Oleg Sofrygin

Unify internal structure for predictions

5

* Currently using a matrix to store all predictions. * Should switch to data.table, with one column per model. * The column can be of arbitrary type (i.e., a list))...

plot function for DAGs

1

add S3 method `plot` for DAG object.

Simulated data contains two ID columns

THIS no longer works, because the dimensions of catprob.W0 and catprob.W1 (1 row) do not match the dims of W (n rows) ``` R D

`latent.v` does not appear to work when output data is in long format ``` sim(DAG, wide=FALSE) ```

Allow non-existing time-point references to default to some value, for example, instead of doing this ``` R node("TI", t=0:7, distr="rbern", prob=plogis(-5 - 0.3*CVD + 0.5*A1C[t] + 1.5*{if (t==0) {0} else...

using as.integer() in node formulas prints it to the terminal: ``` R library(simcausal) D

cum.g weight truncation scheme and untruncated weight diagnostics

1

Hi Josh, 1) Is the weight truncation (on predicted g) performed _separately_ for each type of AC node or is it being applied to the joint probability of all interventions...

Very long running time for survival on a static regime

3

ltmle() takes too much time to run for end of follow-up time-point survival on a static regime (no SuperLearner). Full data run takes about 80min and 20GB of RAM. It...

The results tables provided by estimating functions are poorly documented. This could be used as a start: https://github.com/osofr/stremr/#simulated-data-example