Wand, Y. and Wang, R.Y. (1996) Anchoring data quality dimensions in ontological foundations, Communications of the ACM, 39, 11, 86--95.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....should be considered correct, unless shown as definite errors. 1.1. Why outliers should be isolated The main reason for isolating outliers is associated with data quality assurance. The exceptional values are more likely to be incorrect. According to the definition, given by Wand and Wang [14] unreliable data represents an unconformity between the state of the database and the state of the real world. For a variety of database applications, the amount of erroneous data may reach ten percent and even more [15] Thus, removing or replacing outliers can improve the quality of stored ....

....on 768 patients. In the dataset, there are eight continuous attributes and one binary valued attribute. No data cleaning is mentioned in the dataset documentation. Glass Identification. This database deals with classification of types of glass, based on chemical and physical tests. It includes 214 cases, with nine continuous attributes and one discrete attribute having seven distinct values. Using any kind of data cleaning by the data donors is not mentioned. Heart Disease. The dataset includes results of medical tests aimed at detecting a heart disease for 297 patients. There are seven ....

[Article contains additional citation context not shown here]

Wand, Y., & Wang, R.Y. (1996). Anchoring Data Quality Dimensions in Ontological Foundations. Communications of the ACM, 39, 11, 86-95.

.... dimensions concern only data values; instead, they do not deal with aspects concerning quality of logical schema and data format [35] The need for providing such definitions stems from the lack of a common reference set of dimensions in the data quality literature (see as disagreeing examples [46] and [35] 2.1 Data Quality Dimensions Data quality dimensions characterize properties that are inherent to data, i.e. depend on the very nature of data; as an example, a dimension specifying whether the data about a citizen are updated or not. In the following definitions, the general ....

....following definitions, the general concept of schema element is used, corresponding, for instance, to an entity in an Entity Relationship schema or to a class in a Unified Modeling Language diagram. The quality dimensions used in this work are those that are used most frequently in the literature [46], namely: i) syntactic and semantic accuracy, ii) completeness, iii) currency, and (iv) internal consistency. Syntactic and Semantic Accuracy In [35] accuracy refers to the proximity of a value v to a value v considered as correct. Based on such a definition, we introduce a further ....

Y. Wand and R.Y. Wang, Anchoring Data Quality Dimensions in Ontological Foundations, Commu- nications of the ACM 39 (1996), no. 11.

.... dimen sions concern only data values; instead, they do not deal with aspects concerning quality of logical schema and data format [23] The need for providing such definitions stems from the lack of a common reference set of dimensions in the data quality literature (see as disagreeing examples [42] and [23] 2.1 Data Quality Dimensions Data quality dimensions characterize properties that are inherent to data, i.e. depend on the very nature of data; as an example, a dimension specifying whether the data about a citizen are updated or not. In the following definitions, the general ....

....following definitions, the general concept of schema element is used, corresponding, for instance, to an entity in an Entity Relationship schema or to a class in a Unified Modeling Language diagram. The quality dimensions used in this work are those that are used most frequently in the literature [42], namely: i) syntactic and semantic accuracy, ii) completeness, iii) currency, and (iv) internal consistency. 2.1.1 Syntactic and Semantic Accuracy In [23] accuracy refers to the proximity of a value v to a value v considered as correct. Based on such a definition, we introduce a further ....

Y. Wand and R.Y. Wang, "Anchoring Data Quality Di- mensions in Ontological Foundations," Communications of the ACM, vol. 39, no. 11, 1996.

....dimensions characterize properties that are inherent to data, i.e. depend on the very nature of data; as an example, a dimension specifying whether the data about the citizen s family composition is updated or not. Though referring to a subset of the dimensions pro posed in the literature [44], we provide new definitions for them on the basis of the classical ones. The need of providing such definitions stems from the lack of a common reference set of dimensions in the data quality literature, as discussed in Section 6. We will refer only to data quality dimensions concerning data ....

....definitions, we refer to schema elements in general, corresponding, for instance, to an entity in a Entity Relationship schema or to a class in a Unified Modeling Language diagram. The quality dimensions we define in the following are those that are used most frequently in the literature [44], namely: i) syntactic and semantic accuracy, ii) completeness, iii) currency, and (iv) internal consistency. 3.1.1. yntactic and Semantic Accuracy In [32] accuracy refers to the proximity of a value v to a value v considered as correct. Based on such a definition, we introduce a further ....

Wand, Y. and R. Wang: 1996, 'Anchoring Data Quality Dimensions in Ontological Foundations'. Communications of the ACM 39(11).

....with data quality as a guiding principle and not as an afterthought [17] Poor data quality, that results from missing customer information, wrong address information, etc. undermines the customer satisfaction, leads to high and unnecessary costs and more importantly impacts decision making [21, 20, 16]. A number of reasons is responsible for bad data quality including: a) multiple sources of data, b) incompatible data, c) data from multiple level of granularity, d) redundant data, e) corrupted and noisy data, and (f) missing attribute values. Data quality is achieved in three stages: the ....

Y. Wand and R.Y Wang, Anchoring Data Quality Dimensions in Ontological Foundations, Communications of the ACM 39 (1996), no. 11, 86--95.

....approach. Our methodology is presented in detail in Section 3. The experiments we conducted on synthetic data and the results are presented in Section 4. Section 5 concludes our discussion and refers to our future plans. 4 2 Background and Related Work Estimating and or improving the quality [WW96, WSF95, WK93] of data stored in real life databases are difficult problems because of the data volume and the variety of ways errors might be introduced in a system (data entry errors, bad design) Consequently, heuristic ad hoc solutions are often sought to balance the computational load and the predictive ....

Y. Wand and R.Y. Wang. Anchoring data quality dimensions in ontological foundations. Communications of the ACM, 39(11):86--95, 1996. 20

....and replies on the basis of data quality information. Moreover, we also take into account improvement features (i.e. iii) that are not considered in [14] The data quality dimensions used in this work are recalled from [15, 9, 16] and are those that are used most frequently in the literature [17], namely: i) syntactic and (ii) semantic accuracy, iii) completeness, iv) currency, and (v) internal consistency. Such dimensions concern only data values; instead, they do not deal with aspects concerning quality of logical schema and data format. 3 The D2Q Model In the remain of this paper, ....

Y. Wand and R.Y. Wang, "Anchoring Data Quality Dimensions in Ontological Foundations," Communications of the ACM, vol. 39, no. 11, 1996.

....take into account improvement features (i.e. iii) that are not considered in [21] 1 UDDI.org: http: www.uddi. org. Data quality dimensions characterize properties that are inherent to data. The quality dimensions used in this work are those that are used most fre quently in the literature [28], namely: i) syntactic and semantic accuracy, ii) completeness, iii currency, iv internal consistency and (v source reliability. In the following we only recall the adopted dimensions; further details and examples can be found in [4, 5, 20] Such dimensions concern only data values; instead, ....

Y. Wand and R.Y. Wang, Anchoring Data Quality Dimensions in Ontological Foundations, Communications of the ACM 39 (1996), no. 11.

....of constructing process models. Each world is characterized by a set of facets, i.e. attributes describing the properties of a process belonging to it. Data Quality and Quality Management. There has been a lot of research on the definition and measurement of data quality dimensions [66,63,62,56]. A very good review of research literature is found in [65] 29] give an extensive list of quality dimensions for data warehouses, and in particular data warehouse relations and data. Several goal hierarchies of quality factors have been proposed for software quality. For example, the GE ....

Y. Wand, R.Y. Wang. Anchoring Data Quality Dimensions in Ontological Foundations. Communications of the ACM, 39(11): 86-95 (1996).

....overwhelming and mental integration with which humans are faced. Since the required fusion of the various models within one s mind is extremely difficult, our conjecture has been that it may adversely affect the two transformations involved in the development and use of information systems [1]: the representation of the real world system as a system specification and the comprehension (interpretation) of the system specification. Indeed, our empirical study, described in this research, supports this claim. We compared OPM T [2] OPM [3] with temporal extension) a graphic ....

Y. Wand and R.Y. Wang, "Anchoring Data Quality Dimensions in Ontological Foundations", Communications of the ACM, Vol. 39, No. 11, November 1996, pp. 86-95.

....Pragmatically, it suggests importing rewrite capabilities from a query processor; like all reuse, this introduces a dependency on the component that provides the capability in question. Many papers have been published about individual meta attributes (i.e. types of metadata) For example, [Wan96] gives a taxonomy of quality meta attributes, and [Kon96] gives ways to infer some result qualities. It is not our intention to compete in this arena. It appears that vendors have not implemented such techniques, because lacking a framework, the cost is too high and benefits too low. In [Ros99b] ....

Yair Wand and Richard Wang. "Anchoring Data Quality Dimensions in Ontological Foundations" Communications of the ACM (November 1996).

....but covers in detail the sequence of steps, the functions and mappings employed and the execution traces of data transformations in a data warehouse environment. As far as quality management is concerned, there has be much research on the definition and measurement of data quality dimensions [WW96,WKM93,WSG94,TB98]. A very good review of research literature is found in [WSF95] JJQV99, JLVV99] provide extensive reviews of methodologies employed for quality management, too (e.g. the GQM approach, introduced in [OB92] Vassiliadis, Quix, Vassiliou, Jarke. A Model for Data Warehouse Processes. Page 29 of ....

Y. Wand, R.Y. Wang. Anchoring Data Quality Dimensions in Ontological Foundations. Communications of the ACM, Vol. 39, No. 11, November 1996.

....affect them. The idea behind this is to enrich the meta data repository in order to ease the impact analysis of each evolution operator and its consequences on the quality factor measures. 5. Related Work There has ben much research on the definition and measurement of data quality dimensions [18,15,17,13]. A very good review is found in [16] The GQM methodology is best presented in [10,2] The TDQM methodology [14] follows the Total Quality Management approach, adapted for the evaluation of data quality in an information system (by assuming that each piece of produced information can be ....

Y. Wand, R.Y. Wang. Anchoring Data Quality Dimensions in Ontological Foundations. Communications of the ACM, Vol. 39, No. 11, November 1996.

....Caruana and Freitag [6] assume that there is an unlimited source of data to test the generalization performance of the learning algorithm. 1.2 Data Quality and Data Cleaning As indicated by Wang et al. 7] data reliability is one of data quality dimensions. Other data quality dimensions include [7 9]: accuracy, timeliness, relevance, completeness, consistency, precision, etc. Various definitions of these and other dimensions can be found in [8] An attribute based approach to data quality [8] is based on the entity relationship (ER) model (described in [10] According to [9] the reliability ....

....include [7 9] accuracy, timeliness, relevance, completeness, consistency, precision, etc. Various definitions of these and other dimensions can be found in [8] An attribute based approach to data quality [8] is based on the entity relationship (ER) model (described in [10] According to [9], the reliability indicates whether the data can be counted on to convey the right information . Unreliable (deficient) data represents an inconformity between the state of the information system and the state of the real world system. The paper [9] follows a Boolean approach to data ....

[Article contains additional citation context not shown here]

Wand Y, and Wang R Y 1996 Anchoring Data Quality Dimensions in Ontological Foundations. Comm ACM 39, 11: 86-95

....frozen into routine work. Unreliability is one aspect that shows the lack of quality, according to Landauer (1995) Furthermore, the quality of the system specifies the quality of data which the system contains. Data quality depends on the design and production processes which generate the data (Wand and Wang 1996). Frequently mentioned dimensions of data quality are accuracy, completeness, consistency, reliability, and timeliness. However, data quality is relative to the actual usage of data. Poor data quality has an influence on the efficiency of the whole organization (ibid. Therefore, problems in data ....

Wand, Y., and Wang, R. Y. "Anchoring Data Quality Dimensions in Ontological Foundations," Communications of the ACM (39:11), 1996, pp. 86-95.

No context found.

Wand, Y. and Wang, R.Y. (1996) Anchoring data quality dimensions in ontological foundations, Communications of the ACM, 39, 11, 86--95.

No context found.

Wand, Y. and R. Y. Wang, Anchoring Data Quality Dimensions in Ontological Foundations. Communications of the ACM, 39(11) 1996, pp. 86-95.

No context found.

Wand, Y. and Wang, R. Y. (1996), "Anchoring Data Quality Dimensions in Ontological Foundations," Communications of the ACM, 39(11), 86-95.

No context found.

Y. Wand and R. Y. Wang, "Anchoring Data Quality Dimensions in Ontological Foundations," Communications of the ACM, vol. 39, pp. 86-95, 1996.

No context found.

Wand, Y. and Wang, R.Y. Anchoring data quality dimensions in ontological foundations. Commun. ACM 39,11 (1996), 86--95.

....and use of data. DQ problems may arise anywhere in this larger IS context. Thus, we argue for a conceptualization of data quality that includes this context. Database research aims at ensuring the quality of data in databases. In the DQ area, existing research investigates DQ definitions [8, 11], modeling [1, 2] and control [6] With few exceptions, however, DQ is treated as an intrinsic concept, independent of the context in which data is produced and used. This focus on intrinsic DQ problems in stored data fails to solve complex organizational problems. We attribute this failure, in ....

Wand, Y. and Wang, R. Y. Anchoring data quality dimensions in ontological foundations. Commun. ACM 39, 11 (1996), pp.86--95.

No context found.

Y.Wand and R.Wang. Anchoring data quality dimensions in ontological foundations. Communications of the ACM, volume 39. ACM, 1996.

No context found.

Wand, Y., and Wang, R. Anchoring data quality dimensions in ontological foundations. Communications of the ACM, 39, 11 (1996), 86--95.

No context found.

Wand, Y., Wang, R., "Anchoring Data Quality Dimensions in Ontological Foundations", CACM Vol. 39, No. 11, Nov. 1996, pp. 8695.

No context found.

Y. Wand, and R.Y. Wang. Anchoring data quality dimensions ontological foundations. Communications of the ACM (CACM), vol. 39, no. 11, November 1996.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC