Sensitivity Analysis to Select the Most Influential Risk Factors in a Logistic Regression Model

Table 1

Estimated coefficients and standard errors for different variable selection methods.

Methods	MLE	Best subset AIC	Best subset BIC	SCAD	LASSO	SA 𝑆𝑖(𝑆𝑇𝑖)
Factors
Intercept	5.51 (0.75)	4.81 (0.45)	6.12 (0.57)	6.09 (0.29)	3.70 (0.25)	Constant
𝑋1	−8.8 (2.97)	−6.49 (1.75)	−12.15 (1.81)	−12.2 (.08)	0 (—)	0.487 (0.536)
𝑋2	2.30 (2.00)	0 (—)	0 (—)	0 (—)	0 (—)	0.014 (0.125)
𝑋3	−2.77 (3.43)	0 (—)	−6.93 (0.79)	−7.0 (0.21)	0 (—)	0.143 (0.218)
𝑋4	−1.74 (1.41)	0.30 (0.11)	−0.29 (0.11)	0 (—)	−0.28 (0.09)	0.003 (0.034)
𝑋^21	−0.75 (.61)	−1.04 (0.54)	0 (—)	0 (—)	−1.71 (0.24)	0.013 (0.057)
𝑋^23	−2.7 (2.45)	−4.55 (0.55)	0 (—)	0 (—)	−2.67 (0.22)	0.032 (0.091)
𝑋1𝑋2	0.03 (0.34)	0 (—)	0 (—)	0 (—)	0 (—)	0.014 (0.237)
𝑋1𝑋3	7.46 (2.34)	5.69 (1.29)	9.83 (1.63)	9.84 (0.14)	0.36 (0.22)	0.362 (0.502)
𝑋1𝑋4	0.24 (0.32)	0 (—)	0 (—)	0 (—)	0 (—)	0.001 (0.042)
𝑋2𝑋3	−2.15 (1.61)	0 (—)	0 (—)	0 (—)	−0.10 (0.10)	0.016 (0.075)
𝑋2𝑋4	−0.12 (0.16)	0 (—)	0 (—)	0 (—)	0 (—)	0.003 (0.047)
𝑋3𝑋4	1.23 (1.21)	0 (—)	0 (—)	0 (—)	0 (—)	0.019 (0.307)