Limits...
Interactive graphics: exemplified with real data applications.

Malik WA, Unlü A - Front Psychol (2011)

Bottom Line: Graphics are widely used in modern applied statistics because they are easy to create, convenient to use, and they can present information effectively.Static plots do not allow interacting with graphics.The benefits and strengths of interactive graphics for data exploration and data quality analyses are illustrated systematically with three complex real datasets.

View Article: PubMed Central - PubMed

Affiliation: Department of Mathematics, University of Augsburg Augsburg, Germany.

ABSTRACT
Graphics are widely used in modern applied statistics because they are easy to create, convenient to use, and they can present information effectively. Static plots do not allow interacting with graphics. User interaction, on the other hand, is crucial in exploring data. It gives flexibility and control. One can experiment with the data and the displays. One can investigate the data from different perspectives to produce views that are easily interpretable and informative. In this paper, we try to explain interactive graphics and advocate their use as a practical tool. The benefits and strengths of interactive graphics for data exploration and data quality analyses are illustrated systematically with three complex real datasets.

No MeSH data available.


A small group is selected in Mag variable. It shows an outlier with low potassium, thorium, and uranium values.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3111423&req=5

Figure 12: A small group is selected in Mag variable. It shows an outlier with low potassium, thorium, and uranium values.

Mentions: A parallel coordinate plot (PCP) (Wegman, 1990; Inselberg, 1985, 1998) of all variables in the out5d dataset in Figure 11 shows the structure of relations between variables. α-blending has been used to make the distributional structure more visible. Common scaling has been used as the variables look as if they have been initially standardized. From this we can see additionally that variables SPOT and Mag are negatively correlated. Outliers can be sometimes identified with a parallel coordinate plot. In Figure 11, brushing has been used on the variable SPOT and unusual magnetics and potassium values have been found. Observations which are outliers in more than one variable can be identified in PCP. Brushing the variable Mag led to Figure 12 where a case which is outlying on three variables has been found.


Interactive graphics: exemplified with real data applications.

Malik WA, Unlü A - Front Psychol (2011)

A small group is selected in Mag variable. It shows an outlier with low potassium, thorium, and uranium values.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3111423&req=5

Figure 12: A small group is selected in Mag variable. It shows an outlier with low potassium, thorium, and uranium values.
Mentions: A parallel coordinate plot (PCP) (Wegman, 1990; Inselberg, 1985, 1998) of all variables in the out5d dataset in Figure 11 shows the structure of relations between variables. α-blending has been used to make the distributional structure more visible. Common scaling has been used as the variables look as if they have been initially standardized. From this we can see additionally that variables SPOT and Mag are negatively correlated. Outliers can be sometimes identified with a parallel coordinate plot. In Figure 11, brushing has been used on the variable SPOT and unusual magnetics and potassium values have been found. Observations which are outliers in more than one variable can be identified in PCP. Brushing the variable Mag led to Figure 12 where a case which is outlying on three variables has been found.

Bottom Line: Graphics are widely used in modern applied statistics because they are easy to create, convenient to use, and they can present information effectively.Static plots do not allow interacting with graphics.The benefits and strengths of interactive graphics for data exploration and data quality analyses are illustrated systematically with three complex real datasets.

View Article: PubMed Central - PubMed

Affiliation: Department of Mathematics, University of Augsburg Augsburg, Germany.

ABSTRACT
Graphics are widely used in modern applied statistics because they are easy to create, convenient to use, and they can present information effectively. Static plots do not allow interacting with graphics. User interaction, on the other hand, is crucial in exploring data. It gives flexibility and control. One can experiment with the data and the displays. One can investigate the data from different perspectives to produce views that are easily interpretable and informative. In this paper, we try to explain interactive graphics and advocate their use as a practical tool. The benefits and strengths of interactive graphics for data exploration and data quality analyses are illustrated systematically with three complex real datasets.

No MeSH data available.