A Practical Hands-on Approach to Conducting Quantitative Analysis

This session will introduce the reader to the principles of information flow within organizations as well as data analytic methodologies and terminology.
The focus will be on developing an understanding of where critical data exists for analysis, the obtaining of access and the selection of the appropriate analytical techniques.

This session will cover the fundamental assumptions underlying the use of sampling techniques, the nature of populations and the use of variables. Distribution frequencies and central tendency measurement will be covered as well as the impact on analysis of distribution characteristics. It will also examine the differences between judgmental and statistical sampling, the applicability of both in audit practice, and the dangers inherent in confusing the two. The differences in selection methods will be covered as well as their impact on the analysis and interpretation possible within the sampling methods.

This session will examine the various types of evidence available to the auditor in order to evaluate both the adequacy and effectiveness of the system of internal controls. This will include the identification of population types and the division into sub-populations for analytic purposes. Differing collection types and evidence sources will also be identified.

This session will examine the differences between a given set of data in the standard benchmark in terms of central tendency, variation and shape of curve. In addition we will examine the fundamental principles of Baysian probability theory. In general, this is a methodology used to trying to clarify the relationship between theory and evidence. It attempts to demonstrate how the probability that the theory is true is affected by a new piece of evidence. This can be critical to auditors in drawing conclusions about large populations based upon small samples drawn.

This session will examine the differences between correlations and regressions as well as the auditor's usage of both. It will focus on determination of the type of situation in which correlations and linear regressions may be deemed appropriate.

This session will examine how audit objectives are determined and how data analytics are selected in order to achieve those objectives. This will include the use of the appropriate risk analysis techniques in order to identify potential internal control failures. It will also cover the definition of “exception” conditions.

This session will cover the assessment of IT systems in order to determine the sources of evidentiary data appropriate for analysis as well as the techniques the auditor may use in order to obtain, extract and, if necessary, transform such data to facilitate analysis.

This session will examine typical CAATs in common use in the selection of the appropriate technique based upon the type of evidence and the audit objective. Included will be the dangers to the auditor inherent in pre-judgment of expected results and the subsequent distortion of the analysis based upon these pre-conceptions. It will also examine the audit methodologies for the analysis of Big data. Big data is a term given to large datasets containing a variety of data types. Big data analysis allows the auditor to seek for hidden patterns and identify concealed correlations, market trends and other data inter-relationships which can indicate areas for improved operational efficiencies within business processes.

This session will examine the techniques available to the auditor in order to identify the red flags and indicators that fraud may be occurring or may have occurred in the past as well as the obtaining of forensically acceptable data analytical evidence.