M

Macro-edit (selective edit)

Detection of individual errors by:

1) checks on aggregated data, or

2) checks applied to the whole body of records.

The checks are typically based on the models, either graphical or numerical formula based, that determine the impact of specific fields in individual records on the aggregate estimates.

Source: UNECE Data Editing Group

See also: Micro-Editing, Selective Editing

Manual Correction

A human activity aimed at changing the values of data items deemed erroneous. The correction specified usually on the diagnostic list is entered into the data set by means of a program specially written for this purpose.

Source: UNECE Data Editing Group

Manual Data Review

May occur prior to data entry. The data may be reviewed and prepared/corrected prior to key-entry. This procedure is more typically followed when heads-down data entry is used.

Source: UNECE Data Editing Group

Matching Fields

See: Editing Match

Micro-editing

Finding errors by inspection of individual observations. Editing done at the record, or questionnaire level.

Source: UNECE Data Editing Group

See also: Macro-Edit, Selective Editing

Minimal Set of Conflict Rules

A minimal subset of the complete set of conflict rules expressing the same erroneous data combinations as the complete set of conflict rules.

Source: UNECE Data Editing Group

Minimal Set of Fields to Impute

The smallest set of fields requiring imputation that will guarantee that all edits are passed. See also weighted minimal set.

Source: UNECE Data Editing Group

Mixed Imputation

In most systems there usually is a mixture of categories used in some fixed rank fashion for all items. For example, first a deterministic approach is used. If it is not successful, then a hot deck approach is tried. This is followed by a model-based approach. If all these approaches fail, then a manual imputation occurs through a human review process.

Source: UNECE Data Editing Group

See Also: Automated Imputations

Model-based Imputation

Use of averages, medians, regression equations, etc. to impute a value.

Source: UNECE Data Editing Group

See Also: Automated Imputations

Monitoring of Editing

Analyzing the audit trail and evaluating the edits for efficiency. *Note: This definition may not be fully satisfactory.

Source: UNECE Data Editing Group

Monte-Carlo Method for Autocorrection

An automatic correction method in which the corrected data value is randomly chosen on the basis of a previously supplied probability distribution for this data item. The method employs computer algorithms for generating pseudo-random variables with the given probability distribution.

Source: UNECE Data Editing Group

Multi-level Modeling Imputation

An imputation rule defined by a sequence of decisions each based on exclusive sets of observations.

Source: UNECE Data Editing Group

Multivariate Edit

A type of statistical edit where multivariate distributions are used to evaluate the data and to find outliers.

Source: UNECE Data Editing Group