missing data

(redirected from Missing values)
Also found in: Wikipedia.

missing data

EBM
A term used in the context of a clinical trial for:
(1) Data not completed or corrupted in reports and case report forms; or
(2) Data not captured when a subject withdraws from a trial.
 
Clinical trial reviewers are usually more concerned about non-captured data, as patients who are not improved or who believe they have experienced side effects are more prone to leave a trial, thus skewing the analysis of results if such analysis were only done on subjects who had continued with the trial. Trial designs therefore specify plans for how such missing data will be treated in analysis.
References in periodicals archive ?
However, a problem of this questionnaire was the presence of missing values, questions that are left unanswered due to lack of information.
2) Replace missing values with most suitable constant values
Another issue that is addressed in this paper is the one of missing values, which is the endemic problem for researchers working with economic indicators for a set of countries.
Contract awarded for Purchase of SPSS missing values user license or its equivalent
The second approach comprises value imputation methods, wherein missing values are estimated and these methods are divided into two: single and multiple imputation (MI).
The author has organized the main body of his text in nine chapters focused on weighting methods, imputation, multiple imputations, regression analysis, longitudinal analysis with missing values, and a variety of other related subjects.
Remarks at both reports regarding AQMS mention that missing values were due to rapid load shedding and AVR tripping.
Saravanan and Sailakshmi [13] propose fuzzy probabilistic c-means algorithms to impute the missing values using the genetic algorithm.
In addition, an implementation of Kalman filter that can be used to estimate the missing values, estimate the velocity of movement from recorded locations, and for smooth the signal is described.
As far as imputation goes, their problem is very simple, because race/ ethnicity is the only variable with missing values.
Normalization: Translating and formatting data from each source consistently by sourcing missing values
First introduced in 1960's, decision trees are one of the most effective methods for data mining; they have been widely used in several disciplines [l] because they are easy to be used, free of ambiguity, and robust even in the presence of missing values.