C

CAI

CAI (Computer-assisted interviewing) uses the computer during interviewing. Any contradictory data can be flagged by edit routines and the resultant data can be immediately adjusted by information from the respondent. An added benefit is that data capture (key-entry) is occurring at interview time. CAI assists the interview in the wording of questions and tailors succeeding questions based on previous responses. CAI has been mainly used in Computer-Assisted Telephone Interviews (CATI) or Computer-Assisted Personal Interviewing (CAPI).

Source: UNECE Data Editing Group

See: CASIC (Computer-Assisted Survey Information Collection)

CASIC

The acronym "CASIC" stands for computer assisted survey information collection. This encompasses computer assisted data collection and data capture. CASIC may be more broadly defined to include the use of computer assisted, automated, or advanced computing methods for data editing and imputation, data analysis and tabulation, data dissemination, or other steps in the survey or census process.

Source: UNECE Data Editing Group

See: CAI (Computer-Assisted Interviewing)

Check Digit

See: Error Detecting Characters

Checking Rule (edit rule)

A logical condition or a restriction to the value of a data item or a data group which must be met if the data is to be considered correct. In various connections other terms are used, e.g. edit rule.

Source: UNECE Data Editing Group

Checking Rule Specification (edit rule specification)

A set of checking rules that should be applied in the given editing task.

Source: UNECE Data Editing Group

Class Attribute Check

Verifying whether the value of the common attributes (class attributes) of a logical unit or its components are identical.

Source: UNECE Data Editing Group

Code List (list of code words)

List of all allowed (admissible) values of a data item.

Source: UNECE Data Editing Group

Code Redundancy

When a character or group of characters in a code word can be partially or completely deduced from the remaining characters of the code word.

Source: UNECE Data Editing Group

Code Space

A set of all combinations of admissible values of a particular record of data. Cartesian product of the code word lists of individual data in a record.

Source: UNECE Data Editing Group

Code Structure Check

See: Code Structure Validation

Code Structure Validation

Verifying whether the characters of the correct type (e.g., digits, letters) are at the correct positions of the code word.

Source: UNECE Data Editing Group

Cold-deck

A correction base for which the elements are given before correction starts and do not change during correction. An example would be using prior year's data. A modified cold-deck may adjust cold-deck values according to (possibly aggregate) current information.

Source: UN/ECE Data Editing Group

See also: Hot-Deck,  Deck Imputation

Complete Set of Conflict Rules

A set of explicitly given conflict rules and of all implied conflict rules.

Source: UNECE Data Editing Group

Complete Set of Edits

The union of explicit edits and implied edits. Sufficient for the generation of feasible (acceptance) regions for imputation (that is if the imputations are to satisfy the edits).

Source: UNECE Data Editing Group

Completeness Checking

- Completeness Checking at survey level ensures that all survey data have been collected. A minimal completeness check compares the sample count to the questionnaire count to insure that all samples are accounted for, even if no data were collected.

- Completeness Checking at questionnaire level insures that routing instructions have been followed. Questionnaires should be coded to specify whether the respondent was inaccessible or has refused, this information can be used in verification procedures.

Source: UNECE Data Editing Group

Composition Check

Verifying whether the structure of a logical unit (e.g. - household) is consistent with the definition (e.g., at least one adult).

Example: A household must have at least one adult

Source: UNECE Data Editing Group

Computer-assisted Interviewing

See: CAI

Computer-Assisted Survey Information Collection

See: CASIC

Conditional Edit

An edit where the value of one field determines the editing relationship between other fields and possibly itself. For example, suppose there are three fields A, B, and C. A conditional edit would exist if the relationship between fields B and C as expressed through the edits depended on the value in A.

Example:
1) If A>0 then B>C
2) If A>B then C>B

Source: UNECE Data Editing Group

Conflict Rule (rejection rule)

A logical condition or a restriction to the value of a data item or a data group which must not be met if the data is to be considered correct.

Source: UNECE Data Editing Group

See also: Rejection Rule

Consistency Check

Detecting whether the value of two or more data items are not in contradiction.

Source: UNECE Data Editing Group

Consistency Edit

A check for determinant relationships, such as parts adding to a total or harvested acres being less than or equal to planted acres.

Source: UNECE Data Editing Group

Consistency Error

Occurrence of the values of two or more data items which do not satisfy some predefined relationship between those data items.

Source: UNECE Data Editing Group

Consistent Edit

A set of edits which do not contradict each other is considered to be consistent. If edits are not consistent, then no record can pass the edits.

Source: UNECE Data Editing Group

Correction Base

A set of correct data or records from which date or records are retrieved for imputation in the (probably) erroneous data or records.

Source: UNECE Data Editing Group

*Correction Cycle

A cycle in which corrections (changes) are made to a record according to an existing edit/imputation strategy. If there are logical inconsistencies in the strategy or software contains error, then it may be possible for a record to pass through the edit/imputation software and still fail edits. If the record fails at the end of a cycle, then it is sent through the edit/imputation software subroutines until it passes or until a pre-determined number of cycles has been exceeded.

*Note: This definition may not be fully satisfactory.

Source: UNECE Data Editing Group

Correction of Errors in Data

See: Data Correction

Correction Rule

A rule for correcting certain types of errors. Its general form is as follows: "If errors are detected by the checks e1, ......, ek, make a correction in this way:

Source: UNECE Data Editing Group

*Creative Editing

Manual editors (i.e., those doing the manual review) invent editing procedures to avoid reviewing another error message from subsequent machine editing. As an example, a survey or census may ask for information that is too detailed for respondents to provide. For those types of responses, if the manual editors compare the current responses with data reported in the previous period, then they may need to deduct amounts from the reported values and allocate them to the areas for which no current values were reported.

*Note: This definition may not be fully satisfactory.

Source: UNECE Data Editing Group