StataNow adds more new features with a 26 February update.
Machine learning via H2O
With the new h2oml suite, you can use machine learning via H2O to uncover insights from data when traditional statistical models fall short. Use ensemble decision trees—gradient boosting machine (GBM) or random forest—to perform classification or regression. Tune hyperparameters, use validation or cross-validation (CV), evaluate model performance, explain predictions, and more.
Cluster-robust standard errors for interval censored multiple event Cox model
Need to analyze event times from multiple types of events such as the onset of diabetes and hypertension? Don’t know the exact event times? Use the new stmgintcox command to analyze such interval-censored multiple-event data and account for possible correlation between event times across the different events. Evaluate the proportional-hazards assumption. Perform a powerful test for a common covariate effect across all events. Graph covariate-specific survivor, hazard, and other functions. And more!
Enhancement for listing data: relative observation numbers
The list command has three new options:
- sepbyexp(exp)draws a separator line whenever the value of expression exp exp does not necessarily have to refer to the variables in the dataset;
- footerdisplays variable names as a footer;
- relativedisplays relative observation numbers when a subset of observations is listed.
Enhancements to H2O integration features
Additional updates:
- When working with h2o, subcommands of _h2oframe no longer require a leading underscore. For example, _h2oframe put can be used instead of _h2oframe _put.
- h2o init will now generate credentials and create new H2O instances using those credentials by default. The new h2o credentials query and h2o credentials clear commands are available for retrieving and managing credentials that Stata automatically creates using h2o init.
- h2o init has a new maxmem() option for specifying the maximum memory to allocate when starting a local H2O cluster.
- The h2o command has a new subcommand clear. h2o clear discards all resources within the H2O cluster.
- The _h2oframe command for interacting with H2O has the following new subcommands:
- _h2oframe factor converts columns in the H2O frame to categorical.
- _h2oframe levelsof lists all levels of a categorical column.
- _h2oframe baselevel sets the base level of a categorical column.
- _h2oframe recodelevel assigns new levels of a categorical column.
- _h2oframe distinct lists the distinct values of a column.
- The _h2oframe put, _h2oframe create, _h2oframe import, and _h2oframe upload commands now have the current option, which sets the H2O frame as the current (working) H2O frame.
- The _h2oframe put, _h2oframe import, _h2oframe upload, and _h2oframe split now have the replace option, which replaces the H2O frame if it already exists.
- The _h2oframe put command now has the coltype(varlist, type) option, which sets the column type for the specified variable(s) in the destination H2O frame.
- The _h2oframe split command now has the split(numlist) option, which splits an existing H2O frame into a list of H2O frames based on the proportions or ratio specified in numlist.
See all of the updates we have added so far with StataNow.
If you have questions, please contact us: Info@dpc-software.de