N

*Neural Networks

Automated imputation method which uses artificial intelligence.

*Note: This definition may not be fully satisfactory.

Source: UNECE Data Editing Group

New Imputation Methodology

See: NIM

NIM

Mew Imputation Methodology: A generalization of the hot-deck that employs sophisticated matching methods to chose potential donors from a pool of edit-passing records that most closely resemble the edit-failing record being donated to. The method uses additional metrics for comparing numeric data and specific logic to assure that records satisfy edits that are not available with traditional hot-deck methods. A more complete description is available in the NIM evaluation page, on this site.

Source: UNECE Data Editing Group

Non-linear Edits

Edits from non-linear constraints. For example, if v1 and v2 are variables and b are real constants, then nonlinear edits are:
1. v1 v2 b.
2. v1 exp(v2).
3. conditional edits.
4. Mahalanobis-distance edits with multivariate normal data.

The importance of nonlinear edits is that they occur often but are not amendable to theory in the determination of a minimal set. Some nonlinear edits, such as ratio edits, can be cast in a linear form.

Source: UNECE Data Editing Group

Normal Form of Conflict Rule

A conflict rule which is defined by the logical product of conditions on the values of individual data items in a record.

Example: The conflict (branch - (101, 107, 112); production 104, 180; efficiency 0.8) is a conflict in the normal form (CAN-EDIT).

Source: UNECE Data Editing Group