I don't think this information can be found in the documentation, but you can always just check the actual influence.measures() and print.infl() code to find out. Most importantly, influence.measures() incldues the following code: function (model) { is.influential <- function(infmat, n) { k <- ncol(infmat) - 4 if (n <= k) stop("too few cases, n < k") absmat <- abs(infmat) result <- cbind(absmat[, 1L:k] > 1, absmat[, k + 1] > 3 * sqrt(k/(n - k)), abs(1 - infmat[, k + 2]) > (3 * k)/(n - k), pf(infmat[, k + 3], k, n - k) > 0.5, infmat[, k + 4] > (3 * k)/n) dimnames(result) <- dimnames(infmat) result } ... infmat <- cbind(dfbetas, dffit = dffits, cov.r = cov.ratio, cook.d = cooks.d, hat = h) ... is.inf <- is.influential(infmat, sum(h > 0)) ... } So, a case is flagged if: - any of its absolute dfbetas values are larger than 1, or - its absolute dffits value is larger than 3*sqrt(k/(n-k)), or - abs(1 - covratio) is larger than 3*k/(n-k), or - its Cook's distance is larger than the 50% percentile of an F-distributio with k and n-k degrees of freedom, or - its hatvalue is larger than 3*k/n, where k denotes the number of model coefficients (e.g., k = 2 for simple regression with the intercept included in the model). Note in RPD, k=p'