Completeness of optional attributes

Characteristic Name:	Completeness of optional attributes
Dimension:	Completeness
Description:	Optional attributes should not contain invalid null values
Granularity:	Element
Implementation Type:	Rule-based approach
Characteristic Type:	Declarative

Verification Metric:

The number of invalid null values reported in an optional attribute per thousand records

GuidelinesExamplesDefinitons

The implementation guidelines are guidelines to follow in regard to the characteristic. The scenarios are examples of the implementation

Guidelines:	Scenario:
Provide default values for each valid case of null values for the attribute in concern so that null values occur only for actually missing values which are invalid cases for the attribute in concern.	Case1: Attribute values that are not defined for a particular entity instance (e.g.: Maiden name of unmarried women ) Such instances will get the default value “NOT DEFINED” Case2 : Attribute values that are defined for the entity instance whereas the real value for the attribute instance is null (eg: Vehicle number of a student who does not have a vehicle) Such instances will get the default value “NOT EXIST” Case3: Attribute values are defined for the entity instance and the attribute instance should have a value (Student’s date of birth).

Guidelines:

Scenario:

Provide default values for each valid case of null values for the attribute in concern so that null values occur only for actually missing values which are invalid cases for the attribute in concern.

Case1: Attribute values that are not defined for a particular entity instance (e.g.: Maiden name of unmarried women ) Such instances will get the default value “NOT DEFINED”

Case2 : Attribute values that are defined for the entity instance whereas the real value for the attribute instance is null (eg: Vehicle number of a student who does not have a vehicle) Such instances will get the default value “NOT EXIST”

Case3: Attribute values are defined for the entity instance and the attribute instance should have a value (Student’s date of birth).

Validation Metric:

How mature is the creation and implementation of the DQ rules to define valid null cases

These are examples of how the characteristic might occur in a database.

Example:	Source:
Let us consider a Person relation with the attributes Name, Surname, BirthDate,and Email. The relation is shown in Figure 2.2. For the tuples with Id equalto2,3,and 4, the Email value is NULL. Let us suppose that the person represented by tuple 2 has no e-mail: no incompleteness case occurs. If the person represented by tuple 3 has an e-mail, but its value is not known then tuple 3 presents an incompleteness. Finally, if it is not known whether the person represented by tuple 4 has an e-mail or not, incompleteness may not be the case. ID 1 2 3 4 Name John Edward Anthony Marianne Surname Smith Monroe White Collins BirthDate 03/17/1974 02/03/1967 01/01/1936 11/20/1955 Email smith@abc.it NULL NULL NULL not existing existing but unknown not known if existing Fig. 2.2. The Person relation, with diﬀerent null value meanings for the e-mail attribute	C. Batini and M, Scannapieco, “Data Quality: Concepts, Methodologies, and Techniques”, Springer, 2006.
1) A database contains information on repairs done to capital equipment. How- ever, it is a known fact that sometimes the repairs are done and the informa- tion about the repair is just not entered into the database. This is the result of lack of concern on the part of the repair people and a lack of enforcement on the part of their supervisors. It is estimated that the amount of missing information is about 5%. This database is probably a good-quality database for assessing the genral health of capital equipment. Equipment that required a great deal of expense to maintain can be identiﬁed from the data. Unless the missing data is disproportionately skewed, the records are usable for all ordinary decisions. However, trying to use it as a base for evaluating information makes it a low-quality database. The missing transactions could easily tag an important piece of equipment as satisfying a warranty when in fact it does not. 2) A blank for COLLEGE_LAST_ATTENDED may be accurate or inaccurate. If the person it applied to had attended college, it would be inaccurate. This is another case of valid but not accurate.	J. E. Olson, “Data Quality: The Accuracy Dimension”, Morgan Kaufmann Publishers, 9 January 2003.

Example:

Source:

Let us consider a Person relation with the attributes Name, Surname,

BirthDate,and Email. The relation is shown in Figure 2.2. For the tuples with Id equalto2,3,and 4, the Email value is NULL. Let us suppose that the person represented by tuple 2 has no e-mail: no incompleteness case occurs. If the person represented by tuple 3 has an e-mail, but its value is not known then tuple 3 presents an incompleteness. Finally, if it is not known whether the person represented by tuple 4 has an e-mail or not, incompleteness may not be the case.

ID 1

2 3 4

Name John

Edward Anthony Marianne

Surname Smith

Monroe White Collins

BirthDate 03/17/1974 02/03/1967 01/01/1936 11/20/1955

smith@abc.it NULL NULL NULL

not existing existing but unknown not known if existing

Fig. 2.2. The Person relation, with diﬀerent null value meanings for the e-mail attribute

C. Batini and M, Scannapieco, “Data Quality: Concepts, Methodologies, and Techniques”, Springer, 2006.

1) A database contains information on repairs done to capital equipment. How- ever, it is a known fact that sometimes the repairs are done and the informa- tion about the repair is just not entered into the database. This is the result of lack of concern on the part of the repair people and a lack of enforcement on the part of their supervisors. It is estimated that the amount of missing information is about 5%. This database is probably a good-quality database for assessing the genral health of capital equipment. Equipment that required a great deal of expense to maintain can be identiﬁed from the data. Unless the missing data is disproportionately skewed, the records are usable for all ordinary decisions. However, trying to use it as a base for evaluating information makes it a low-quality database. The missing transactions could easily tag an important piece of equipment as satisfying a warranty when in fact it does not.

2) A blank for COLLEGE_LAST_ATTENDED may be accurate or inaccurate. If the person it applied to had attended college, it would be inaccurate. This is another case of valid but not accurate.

J. E. Olson, “Data Quality: The Accuracy Dimension”, Morgan Kaufmann Publishers, 9 January 2003.

The Definitions are examples of the characteristic that appear in the sources provided.

Definition:	Source:
1) A null value is a missing value. However, a value that is missing may provide more information than one might think because there may be different reason that it is missing. A null value might actually represent an unavailable value, an attribute that is not applicable for this entity, or no value in the attribute’s domain that correctly classifies this entity. Of course, the value may actually be missing. 2) When the null value (or absence of a value) is required for an attribute, there should be a recognizable form for presenting that null value that does not conflict with any valid values.	LOSHIN, D. 2001. Enterprise knowledge management: The data quality approach, Morgan Kaufmann Pub.
1) Ability to distinguish neatly (without ambiguities) null and default values from applicable values of the domain. 2) Completeness refers to the degree to which values are present in a data collection, as for as an individual datum is concerned, only two situations are possible: Either a value is assigned to the attribute in question or not. In the latter case, null, a special element of an attribute’s domain can be assigned as the attribute’s value. Depending on whether the attribute is mandatory, optional, or inapplicable, null can mean different things.	REDMAN, T. C. 1997. Data quality for the information age, Artech House, Inc.

Definition:

Source:

1) A null value is a missing value. However, a value that is missing may provide more information than one might think because there may be different reason that it is missing. A null value might actually represent an unavailable value, an attribute that is not applicable for this entity, or no value in the attribute’s domain that correctly classifies this entity. Of course, the value may actually be missing.

2) When the null value (or absence of a value) is required for an attribute, there should be a recognizable form for presenting that null value that does not conflict with any valid values.

LOSHIN, D. 2001. Enterprise knowledge management: The data quality approach, Morgan Kaufmann Pub.

1) Ability to distinguish neatly (without ambiguities) null and default values from applicable values of the domain.

2) Completeness refers to the degree to which values are present in a data collection, as for as an individual datum is concerned, only two situations are possible: Either a value is assigned to the attribute in question or not. In the latter case, null, a special element of an attribute’s domain can be assigned as the attribute’s value. Depending on whether the attribute is mandatory, optional, or inapplicable, null can mean different things.

REDMAN, T. C. 1997. Data quality for the information age, Artech House, Inc.

Statistical validity

Characteristic Name:	Statistical validity
Dimension:	Validity
Description:	Computed data must be statistically valid
Granularity:	Information object
Implementation Type:	Process-based approach
Characteristic Type:	Usage

Verification Metric:

The number of tasks failed or under performed due to lack of statistical validity in data

The number of complaints received due to lack of statistical validity of data

GuidelinesExamplesDefinitons

The implementation guidelines are guidelines to follow in regard to the characteristic. The scenarios are examples of the implementation

Guidelines:	Scenario:
Establish the population of interest unambiguously with appropriate justification (maintain documentation)	(1) Both credit customers and cash customers are considered for a survey on customer satisfaction.
Establish an appropriate sampling method with appropriate justification	(1) Stratified sampling is used to investigate drug preference of the medical officers
Establish statistical validity of samples -avoid over coverage and under coverage (maintain documentation)	(1) Samples are taken from all income levels in a survey on vaccination
Maintain consistency of samples in case longitudinal analysis is performed. (Maintain documentation)	(1) Same population is used over the time to collect epidemic data for a longitudinal analysis
Ensure that valid statistical methods are used to enable valid inferences about data, valid comparisons of parameters and generalise the findings.	(1) Poisson distribution is used to make inferences since data generating events are occurred in a fixed interval of time and/or space
Ensure that the acceptable variations for estimated parameters are established with appropriate justifications	(1) 95% confidence interval is used in estimating the mean value
Ensure that appropriate imputation measures are taken to nullify the impact of problems relating to outliers, data collection and data collection procedures and the edit rules are defined and maintained.	(1) Incomplete responses are removed from the final data sample

Validation Metric:

How mature is the process to maintain statistical validity of data

These are examples of how the characteristic might occur in a database.

Example:	Source:
if a column should contain at least one occurrence of all 50 states, but the column contains only 43 states, then the population is incomplete.	Y. Lee, et al., “Journey to Data Quality”, Massachusetts Institute of Technology, 2006.

The Definitions are examples of the characteristic that appear in the sources provided.

Definition:	Source:
Coherence of data refers to the internal consistency of the data. Coherence can be evaluated by determining if there is coherence between different data items for the same point in time, coherence between the same data items for different points in time or coherence between organisations or internationally. Coherence is promoted through the use of standard data concepts, classifications and target populations.	HIQA 2011. International Review of Data Quality Health Information and Quality Authority (HIQA), Ireland. http://www.hiqa.ie/press-release/2011-04-28-international-review-data-quality.
1) Accuracy in the general statistical sense denotes the closeness of computations or estimates to the exact or true values. 2) Coherence of statistics is their adequacy to be reliably combined in different ways and for various uses.	LYON, M. 2008. Assessing Data Quality , Monetary and Financial Statistics. Bank of England. http://www.bankofengland.co.uk/ statistics/Documents/ms/articles/art1mar08.pdf.

Definition:

Source:

Coherence of data refers to the internal consistency of the data. Coherence can be evaluated by determining if there is coherence between different data items for the same point in time, coherence between the same data items for different points in time or coherence between organisations or internationally. Coherence is promoted through the use of standard data concepts, classifications and target populations.

HIQA 2011. International Review of Data Quality Health Information and Quality Authority (HIQA), Ireland. http://www.hiqa.ie/press-release/2011-04-28-international-review-data-quality.

1) Accuracy in the general statistical sense denotes the closeness of computations or estimates to the exact or true values.

2) Coherence of statistics is their adequacy to be reliably combined in different ways and for various uses.

LYON, M. 2008. Assessing Data Quality ,
Monetary and Financial Statistics.
Bank of England. http://www.bankofengland.co.uk/
statistics/Documents/ms/articles/art1mar08.pdf.