Showing Predictor "NACD (L1) "

This predictor was successfully trained!

Meta

Notes:

from V Baracos

[Trained to optimize Log Likelihood, with L1 regularization ]

Publicly Accessible: yes

Viewable by Administrators: yes

Actions:Edit Delete

Hide

Dataset Show

Options
Regularization: L1	Tuning Score: avg log-likelihood loss
Time Points: 50	Tune Parameters: true
Feature Selection: false	Include Sibling Features: false
Standardize: true	Run Cross-Validation: true
Objective Function: log-likelihood	Marginal Loss Type: unweighted
Use pre-defined Fold: No

Results
Start Time: 2016-10-20 15:36:11 -0600	Used Time: 9 minutes
Label Name: SURVIVAL	C Parameter: 1.0
PSSP model: mtlr_model_file32.mtlr	Version: 0.0.2
Feature Sparsity Index: 51.7% used

Predictor Settings / Retrain Show

Cross-validation results

5-Fold Cross-Validation Statistics*
Measure	PSSP Predictor (median)	PSSP Predictor (mean)	K-M Predictor
Concordance Index	0.76 ± 0.01	0.76 ± 0.01	0.5 ± 0.0
Hinged L1 Loss	9.39 ± 0.35		13.28 ± 0.05
Uncensored L1 loss	10.55 ± 0.4	14.73 ± 0.38	12.18 ± 0.05
Marginal L1 Loss	15.96 ± 0.57	16.94 ± 0.49	21.74 ± 0.18
Marginal L2 Loss	N / A
Hinged L1 Log-Loss	0.56 ± 0.02	0.65 ± 0.01	0.79 ± 0.01
Uncensored L1 Log-Loss	0.75 ± 0.02	0.96 ± 0.02	0.97 ± 0.01
Marginal L1 Log-Loss	0.7 ± 0.03	0.76 ± 0.02	0.99 ± 0.01
Log-Likelihood Loss	2.57 ± 0.01
D-calibration χ² statistics	11.64 ± 3.7		0.97 ± 0.12
D-calibration χ² p-value	0.85 ± 0.15		1.0 ± 0.0

*Mean value ± standard deviation.

Examine Classification Accuracy