AUC_IF {dmetatools}

Influence diagnostics based on the AUC of summary ROC curve

Description

Influence diagnostics based on AUC of the summary ROC curve by leave-one-out analysis. The threshold to determine influential outlying study is computed by parametric bootstrap.

Usage

AUC_IF(TP, FP, FN, TN, B=2000, alpha=0.95)

Arguments

TP

A vector of the number of true positives (TP)

FP

A vector of the number of false positives (FP)

FN

A vector of the number of false negatives (FN)

TN

A vector of the number of true negatives (TN)

B

The number of bootstrap resampling (default: 2000)

alpha

The error level to be calculated for the bootstrap interval of deltaAUC (default: 0.95)

Value

Influence diagnostic statistics based on the AUC of the summary ROC curve. The output is sorted by the absolute size of deltaAUC.

• AUC: The AUC of the summary ROC curve.

• id: identification number.

• AUC(-i): The AUC estimate if ith study is excluded.

• deltaAUC: The difference of AUC estimates for all study and for the subpopulation that ith study is excluded.

• Q1: Default 2.5th percentile of the bootstrap distribution of deltaAUC (can be changed by alpha).

• Q2: Default 97.5th percentile of the bootstrap distribution of deltaAUC (can be changed by alpha).

Author(s)

Hisashi Noma <[e-mail]>

References

Noma, H., Matsushima, Y., and Ishii, R. (2021). Confidence interval for the AUC of SROC curve and some related methods using bootstrap for meta-analysis of diagnostic accuracy studies. Communications in Statistics: Case Studies and Data Analysis 7: 344-358. doi:10.1080/23737484.2021.1894408

Examples

require(mada)

data(asthma)

fit1 <- reitsma(asthma)    # DTA analysis using the Reitsma model
summary(fit1)

plot(fit1)		# Plot the SROC curves
points(fpr(asthma), sens(asthma), cex = .5)

attach(asthma)
AUC_IF(TP, FP, FN, TN, B=2)    # Influential analysis based on the AUC
detach(asthma)
# This is an example command for illustration. B should be >= 1000.