Model 1Model 2Model 3Model 4Model 5
Econometric estimation methodOLSaOLSaOLSaTOBITCLAD
Independent variablesPCS MCSPCS MCS, squared termsPCS MCS, squared terms and interaction termPCS MCS, squared terms and interaction termPCS MCS, squared terms and interaction term
Coeff.SECoeff.SECoeff.SECoeff.SECoeff.SE
Intercept0.28426820.1811317−0.62335330.5770837−1.5524340.749881−1.8148380.7887539−0.67704891.035821
PCS0.0045590.0034250.00180810.02017210.02497010.02329690.02865080.02445270.01572590.0273862
MCS0.00263230.00307360.05162040.02219070.0734180.02466420.08316820.02599280.03996890.0316185
PCS*PCS0.00001860.0002580.00004640.00025410.0000410.00026830.00001520.0002815
MCS*MCS−0.00055610.0002495−0.00058770.0002459−0.00067110.0002584−0.00028750.0002772
PCS*MCS−0.000520.0002744−0.00058160.0002883−0.00026410.0003168
Adjusted R20.01470.05130.0830
ME0.06620.07030.07610.0654−0.0100
MAE0.19690.20450.20390.26720.1531
RMSE0.2479360.2668840.2600140.3511590.221678
|Differencel|b
|Δ| ≤ 0.105131%5534%5836%5836%9458%
|Δ| ≤ 0.052314%3421%3924%3622%5634%
|Δ| ≤ 0.0174%159%88%176%1610%
ActualPredictPredictPredictPredictPredict
Mean0.66900.60280.59870.59290.60370.6790
SD0.292540.072500.12770.158070.196920.12368
Min.−0.240.46−0.20−0.24−0.500.10
Max.1.000.710.760.860.910.84
Rangec1.020.2560.6070.7550.8460.541

SE, robust standard error.

a

With adjustment for repeated measurements at 1, 3 and 12 months' follow-up.

b

Proportion of predicted values with errors < |0.01|, |0.05| and |0.10|.

c

Range = maximum value - minimum value.

Validation data set = 163.

From: Appendix 14, Exploratory mapping analysis

Cover of Management of Frozen Shoulder: A Systematic Review and Cost-Effectiveness Analysis
Management of Frozen Shoulder: A Systematic Review and Cost-Effectiveness Analysis.
Health Technology Assessment, No. 16.11.
Maund E, Craig D, Suekarran S, et al.
Southampton (UK): NIHR Journals Library; 2012 Mar.
© 2012, Crown Copyright.

Included under terms of UK Non-commercial Government License.

NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.