This function provides detailed information regarding the comparison of two competing methods, for example self-report and gold-standard treatment through a sensitivity/specificity analysis.
sensSpec(X, alpha=0.05, CL=TRUE, digits=3)A 2x2 matrix, with Gold Standard Class A and B in the columns and Comparison Method A and B in the rows.
Logical: If TRUE, Confidence Intervals are calculated and displayed in summary method.
The desired Type I Error Rate for Hypothesis Tests and Confidence Intervals
Number of Digits to round calculations
The original input matrix.
The point estimate of sensitivity
The point estimate of specificity
The point estimate of Percent Agreement
The point estimate of Youden's J
The standard deviation of sensitivity
The standard deviation of specificity
The standard deviation of Percent Agreement
The standard deviation of Youden's J
The lower bound of the constructed confidence interval for true sensitivity.
The upper bound of the constructed confidence interval for true sensitivity
The lower bound of the constructed confidence interval for true specificity.
The upper bound of the constructed confidence interval for true specificity.
The lower bound of the constructed confidence interval for Percent Agreement.
The upper bound of the constructed confidence interval for Percent Agreement.
The lower bound of the constructed confidence interval for Youden's J.
The upper bound of the constructed confidence interval for Youden's J.
The desired Type I Error Rate for Hypothesis Tests and Confidence Intervals
Number of Digits to round calculations
This function is designed to calculate Sensitivity, Specificity, Youden's J and Percent Agreement. These tools are used to assess the validity of a new instrument or self-report against the current gold standard. In general, self-report is less expensive, but may be subject to information bias. Computational formulae can be found in the reference.
Szklo M and Nieto FJ. Epidemiology: Beyond the Basics, Jones and Bartlett: Boston, 2007.
# NOT RUN {
From Szklo and Nieto, p. 315
# }
# NOT RUN {
dat <- cbind(c(18,1), c(19,11));
summary(sensSpec(dat));
# }
Run the code above in your browser using DataLab