characteristic curve comparing fraction of reported effects that are true positives as the predicted strength varies in the p = 4, 000 simulations.

More »

Fig 6 Expand

Fig 7.

Comparison of methods when 3-way interactions are present.

(a) ROC curve for full fit of all 3-way interaction data sets. (b) Time taken for each method. Note that Pint and Pint (hierarchy) are including three-way interactions, whereas glinternet and WHInter include only two-way.

More »

Fig 7 Expand

Table 3.

AUROC for simulated three-way interaction data sets, separated by the type of effect.

More »

Table 3 Expand

Table 4.

InfectX most significant proposed effects.

More »

Table 4 Expand