dx_ppv_prevalence: Calculate Positive Predictive Value (PPV) at Target...

In overdodactyl/diagnosticSummary: Diagnostic Summaries

Calculate Positive Predictive Value (PPV) at Target Prevalence

Description

Computes the Positive Predictive Value (PPV) adjusted to a specified prevalence level. This function is useful for understanding classifier performance in settings where the actual prevalence of the condition may differ from that in the initial data.

Usage

dx_ppv_prevalence(cm, prevalence, detail = "full", ...)

Arguments

cm	A dx_cm object created by dx_cm().
prevalence	Numeric value between 0 and 1, representing the target prevalence for adjusting the PPV calculation.
detail	Character specifying the level of detail in the output: "simple" for raw estimate, "full" for detailed estimate including 95% confidence intervals.
...	Additional arguments to pass to metric_binomial function, such as citype for type of confidence interval method.

Details

This function calculates the PPV using the formula:

PPV = \frac{Sensitivity \times Prevalence}{(Sensitivity \times Prevalence) + (1 - Specificity) \times (1 - Prevalence)}

where Sensitivity is the true positive rate and Specificity is the true negative rate. Adjusting PPV for prevalence allows a more accurate assessment of the classifier’s performance in different population settings.

Confidence intervales are calucated using a simple logit (Mercaldo et al, 2007)

Value

Depending on the detail parameter, returns a numeric value representing the calculated metric or a data frame/tibble with detailed diagnostics including confidence intervals and possibly other metrics relevant to understanding the metric.

See Also

dx_cm(), dx_ppv() for the non-prevalence adjusted PPV.

Examples

cm <- dx_cm(dx_heart_failure$predicted, dx_heart_failure$truth,
  threshold = 0.5, poslabel = 1
)
# Calculate PPV at a prevalence of 0.1
dx_ppv_prevalence(cm, prevalence = 0.1)

overdodactyl/diagnosticSummary documentation built on Jan. 29, 2025, 11:11 a.m.