Risk Based Audit Approach Session 5.1 Statistical Sampling Session Overview Sampling is an important technique since it enables the auditor to select some transactions out of a large mass of repetitive data in a manner that he can draw valid conclusions about the entire data after a thorough examination of the selected transactions. Statistical sampling may be used in different auditing situations. The auditor may wish to estimate how many departures have occurred from the prescribed procedures; or estimate a quantity, e.g., the value (amount) of errors in the population. Based on whether the audit objective is to determine a qualitative characteristic or a quantitative estimate of the population, the sampling is called an attribute or variable sampling. Attributes sampling estimates the proportion of items in a population having a certain attribute or characteristic. In an audit situation, attribute sampling would estimate the existence or otherwise of an error. Attribute sampling would be used when drawing assurance that prescribed Note 5.1 RTI, JAIPUR procedures are being followed properly. For example, attribute sampling may be used to derive assurance that procedures for classification of vouchers have been followed properly. Here, the auditor estimates through attribute sampling the percentage of error (vouchers that have been miss-classified) and sets an upper limit of error that he is willing to accept and still be assured that the systems are in place. Variables sampling estimates a quantity, e.g., amount of sundry debtors shown in the balance sheet or the underassessment in a tax circle. Variables sampling has certain drawbacks which can be overcome through monetary unit sampling, which is an attribute sampling which provides quantitative results and is suited to most audit situations. Learning Objectives In this session we will understand the rationale of statistical sampling, Sampling methods, determining sample size, selecting a sample and projecting of results. 1 Risk Based Audit Approach Session 5.1 At the end of this session, you will be able to understand rationale of audit sampling, Elementary concepts and approach to statistical sampling Basic Concepts AUDIT SAMPLING Audit sampling is the application of an audit procedure to less than 100 per cent of the items within a class of transactions or an account balance to enable the auditor to form certain conclusions about that class or balance as a whole. An auditor can apply sampling in carrying out both compliance procedures (to evaluate the effectiveness of the internal control system) and substantive procedures (to obtain evidence regarding the completeness, accuracy and validity of the data). ELEMENTS OF STATISTICAL SAMPLING The theory of statistical sampling is used in a large number of situations where a Note 5.1 RTI, JAIPUR characteristic of a large mass of data is to be evaluated. In auditing, the auditor has to form his opinion about a large mass of data. Therefore, it is possible to apply statistical sampling techniques in auditing. Actually, the application of statistical sampling in auditing is merely an improvement over test checking or judgmental sampling which has traditionally been an important tool of auditing. Elementary Concepts of Statistical Sampling The statistical sampling theory basically states that if a sample is selected at random from a given population and examined properly, a valid conclusion can be drawn about the characteristics of the entire population. In this context, let us understand the precise meaning of terms like 'sample', 'population', 'random sample', etc., which we shall use frequently in our discussion on statistical sampling. Sample: A sample is the part of an aggregate selected with a view to drawing inferences about the aggregate. Thus, if out of 6,000 debtor accounts, an auditor selects, say, 349 debtor accounts (or any number lower than 6,000) for 2 Risk Based Audit Approach Session 5.1 obtaining confirmations, it can be said that he is sampling the debtor accounts. The debtor accounts selected by the auditor constitute the sample. Population: The aggregate or the totality from which the sample is drawn is called the population or the universe. A population or universe may consist of a definite number of elements (finite universe) or may contain a limitless number of elements (infinite universe). In our example, 6,000 debtor accounts constitute the population. Stratification: For sampling to be effective, population should be more or less homogenous. In auditing situations (as in many other cases), population can seldom be homogenous in all respects. For example, in a business enterprise, some of the items of raw materials or components may cost more than Rs. 10,000 per unit (e.g., a high capacity hard disk of a computer) whereas others may cost less than Rs 100 per unit (e.g., connecting cables in a computer). Similarly, the sundry debtors in an organisation may include some debts, which are outstanding only for a day or a week or a month whereas some others may be outstanding for more than, say, Note 5.1 RTI, JAIPUR three years. To make sampling more efficient, the total population in such a situation is divided into several subpopulations (each sub-population is called 'stratum') each of which is, in itself, more homogenous in nature, size, importance or other characteristics than the population as a whole. A sample is then selected out of each stratum. This process is called 'stratification'. Random Sample: A random sample is one where the elements constituting the sample are so selected that all the items in the population have an equal chance of selection. There are various ways of selecting a random sample. The basic hypotheses of statistical sampling theory are: (a) The population is a homogeneous group. (b) There is no bias in the selection of items of the sample. All items of the population have equal chance of being selected in the sample. 3 Risk Based Audit Approach Session 5.1 Approach to Statistical Sampling Statistical Sampling Auditing Situations in Various An auditor in carrying out both the compliance procedures as well as the substantive procedures can use statistical sampling, like test checking. Estimating the Qualitative Characteristics of a Population As we known that through compliance procedures, the auditor obtains evidence about the effectiveness of the operation of the internal controls. The auditor recognizes that even where some deviations from prescribed controls have taken place, he can place a certain degree of reliance on internal controls. If, however, the rate of deviations from prescribed controls is higher, he has to reduce the extent of reliance on internal controls, thus, in carrying out the compliance procedures, the auditor’s objective is to ascertain the rate or extent of deviations from prescribed controls. The statistical sampling method to be used for carrying out compliance procedures has, therefore, to be such as would enable the auditor to estimate the rate of deviation from prescribed Note 5.1 RTI, JAIPUR controls in the entire population based on the results of his sample examination. A statistical sampling method, which is commonly used in carrying out compliance procedures, is ‘attribute sampling’. (The term ‘attribute’ refers to a qualitative characteristic. In carrying out compliance procedures, the auditor is interested in ascertaining the presence of a qualitative characteristic, namely, deviation from a prescribed control.) Attribute Sampling: Attribute sampling is a statistical method to estimate the proportion of items in a population, which have certain attributes or characteristics. Suppose, the auditor wishes to evaluate the internal control system relating to preparation of sale invoices. For this purpose, he would like to estimate the number of invoices, which have errors. The method of attributes sampling would be of great assistance to him. By taking a small sample, he can draw reasonable conclusions about the proportion of invoices in the total population, which have errors. On the basis of this estimate, he can reach a conclusion as to whether the internal 4 Risk Based Audit Approach Session 5.1 control system in this regard is effective or not. We will discuss this method in detail in session 6.1. Estimating the Quantitative Characteristics of a Population We have already seen that substantive procedures are such audit procedures as provide evidence to the auditor regarding the completeness, accuracy and validity of the data under examination. In respect of substantive procedures, the auditor needs a statistical sampling method, which helps him in estimating the value (amount or quantity) of the population. For example, an auditor may wish to verify whether the amount of sundry debtors, as shown in the balance sheet, is correct. Similarly, the auditor may wish to verify the correctness of the value of various categories of inventories shown in the balance sheet. The most commonly used methods of estimating the value of a population are monetary unit sampling (MUS) and variables sampling. Note 5.1 RTI, JAIPUR Monetary Unit Sampling: This is also known as Probability-Proportional-toSize (PPS) sampling. This method gives proportionately greater weightage to those items, which have higher monetary value. This method is particularly suitable in the case of audit of financial statements since in such cases, the concept of material items often corresponds with the monetary value of the items. The main feature of monetary unit sampling is that it treats the total monetary amount of the balance under examination as population and each monetary unit (i.e., rupee) as an element of the relevant population. For example, if there are 342 items of inventory, valued in aggregate at Rs. 16,61,478, the population size is 16,61,478 and not 342. Since, in random sampling, each element of the population has an equal chance of selection, it is obvious that the probability of selection of an item is directly proportional to its monetary amount. For example, the probability of selection of an inventory item valued at Rs. 1,44,434 is 1,44,434/16,61,478. The monetary unit sampling method is easy to understand and generally simple to apply since it does not involve 5 Risk Based Audit Approach Session 5.1 complex mathematics. The method also results in relatively small sample sizes and is especially useful where the auditor expects a low level of errors. It may be noted, however, that monetary unit sampling cannot be used in situations where errors are expected to be large, or where there are zero or negative balances. We will discuss this method in detail in session 7.1. Variables Sampling: This method of sampling also gives an estimate of the value of a population through a sample and is, therefore, useful in auditing situations. However, under this method, the population size is the number of items constituting a balance and not their total monetary amount. In the example of inventories given above, the population size under variables sampling would be 342 and not 16,61,478 as was the case under monetary unit sampling. Under variables sampling, each item constituting a population has an equal chance of selection, irrespective of its monetary amount. Unlike the monetary unit sampling method, variables sampling method can be used in those Note 5.1 RTI, JAIPUR situations also where errors are expected to be large, or where there are zero or negative balances. However, this method is somewhat complex, and the sample size for a given population is usually larger than that under the monetary unit sampling method. Sampling methods Although there are large numbers of methods of selecting the sample, the four important methods, which are frequently used, are discussed below: (a) Random selection: Random selection is a sampling method in which each and every item has an equal chance of selection. For example, if 5 items are to be selected out of a population of 1000, the items selected could be 1,2,3,4 and 5 or 14,15,16,998 & 999. The numbers can be selected by using random number tables or through the computers. (b) Systematic selection: This is a selection method in which one or two items are selected randomly, but other items are selected by adding the average sampling interval to the item selected randomly. For example, if 5 items are to be selected and the average sampling interval is 200, the items selected could be 14, 214, 414, 614 and 814. In 6 Risk Based Audit Approach Session 5.1 this the first item (14) is selected randomly and subsequent items are selected by adding the average sampling interval (200). The greatest advantage of this method is that when it is used in monetary unit sampling, it automatically ensures that all items greater than the average sampling interval (e.g. planned precision) are selected. However, this method cannot be used when some fixed numbers are assigned to various categories of transactions, which make up the accounts, as either all items of a particular category may be selected or ignored totally. For example, assume that voyages from destination ’X’ are given numbers ending with digits 21-30 and the average sampling interval is 100 and the first item selected is 24. Then the items selected would be 24,124,224,324 etc., In this case all the voyages selected for audit will be voyages originating from destination ‘X’ and the sample would be biased. (c) Cell selection: In this method, the population is divided into a number of cells and one item is selected from each cell randomly. For example, if the average sampling interval is 200, sample size is 5 and the total population is 1000, the population would be broken into cells of 1- Note 5.1 RTI, JAIPUR 200, 201-400, 401-600, 601-800 and 8011000 and one item selected from each cell. This method overcomes the drawback of systematic sampling when fixed numbers are given to various categories, but retains the advantage of systematic sampling of automatically selecting all items bigger than the average sampling interval. The drawback of the above method is that it is much more time consuming. (d) Haphazard: This method of sample selection is also called as judgmental sample selection, in which items are selected according to the auditor’s judgement. This method is more subjective and susceptible to bias compared to other methods. There are various tools available for selecting samples. The most commonly used are the random number tables and the computers. Random number tables are very useful in case of simple random selection and systematic selection. In case of cell selection, computers can be used both for segregating the population and for selecting items from each cell. Advanced auditing software like IDEA.5 7 Risk Based Audit Approach Session 5.1 is of immense use in performing complex sample selection. more than this estimate. The difference between the error in sample estimate and the error in the actual population is the precision level. The auditor has to decide the precision he desires to provide in his estimates. Tolerable error being the maximum error that the auditor is willing to accept (sample estimate + precision level) Designing a sample Once the method of sampling is decided, it is essential to design the actual sample. The basic stages that are involved in attributes sampling are mentioned below: (a) size The confidence level or the level of assurance that audit needs to provide is to be defined. When a risk assessment has preceded the sampling process, the confidence level would be (1-detection risk). Confidence level states how certain the auditor is, that the actual population measure is within the sample estimate and its associated precision level. The occurrence rate or population proportion is the proportion of items in the population having the error/exception that audit wishes to test. The required sample size can be calculated using the formula (Handout 4.2-A), or read off from standard statistical tables (Handout 4.2-B) at the required confidence level. Determining the sample (b) Selecting the sample and performing substantive audit tests on the sample (c) Projecting the results Determining the sample size: The first step is to define clearly the target population and the error/exception (attribute) that audit wishes to test. The tolerable error or the maximum errors that the auditor is willing to accept and still conclude that the auditee is following the procedures properly. Audit test on the sample will throw up an estimate of error for the population. The true error of the population could be Note 5.1 RTI, JAIPUR 8 Risk Based Audit Approach Session 5.1 The sample size would be larger, higher the confidence level and precision required. Also if the occurrence rate in the population becomes larger the size of the sample would increase. In case of variables sampling, where the estimate of a quantity is required, sample size becomes a function of the standard deviation in the population rather than the occurrence rate. Selecting the sample and performing substantive audit tests on the sample There are a large number of methods of sample selection. The most frequently used method is random selection where each item in the population has an equal chance of selection. This could be done by using random number tables or through computers. In a systematic selection, one or two items are selected randomly, but the other items are selected by adding the average sampling interval. The greatest advantage of this method is that when it is used in monetary unit sampling, it automatically ensures that all items greater than the average sampling interval are selected. However, this method cannot be used when some fixed numbers are assigned Note 5.1 RTI, JAIPUR to various categories of transactions, which make up the accounts, as either all items of a particular category will be selected or ignored completely. In the cell sampling method, the population is divided into a number of cells and one item is selected from each cell randomly. This method overcomes the drawback of systematic sampling when fixed numbers are given to various categories, but retains the advantage of systematic sampling of automatically selecting items bigger than the average sampling interval. Projecting the results Once the audit tests are performed on the sample, the test results need to be projected to the population. Following this, a conclusion has to be reached whether the auditor can place an assurance on the systems. After the audit tests, the auditor obtains the actual number of errors in the sample selected. As the sample size and the confidence level desired by the auditor are known elements, the formula given at Handout 5.2-A, can be used to solve for the precision. The maximum error estimate of the population would then be obtained after loading the sample 9 Risk Based Audit Approach Session 5.1 estimate with the precision. This is the computed tolerable error. Instead of solving the mathematical formula, it is possible to read off the 'computed tolerable error' straightaway from the statistical tables for the desired confidence (assurance levels). . e. In a case when the computed tolerable error is less than the tolerable error, the auditor can place the desired assurance on the systems. When the computed tolerable error is higher than the tolerable error, the auditor cannot derive assurance from the systems. The auditor may, in such situations reduce the assurance he derives from the control and increase the assurance required from substantive tests. h. Advantages of statistical Sampling Techniques: a. b. c. d. Note 5.1 The sample result is objective and defensible. Objective evaluation of a test result is possible. The method provides a means of advance estimation of sample size on an objective basis. The method provides an estimate of sampling error. RTI, JAIPUR f. g. It may give more accurate results than a 100% examination for large population size as failure to detect errors tend to increase if the population size is very large. It saves time and money. It may be combined and evaluated even though accomplished by different auditors. It helps in bringing the observations in for sharp focus as these can be analyzed for each type of auditee. Possible areas of application in IA&AD (i ) Audit of vouchers in CAP/CASS sections. Results obtained through statistical sampling can be used to qualify the accounts. In the present system if a sample of 100 vouchers is studied from a given population and mistakes/irregularities are observed in 10 vouchers we give our observations to the auditee and if considered necessary get these corrected and certify the accounts. No attention is paid to the fact there exists a definite probability of presence of similar mistakes/irregularities in the remaining part of the population, which has not been subjected to audit. The good thing is that this probability can be estimated and a qualification made if the probability is more that a predetermined minimum. By using this technique such qualification can also be made DDO/department wisethus findings can be more focused and 10 Risk Based Audit Approach Session 5.1 recommendations can be specific and direct. DDOs or departments with high probability of occurrence of certain types of irregularities (as inferred from the sample) can either be picked up for intensive central audit or can be selected for local audit. In other cases suitable feedback can be provided to local audit parties. (ii.)This technique can be used during local audit also. It can also help in consolidating audit findings in a department. A sample may be selected from similar units and the audit findings can be generalized. For example, if there are say, 1000 primary schools in a state and the adequacy of financial systems being followed in these schools is to be studied, a sample can be selected studied and findings generalized based on which specific recommendations can be made. iii. This technique can be used very effectively in reviews. Presently samples are drawn for a review but no effort is made to generalize the findings, as we do not stick to the given sample. iv. In revenue audit, we may use this technique for determining with a certain degree of confidence the range (in money terms) of under assessment of a particular type of tax. Presently we state, “In so many cases test checked, we found an under assessment of so much.” This statement can be made more meaningful with the use of statistical sampling. We will discuss a case study on use of SS techniques on CERA, in coming sessions. This technique can also be used for audits under section 14 where the distribution of grants and irregularities Note 5.1 RTI, JAIPUR notice during audit of a particular body/authority can be studied for a department. Summary Statistical sampling provides a scientific framework for auditing and allows us to calculate a minimum sample size needed to support a given inference. Attributes and Variable sampling can assist an auditor to estimate a proportion to a given accuracy. Estimation sampling of variables can be used to estimate a value. Monetary unit sampling is best suited to the external auditor. Sampling can be applied in various auditing situations with due consideration of sampling risk. 11