outlier


Also found in: Dictionary, Thesaurus, Financial, Encyclopedia, Wikipedia.

outlier

 [out´li-er]
an observation so distant from the central mass of the data that it noticeably influences results and must be carefully checked to ensure it is not an error.

out·li·er

(owt'lē-ĕr),
An observation that differs so widely from all others in a set as to justify the conclusion that a gross error has occurred or that it comes from a different population.

outlier

Any value outside of an expected range.

outlier

Managed care A Pt who falls outside of the norm–ie, who has an extremely long length of hospital stay or has incurred extraordinarily high costs. See Extreme outlier, High mortality outlier.

out·li·er

(owt'lī-ĕr)
1. Deviant values or figures that are obviously from a different population than those from the rest of the sample.
2. Additions to an estimated cost of delivered services when exceeding a fixed loss threshold.
References in periodicals archive ?
The most common outlier treatments in finance are winsorizing, trimming, and dropping (referred to hereafter as WTD).
As "Outliers" argues, this constant churning--this trespassing of the borders of high and low, this teetering between the unknown and the famous--is essential to the dynamism of American art itself.
"Joint Estimation of Model Parameters and Outlier Effects in Time Series." Journal of the American Statistical Association, 88, 1993, 284-97.
Some outliers may position themselves on the fringe, seeking to gain reputations as innovators.
Before applying the LOF algorithm, it is necessary to specify two parameters: the number of closest neighbours k and the threshold value, above which it is considered that the record is outlier. When choosing the number of closest neighbours, it is recommended that k value would be equal to square root of all data, used for the model training.
For the point outliers, results from outlier method #1 (Standard Deviation), #2 (Quartile), and # 3 (Grubbs' Test) are 7, 17, 12 outliers respectively.
From a practical point of view, it is well known that Pearson's correlation is not resistant to outliers and thus choosing weights in (2) based on this correlation will cause uncertain and deceptive results.
The relative prediction error term indicates whether the point is an outlier. The larger value of [r.sub.t] means the current point is more suspicious to be an outlier.
Velleman, "BACON: blocked adaptive computationally efficient outlier nominators," Computational Statistics and Data Analysis, vol.
Ruiz-Gazen, Outlier Detection Using Invariant Coordinate Selection.
Unlike other outlier detect method (such as the traditional AR model detection method), the outliers detect method proposed in this paper does not need to set the detection threshold.
It works on the premise that many outliers are unaware they are an outlier, no one wants to be an outlier, and confidential, collegial education and peer mentoring within a medical specialty society can reduce unnecessary variations in care.