Showing Predictor "MCL"

This predictor was successfully trained!

Meta

Publicly Accessible: yes

Viewable by Administrators: yes

Actions:Edit Delete

Hide

Dataset Show

Options
Regularization: L2	Tuning Score: avg log-likelihood loss
Time Points: 10	Tune Parameters: true
Feature Selection: false	Include Sibling Features: false
Standardize: true	Run Cross-Validation: true
Objective Function: log-likelihood	Marginal Loss Type: weighted
Use pre-defined Fold: No

Results
Start Time: 2016-10-21 14:17:38 -0600	Used Time: 27 minutes
Label Name: time	C Parameter: 100.0
PSSP model: mtlr_model_file2376.mtlr	Version: 0.0.3

Predictor Settings / Retrain Show

Cross-validation results

5-Fold Cross-Validation Statistics*
Measure	PSSP Predictor (median)	PSSP Predictor (mean)	K-M Predictor
Concordance Index	0.72 ± 0.05	0.72 ± 0.05	0.5 ± 0.0
Hinged L1 Loss	1.44 ± 0.26		1.75 ± 0.2
Uncensored L1 loss	1.63 ± 0.3	2.89 ± 0.49	2.01 ± 0.21
Marginal L1 Loss	2.53 ± 0.25	3.09 ± 0.25	2.89 ± 0.31
Marginal L2 Loss	N / A
Hinged L1 Log-Loss	0.63 ± 0.08	0.85 ± 0.12	0.77 ± 0.08
Uncensored L1 Log-Loss	0.83 ± 0.12	1.2 ± 0.16	1.01 ± 0.11
Marginal L1 Log-Loss	0.85 ± 0.07	1.04 ± 0.11	1.01 ± 0.1
Log-Likelihood Loss	1.64 ± 0.07
D-calibration χ² statistics	14.58 ± 4.05		4.0 ± 0.65
D-calibration χ² p-value	0.72 ± 0.24		1.0 ± 0.0

*Mean value ± standard deviation.

Examine Classification Accuracy