The XBRL filings of SEC companies provides insight into why an information model is important. Consider this one presentation linkbase from the US GAAP Taxonomy: Statement of Income. If you click on that link and look at the page, you will notice that the presentation network of the income statement starts off something like this:
Income Statement [Abstract] {ID1}
Statement [Table] {ID2}
Statement, Scenario [Axis] {ID3}
Statement [Line Items] {ID5}
You can click on the page and get to that presentation arrangement by collapsing or expanding the line items of that network. The IDs on the right just help you see which nodes I want you to focus on.
Why is the income statement organized in this manner, as a [Table]? Well, there are two primary reasons reasons. The first reason is that an income statement have a number of dimensions, for example it could be actual or budgeted, it could be for a consolidated group or for a subsidiary, or there are other breakdowns or "dimensions" which could be provided. Those dimensions can be expressed using the "Statement, Scenario [Axis]" and the facts for which values are expressed are provided within the "Statement [Line Items]". The second reason this [Table] is organized in this manner is because the US GAAP Taxonomy Architecture says that all [Table]s are to be organized in this manner (see the US GAAP Taxonomy Architecture, section 4.5 Implementation of Tables, page 34).
In fact, it is not that just this one [Table] is organized in this manner, ALL [Table]s in the US GAAP Taxonomy are organized in this manner.
However, look at the following sample of XBRL filings to the SEC:
http://www.xbrlsite.com/demos/console/TreeView-0001047469-09-007400.html#ID1([Table], [Axis], and [Line Items] used just like US GAAP Taxonomy)
http://www.xbrlsite.com/demos/console/TreeView-0000950123-09-030335.html#ID505 ([Table], [Axis], and [Line Items] used just like US GAAP Taxonomy)
http://www.xbrlsite.com/demos/console/TreeView-0000950123-09-029921.html(Table on balance sheet just like US GAAP Taxonomy, but no Axis on the income statement)
http://www.xbrlsite.com/demos/console/TreeView-0001104659-09-046329.html#ID1 (No table, no axis, no line items)
http://www.xbrlsite.com/demos/console/TreeView-0001104659-09-048234.html#ID50 (No table, no axis, does have line items, but not modeled using [Line Items] marker)
http://www.xbrlsite.com/demos/console/TreeView-0001310243-09-000085.html#ID1 (Table, line items, but no axis)
http://www.xbrlsite.com/demos/console/TreeView-0000004904-09-000117.html#ID1 (No table at all)
http://www.xbrlsite.com/demos/console/TreeView-0001104659-09-047977.html#ID1 (Line items, but no table or axis)
http://www.xbrlsite.com/demos/console/TreeView-0001104659-09-046313.html (No table, no axis, no line items)
http://www.xbrlsite.com/demos/console/TreeView-0000037748-09-000037.html (Table and line items, but no axis)
Why the inconsistency between the filings? Why the inconsistency between the filings and the US GAAP Taxonomy? The reason is that no "model" is being enforced as to how, in this case SEC filers, create their extension taxonomies. There is no "information model" or manner specified to construct this component of the XBRL taxonomy and no automated validation to ensure that the model is being followed.
An articulated information model achieves many things, not just consistency within an XBRL taxonomy or between a base XBRL taxonomy such as the US GAAP Taxonomy and those who extend that taxonomy.
The third benefit about is by far the most important, but it is only achieved if you also have the first two: the consistency of an articulated information model. This points out another challenge working with the US GAAP Taxonomy: when is something a [Table]? This problem can be easily overcome by doing what the creators of the COREP taxonomy did: make EVERYTHING a [Table]. Now, the COREP taxonomy does not call them [Table]s, they use the XBRL term hypercube. But, everything within the COREP taxonomy is constructed in one very easly to explain and leverage information model.
The bottom line here is this. If you articulate an information model, meaning a formal set of rules as to how that taxonomy is to be constructed, then those rules can be used to ensure that your taxonomy was created consistently and to ensure that those extending your taxonomy do so consistently. The consistency can be taken even further making using the taxonomy significantly easier if every area of the taxonomy is created in the same manner, in this case we are using [Table]s but actually [Table]s are a way to implement the multidimensional model. If, say, every component of the taxonomy works in a similar manner, that similarity can be leveraged by software creators to make the experience of using that taxonomy easier, significantly easier in many cases.
There are a number of other entries on this blog which discuss the notion of an information model. Also, you can read more about this in my book which will be available next month, XBRL for Dummies.