The data module of VISO describes characteristics of data, as far as needed for visualization
purposes.
Classes
Characteristic^{c}▲
http://purl.org/viso/data/Characteristic
 has superclasses

Continuous Variable^{c}▲
http://purl.org/viso/data/Continuous_Variable
 has superclasses

Data^{c}▲
http://purl.org/viso/data/Data

»###Data Type###
«
Card
Stuart K
,
"Information visualization",
1997
,p. 519, 530

»###Data Type###«
Ben
Schneiderman
,
"The eyes have it",
1996

»###Data Type###«
Colin
Ware
,
"Information visualization",
20040407
,p. 23

»Regularities (geometric and/or topological) have long been used to structure and organize
data, and these all underpin fundamental disinctions, e.g. between structured and
unstructured grids. Several taxonomies of data and its organization have been been
developed, in particular work by Butler, Pendley, and Bergeron and Kao; other approaches
are also notable, for example the lattice model of Hibbard et.al. is significant in
addressing error and uncertainty.
A classification scheme for data proposed by Brodlie emphasises the importance of
the underlying field, i.e. the phenomenon that is captured within the data. Building
on this, Tory and Möller have developed a visualization taxonomy based on data models
rather than data. These two groups of taxonomies (e.g. Bergeron and Kao, and Brodlie),
are complimentary; the former concentrate on how data is structured, while the latter
the link between data and representation. A synthesis of these two contributions should
help to develop the ‘data’ branch of the toplevel ontology.«
,p. 2
, Sect. 3.3 Data Models

[General note on the topic, no concrete quotation given]
Bertin
Jacques
,
"Semiology of Graphics",
1983
Bertin
Jacques
,
"Graphics and Graphic Information Processing",
198112

»###Type of Information###
Type of information that is expressed by different spatial structures. See section
3.4 for a very brief discussion of types of information.«
Engelhardt
J?rg von
,
"The language of graphics",
2002
,p. 70
, Sect. FIGURE 235

»###Domain Set###
Each domain set can be one of the following three types [...]: A domain set is nominal
when it is a collection of unordered items, such as {Jay, Eagle, Robin). A domain
set is ordinal when it is an ordered tuple, such as (Monday, Tuesday, Wednesday).
A domain set is quantitative when it is a range, such as [ 0, 273].«
Jock D.
Mackinlay
,
"Automating the design of graphical presentations of relational information",
April 1986
,p. 116
 has superclasses

 has subclasses
 Meta Data^{c}, Nominal Data^{c}, OneDimensional Data^{c}, Ordinal Data^{c}, Physical Data^{c}, Quantitative Data^{c}, Raw Data^{c}, Structured Data^{c}, Unstructured Data^{c}
Data Object^{c}▲
http://purl.org/viso/data/Data_Object
 has superclasses

Data Schema^{c}▲
http://purl.org/viso/data/Data_Schema
Prescribes a data structure. Data schema is similar to data structure, however a data
structure may exist without a schema that prescribes it.
 has superclasses

Data Variable^{c}▲
http://purl.org/viso/data/Data_Variable
In contrast to a relation that may exist also without measuring something, a data
variable stands for a variable in a measurement.
 has superclasses

Dependent Variable^{c}▲
http://purl.org/viso/data/Dependent_Variable
 has superclasses

Dimension^{c}▲
http://purl.org/viso/data/Dimension

»###Related Referer and Attributes###
*Similar: dependent and independent dimensions«
Andrienko
Gennady
Natalia
,
"Exploratory analysis of spatial and temporal data",
2006

»###Attribute###«
M?ller
Torsten
Melanie
Tory
,
"Rethinking Visualization",
2004
Daniel A.
Keim
,
"Information Visualization and Visual Data Mining",
2002
Bertin
Jacques
,
"Graphics and Graphic Information Processing",
198112
Mazza
Riccardo
,
"Introduction to Information Visualization",
2009

[General note on the topic, no concrete quotation given]
Bertin
Jacques
,
"Semiology of Graphics",
1983
Bertin
Jacques
,
"Graphics and Graphic Information Processing",
198112

»###Attribute###
attributes or variables«
Card
Stuart K
,
"Information visualization",
1997
,p. 518
 has superclasses

Directed Acyclic Graph (DAG)^{c}▲
http://purl.org/viso/data/DAG
 has superclasses

 has subclasses
 Tree^{c}
Discrete Variable^{c}▲
http://purl.org/viso/data/Discrete_Variable
 has superclasses

Domain^{c}▲
http://purl.org/viso/data/Domain
A topic area of real life.
 has superclasses

Geographical Data^{c}▲
http://purl.org/viso/data/Geographical_Data
 has superclasses

 is disjoint with

Independent Variable^{c}▲
http://purl.org/viso/data/Independent_Variable
 has superclasses

Interval Scale of Measurement^{c}▲
http://purl.org/viso/data/Interval_Scale_of_Measurement

»Interval (can do subtraction on values, but no natural zero and can't compute ratios).
Example: 10. Dec. 19784 Jun. 1982«
Card
Stuart K
,
"Information visualization",
1997
,p. 521

»With the interval scale we come to a form that is "quantitative" in the ordinary sense
of the word. Almost all the usual statistical measures are applicable here, unless
they are the kinds that imply a knowledge of a 'true' zero point. The zero point on
an interval scale is a matter of convention or convenience, as is shown by the fact
that the scale form remains invariant when a constant is added.«
S. S.
Stevens
,
"On the Theory of Scales of Measurement",
1946
,p. 679
 has superclasses

Linked Data Structure^{c}▲
http://purl.org/viso/data/Linked_Data_Structure
We distinguish linked data structures from other structures such as tabular structures.
 has superclasses

 has subclasses
 Graph^{c}
List^{c}▲
http://purl.org/viso/data/List
 has superclasses

Meta Data^{c}▲
http://purl.org/viso/data/Meta_Data
 has superclasses

 is disjoint with

Multidimensional Data^{c}▲
http://purl.org/viso/data/Multidimensional_Data
There could be a propertyrestriction on has_dimensionality_of_independent_variables,
however restricting datatype ranges is not yet possible.
 has superclasses

 is disjoint with

Multivariate Data^{c}▲
http://purl.org/viso/data/Multivariate_Data
There could be a propertyrestriction on has_dimensionality_of_dependent_variables,
however restricting datatype ranges is not yet possible.
 has superclasses

 is disjoint with

Nominal Data^{c}▲
http://purl.org/viso/data/Nominal_Data
 has superclasses

Nominal Scale of Measurement^{c}▲
http://purl.org/viso/data/Nominal_Scale_of_Measurement
 has superclasses

OneDimensional Data^{c}▲
http://purl.org/viso/data/OneDimensional_Data
 has superclasses

Ordinal Data^{c}▲
http://purl.org/viso/data/Ordinal_Data
 has superclasses

Ordinal Scale of Measurement^{c}▲
http://purl.org/viso/data/Ordinal_Scale_of_Measurement
 has superclasses

Polyarchy^{c}▲
http://purl.org/viso/data/Polyarchy
 has superclasses

Quantitative Data^{c}▲
http://purl.org/viso/data/Quantitative_Data
 has superclasses

Ratio Scale of Measurement^{c}▲
http://purl.org/viso/data/Ratio_Scale_of_Measurement

»Ratio scales are those most commonly encountered in physics and are possible only
when there exist operations for determining all four relations: equality, rankorder,
equality of intervals, and equality of ratios. Once such a scale is erected, its numerical
values can be transformed (as from inches to feet) only by multiplying each value
by a constant. An absolute zero is always implied, even though the zero value on some
scales (e.g. Absolute Temperature) may never be produced. All types of statistical
measures are applicable to ratio scales, and only with these scales may we properly
indulge in logarithmic transformations such as are involved in the use of decibels.
Foremost among the ratio scales is the scale of number itselfcardinal numberthe
scale we use when we count such things as eggs, pennies, and apples. This scale of
the numerosity of aggregates is so basic and so common that it is ordinarily not even
mentioned in discussions of measurement.«
S. S.
Stevens
,
"On the Theory of Scales of Measurement",
1946
,p. 679
 has superclasses

Raw Data^{c}▲
http://purl.org/viso/data/Raw_Data
 has superclasses

Reference^{c}▲
http://purl.org/viso/data/Reference
 has superclasses

Relation^{c}▲
http://purl.org/viso/data/Relation
 has superclasses

Scale of Measurement^{c}▲
http://purl.org/viso/data/Scale_of_Measurement

»Variables imply a scale of measurement, and it is important to
keep these straight. The most important to distinguish are
N= Nominal (are only = or # to other values)
O = Ordinal(obeys a < relation)
Q = Quantitative (can do arithmetic on them)
A nominal variable N is an unordered set, such as film titles {Goldfinger, Ben Hur,
Star Wars}. An ordinal variable 0 is a tuple (ordered set), such as film ratings (G,
PG, PG13, R). A quantitative variable Q is a numeric range, such as film length
[O,360].
In addition to the three basic types of variables, subtypes represent important properties
of the world associated with specialized visual conventions. We sometimes distinguish
the subtype QuantitativeSpatial(Qg) for intrinsically spatial variables common in
scientificvisualization and the subtype Quantitative Geographical (Qp) for spatial
variables that are specifically geophysical coordinates. Other important subtypes
are similarity metrics Quantitative Similarity (Q,,), and the temporal variablesQuantitative
Time (Q) and Ordinal Time (0,) We can also distinguish Interval Scales (I) (like Quantitative
Scales, but since there is not a natural zero point, it is not meaningful to take
ratios). An example would be dates. It is meaningful to subtract two dates (June 5,
2002  June 3, 2002 = 2 days), but it does not make sense to divide them (June 5,2002
+ June 23, 2002 = Undefined). Finally, we can define an Unstructured Scale (4, whose
only value is present or absent (e.g., an error flag).«
Card
Stuart K
,
"Information visualization",
1997
,p. 520

»We can distinguish the same types of nodes and links in network Visual Structures
that we did for spatial axes: (a) Unstructured (unlabeled), (b) Nominal (labeled),
(c) Ordinal (labeled with an ordinal quantity), or (d) Quantitative (weighted links).«
Card
Stuart K
,
"Information visualization",
1997
,p. 530
 has superclasses

 has subclasses
 Nominal Scale of Measurement^{c}, Ordinal Scale of Measurement^{c}, Quantitative Scale of Measurement^{c}
Spatial Data^{c}▲
http://purl.org/viso/data/Spatial_Data
 has superclasses

 has subclasses
 Geographical Data^{c}
Tabular Data Structure^{c}▲
http://purl.org/viso/data/Tabular_Data_Structure
 has superclasses

Temporal Data^{c}▲
http://purl.org/viso/data/Temporal_Data
 has superclasses

Tree^{c}▲
http://purl.org/viso/data/Tree
 has superclasses

 has subclasses
 List^{c}
Triples^{c}▲
http://purl.org/viso/data/Triples
Subject, Predicat, Object Structures such as RDF.
 has superclasses

Unstructured Data^{c}▲
http://purl.org/viso/data/Unstructured_Data

»###No information###«
Engelhardt
J?rg von
,
"The language of graphics",
2002
,p. 70
 has superclasses

Value Role^{c}▲
http://purl.org/viso/data/Value_Role
 has superclasses

 has subclasses
 Characteristic^{c}, Reference^{c}
Data Properties
has fractional value^{dp}▲
http://purl.org/viso/data/has_fractional_value
Assigns a ratio value between 0 and 1.
has interval value^{dp}▲
http://purl.org/viso/data/has_interval_value
Assigns an interval value.
has numeral value^{dp}▲
http://purl.org/viso/data/has_numeral_value
Example Assign "1" to "small", "2" to "medium" and "3" to big. This creates an ordinal scale.
By using subproperties, it can be further defined, if even more than an ordinal scale
applies (interval, ratio).
has ordinal value^{dp}▲
http://purl.org/viso/data/has_ordinal_value
Assigns an ordinal value.
Alternatively to the definition of a new order relation between ObjectProperty values
and connecting them by this means, a numeral value can be attached, which is able
to provide the ordinal information and additionally also quantitative (interval, ratio)
information.
has quantitative value^{dp}▲
http://purl.org/viso/data/has_quantitative_value
has ratio value^{dp}▲
http://purl.org/viso/data/has_ratio_value
heterogeneous^{dp}▲
http://purl.org/viso/data/heterogeneous
Heterogeneous means that various data structures and distributed sources may exist.
The opposite is homegeneous.
planar^{dp}▲
http://purl.org/viso/data/planar
sparse^{dp}▲
http://purl.org/viso/data/sparse
A data set is sparse with respect to a type of relation if only a few items take part
in relationships of that type. A data set could be called sparse in general when this
is true for many of its relation types.
weighted^{dp}▲
http://purl.org/viso/data/is_weighted
Work on this project received financial support from the European Union and the
Free State of Saxony.
This HTML document was obtained by processing the OWL ontology source code through LODE, Live OWL Documentation Environment, developed by Silvio Peroni.