ss_cal_slope: Minimum sample size for external validation of a clinical...

In Ayushi-712/ssclip: SAMPLE SIZE REQUIRED TO TARGET PRECISE ESTIMATES OF PREDICTIVE PERFORMANCE

Description

Precise estimate of calibration slope

Usage

ss_cal_slope(R2, lambda, width, alpha)

Arguments

R2	Expected coefficient of determination (R2) of the calibration model
lambda	Anticipated (mis)calibration across the range of predicted values
width	Width of confidence interval of lambda
alpha	Level of Significance

Value

A html file contains minimum sample size

References

Archer L, Snell KIE, Ensor J, Hudda MT, Collins GS, Riley RD. Minimum sample size for external validation of a clinical prediction model with a continuous outcome. Stat Med. 2020;40:133-46.

See Also

ss_citl, ss_R2val , ss_res_var , ss_sens , ss_spec

Examples

#Eg. Sample size to target a 95% confidence interval for 𝜆cal
#that has a narrow width ≤ 0.2 (eg, if the calibration slope was 1,
# the confidence interval would be 0.9 to 1.1 assuming confidence
#intervals derived by 𝜆̂cal ± 1.96SE𝜆̂cal) and assuming R2val = 0.5 .
ss_cal_slope( R2= 0.5,width = 0.2,alpha = 0.05, lambda = 1)

#for different combinations of parameters
ss_cal_slope( R2= c(0.7,0.8),width =c( 1.1,1.2),alpha = 0.05, lambda = 1)

Ayushi-712/ssclip documentation built on Feb. 4, 2022, 11:50 p.m.