Summary
The extent to which the accounts of companies are comparable is considered important to users and regulators. However, prior research has been restricted by a lack of appropriate statistical methods for testing comparability indices. This has made it difficult to assess the true level of comparability from sample data and to test research hypotheses such as whether the level of comparability (a) differs by policy, (b) differs by country, and (c) changes over time. This paper fills this gap by exploring the statistical properties of the T index. The T index generalises the H, C, I and various modifications of these indices and represents a unified framework for the measurement of the extent to which the accounts of companies are comparable. Formulae for the bias and standard error for any index under this framework are provided and proved. The bias is shown to equal zero or be negligible in most practical situations. Using historical data, the standard error is used to illustrate the accuracy with which comparability is estimated and to perform formal statistical inference using confidence intervals and p-values. Furthermore, the sampling distribution of the T index is assessed for normality. Implications for research design and sample size determination are also discussed.
See the full content of this document
Extract
Statistical Inference Using the T Index to Quantify the Level of Comparability Between Accounts
(ProQuest: ... denotes formulae omitted.)
1 IntroductionThe T index was introduced by Taplin (2004) to quantify the degree to which the accounts of companies are comparable. It is easily interpreted as the probability that two randomly selected companies have accounts that are comparable, or as the average comparability of pairs of companies. The T index is a generalisation of the H, I and C indices introduced by van der Tas (1988), and is a framework containing countless individual indices. Many authors have made minor modifications to the basic H, I and C indices to deal with issues such as non-disclosure of the accounting method by a company and many of these are also special cases of the unified approach described by the T index. For details of the history of these indices, references to these modifications, literature using these indices, and literature that considers alternative definitions of harmony or related ideas of harmonisation, uniformity and standardisation, the reader is referred to Taplin (2004), the literature review Ali (2005), or Cole et al. (2008), as well as the references contained within these articles.This paper uses the term 'comparability' in place of the more traditional term 'harmony' used in Taplin (2004) and by papers going back to van der Tas (1988). This is to avoid confusion over terms harmonisation, standardisation and uniformity that potentially have different meanings and positive or negative connotations to different readers (Tay and Parker, 1990). Cole et al. (2008) summarise the changing landscape concerning different perspectives on these terms and on the uniformity-flexibility dilemma when it comes to the extent to which all companies should be forced to use the same method on one extreme, or allowed to use any method they choose on the other extreme. Barth et al. (1999) use a mathematical model to investigate, under several assumptions, the impact of changes such as harmonising domestic regulations in two countries on characteristics such as security market performance. They conclude from their theoretical model that harmonisation is not necessarily desirable.This paper is concerned with the measurement of the extent to which the actual accounts of companies are comparable. This is important regardless of philosophical perspectives or opinions concerning the uniformity-flexibility continuum and regardless of current regulations because there will always be an interest in knowing the extent to which the accounts prepared by companies are comparable. Comparability is important in concepts such as harmonisation, standardisation and uniformity but this paper makes no statement about the preferred position on the uniformity-flexibility continuum. This paper specifically concerns statistical sampling issues when measuring the extent to which company accounts are comparable.The T index is flexible concerning what it means for the accounts of two companies to be comparable. For example, two companies both using FIFO would normally be considered comparable. Companies not disclosing their method, using a combination of methods (FIFO for some inventory and average cost for other inventory) or using multiple methods (results usi...See the full content of this document
Sponsored links
