Showing Predictor "Toy dataset 1"

This predictor was successfully trained!

Meta

Notes:

From Hao, a toy dataset with 20 uncensored patients, 1 feature

Publicly Accessible: yes

Viewable by Administrators: yes

Actions:Edit Delete

Hide

Dataset Show

Options
Regularization: L2	Tuning Score: avg log-likelihood loss
Time Points: 5	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: 2017-09-22 11:34:16 -0600	Used Time: less than a minute
Label Name: SURVIVAL	C Parameter: 0.01
PSSP model: mtlr_model_file2840.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	0.83 ± 0.0	0.83 ± 0.0	0.5 ± 0.0
Hinged L1 Loss	1.46 ± 0.45		2.2 ± 0.29
Uncensored L1 loss	1.46 ± 0.45	1.41 ± 0.58	2.2 ± 0.29
Marginal L1 Loss	1.46 ± 0.45	1.41 ± 0.58	2.2 ± 0.29
Marginal L2 Loss	1.71 ± 0.47		2.74 ± 0.44
Hinged L1 Log-Loss	0.24 ± 0.07	0.23 ± 0.11	0.36 ± 0.02
Uncensored L1 Log-Loss	0.24 ± 0.07	0.23 ± 0.11	0.36 ± 0.02
Marginal L1 Log-Loss	0.22 ± 0.06	0.21 ± 0.1	0.32 ± 0.02
Log-Likelihood Loss	1.17 ± 0.19
D-calibration χ² statistics	20.0 ± 4.9		16.0 ± 0.0
D-calibration χ² p-value	0.45 ± 0.26		0.66 ± 0.0

*Mean value ± standard deviation.

Examine Classification Accuracy