Looking at Characteristics Used to Describe Balance Sheet Facts in SEC XBRL Financial Filings
Monday, February 18, 2013 at 02:41PM
Charlie in Modeling Business Information Using XBRL

Until now I have been focused my analysis of SEC XBRL financial filings on concept usage. I am now expanding that to have a closer look at how filers use [Axis] within SEC XBRL financial filings to express characteristics used to describe reported facts. For this blog post I am focusing on balance sheets.

This is a list of 82 SEC filers who each provide balance sheets. Now, because XBRL requires an entity, a period, and a concept; every filer has to provide at least these 3 characteristics.  The range of characteristics goes from 3 to 7.  Why?

First off, let me quickly explain the terminology which I am using.  (All my terms are defined on the Financial Report Ontology wiki.)

So why the variation between what characteristics SEC XBRL filers report? Well, let's have a look.

As I said three characteristics are required: Entity, period, and concept.  XBRL requires this.  Entity, or more appropriately reporting entity or the CIK number of the filer is used on 82 out of 82 SEC XBRL financial filings.  Period or again more precisely calendar period is likewise used on all 82 filings I looked at. The concept is also required and used by all 82 filers for all reported facts. So, all 82 filings consistently use those characteristics on every balance sheet fact.

Focus on that statement for a moment, "every balance sheet fact." That is important to understand. Characteristics defined relate to every fact within that component.

A popular characteristic is "Legal Entity [Axis]", it is used by 20 of the 82 SEC filings I looked at?  why only 20, why not all 82? What is the legal entity of the other 62 reporting entities?  What does this mean, that the others don't have a legal entity?  No.  If a legal entity axis is not provided, then the legal entity of "consolidated entity" is assumed per SEC XBRL filing rules in the EFM. So whether you do, or do not, provide the legal entity [Axis], users of the information will either explicitly or implicitly understand which legal entity a filer is talking about.

Another popular [Axis] is the "Class of stock [Axis]" (us-gaap:StatementClassOfStockAxis). Of the 82, a total of 13 used that [Axis]. Remember what I said about the characteristic expressed by the [Axis] for a component (i.e. within a [Table]) being applicable for all the facts within that component/[Table]?  Well, in my view the way the class of stock [Axis] is being used is a mistake.  Cash and cash equivalents, total assets, long-term debt, and other stuff found on those balance sheets should not be characterized by the class of stock [Axis].  A breakdown of the details of some category of stock using this axis, sure.  But not the entire balance sheet.  This is a modeling mistake. Chrysler, which has capital units, did a similar thing as those who modeled class of stock, they just used Capital Units [Axis] (us-gaap:CapitalUnitsByClassAxis).

The next most popular [Axis] is the "Reporting Scenario [Axis]" (us-gaap:StatementScenarioAxis).  11 filers used this [Axis]. Interestingly, of the 11; all 11 used the member of the [Axis] (or the value of the characteristic) "scenario unspecified".  What is the reporting scenario which should be assumed per SEC EFM filing rules?  Nothing is said.  In my view, using this [Axis] is a modeling mistake.  It helps nothing.

Three filers used the "Variable Interest Entities, by Classification of Entity [Axis]" (us-gaap:VariableInterestEntitiesByClassificationOfEntityAxis).  This seems reasonable, however the name of the [Axis] is not reasonable.  The phrase "...by Classification of Entity..." is not necessary in the name of the [Axis].  That explains what the [Axis] does, not what the [Axis] is.  "Variable interest entity [Axis]" would be more appropriate in my view.  This is a common issue on [Axis] within the US GAAP Taxonomy.  But the [Axis] itself does seem reasonable.  What is assumed if it does not appear?  No variable interest entities exist which need to be reported. Comparability should be fine.

One filer, American Express, created an extension to define the axis "Error Correction And Prior Period Adjustments Restatement By Restatement Period And Amount [Axis]".  This is an error in my view.  First, for something as common as a restatement, no one should need to create an extension concept.  Second, the "thing that moves" in a restatement is the report date.  Therefore, the report date [Axis] is what should have been used.  The "Report Date [Axis]" already exists in the US GAAP Taxonomy. In my view, this is a modeling mistake.

Berkschire Hathaway created an extension axis "Financial Segments [Axis]" but does not define what a financial segment is as compared to a Business Segment [Axis], which does exist in the US GAAP Taxonomy. Not sure what to think about that.  I can sort of see the rational.  The information is comparable and properly modeled.  So I guess I would see no problem with this. But hold on a minute; in the business segment disclosure, they also used that same extension axis.  Nope, this is a modeling error.  Should have used the existing business segment axis.

Ford created an extension axis "Business Sectors [Axis]".  This seems to be the same deal as the extension created above.  Looking at the disclosures, business segment breakdown...Ford uses the same extension axis.  Yeah...no; this is a modeling error.  No need for that extension axis.  Besides, if you look at the balance sheet in the HTML document and compare that to the XBRL, I am not sure what the creators of this balance sheet were thinking.  I would avoid using the Ford balance sheet as an example.

Again, have a look of the 82 SEC filers which I took a look at for yourself.  I am going to do a more comprehensive analysis of [Axis] for the balance sheet and other components after all the 10Ks get filed.

The bottom line for me is that the SEC filers have a lot of adjustments which need to be made with their [Axis] use.  Use of the information by analysts is really the ultimate test.  As long as more information is provided and as long as how the [Axis] are used do not hinder analysis; then I think more detail really does not hurt anything.  But, using existing [Axis] is far better than creating extension report elements.

Article originally appeared on Intelligent XBRL-based structured digital financial reporting using US GAAP and IFRS (http://xbrl.squarespace.com/).
See website for complete article licensing information.