ebc_tidy_by_threshold {evabic} R Documentation

## Measures by threshold

### Description

Computes measures according to a moving threshold.

### Usage

```ebc_tidy_by_threshold(
detection_values,
true,
all,
m = length(all),
measures = c("TPR", "FPR", "FDR", "ACC", "F1"),
direction = c("<", ">", "<=", ">=")
)
```

### Arguments

 `detection_values` Values corresponding to elements that are detected. Must be named. `true` Vector of element that are supposed to be detected. `all` Vector of all elements. `m` Total number of elements. `measures` Desired measures of performance. `direction` With `<` (default), detected elements are those which are strictly less than the threshold. Could be change to `">"`, `<=` or `>=`.

### Details

See `ebc_allmeasures` for the available measures and their descriptions.

### Value

A dataframe with one column called threshold and other corresponding to those specified in `measures`.

### Examples

```set.seed(42)
X1 <- rnorm(50)
X2 <- rnorm(50)
X3 <- rnorm(50)
predictors <- paste0("X", 1:3)
df_lm <- data.frame(X1 = X1, X2 = X2, X3 = X3,
X4 = X1 + X2 + X3 + rnorm(50, sd = 0.5),
X5 = X1 + 3 * X3 + rnorm(50, sd = 0.5),
X6 = X2 - 2 * X3 + rnorm(50, sd = 0.5),
X7 = X1 - X2 + rnorm(50, sd = 2),
Y  = X1 - X2 + 3 * X3 + rnorm(50))
model <- lm(Y ~ ., data = df_lm)
pvalues <- summary(model)\$coefficients[-1, 4]
ebc_tidy_by_threshold(pvalues, predictors, m = 7)
```

[Package evabic version 0.0.3 Index]