 In this presentation, we will take a look at Attribute Sampling Applied to Test of Controls. When conducting a statistical sample for a test of controls, auditing standards require the auditor to properly plan, perform and evaluate sampling application. First, a word from our sponsor. Well, actually, these are just items that we picked from the YouTube Shopping Affiliate Program, but that's actually good for you, because these aren't things that were just given to us from some large corporation which we don't even use in exchange for us selling them to you. These are things that we actually researched, purchased and used ourselves. Acer 27 inch monitor. I've been using an Acer monitor as my primary monitor for a few years now. This is the first Acer monitor that I have used after having used a series of different brands of monitors in the past. The Acer monitor has been performing well, and I'm trusting the Acer brand more and more as I use the monitor. I have a 27 inch monitor, which I think is ideal for what I do, which is, of course, the screen recording and the editing. If you would like a commercial free experience, consider subscribing to our website at accountinginstruction.com or accountinginstruction.thinkific.com, where we have many different courses. You can purchase one at a time or have a subscription model given you access to all the courses, courses which are well organized, have other resources like Excel files and PDF files to download and no commercials. And to adequately document each phase of the sampling application, those phases including the planning, the performance, evaluation and document. We're going to go through each of these phases, of course, starting with the first one that being the planning phase. Within planning, we will set test objectives. Objective of attribute sampling when used for tests of controls is to evaluate operating effectiveness of the internal controls. We will define the population's characteristics, those including define the sampling population, define the sampling unit, define the control deviation conditions, discuss these items in more depth shortly. Next, we will set the sample size using desired confidence level or risk of incorrect acceptance, tolerable deviation rate, expected population deviation rate. Again, we will go into these items in more depth shortly. Now we're going to go into the definitions up here in the define the population characteristics starting with the defined the sampling population. So what does it mean to define the sampling population? That's going to be all or a subset of the items that constitute the class of transactions make up the sampling population. So the sampling population is the entire population. So for example, if we wanted to test something, say we're testing an internal control related to the purchasing process, some type of verification within the purchasing process, we have the purchasing documentation going through, we want to check that there's some type of verification in accordance with the set of controls, which may be indicated, say by initials related to that documentation. So the population size then would be all of the documents and that would be involved in this purchasing documents that should have this indication on it that they have been properly verified in accordance with the internal control. That's going to be the entire full population or the sampling population define the sampling unit. The sampling unit then is each sampling unit makes up one item in the population. So in this case, it would be one of the purchase order documents that we're looking for that would have this indication that it does have the verification on it. This sampling unit will be defined in relation to the control being tested. So that's going to be our units that we're going to be testing, we're going to be testing these units. And then we're going to be testing to see if they apply or are in compliance with what we are looking for. In this case, we're going to say some type of initial that would indicate the verification define the control deviation condition. A deviation is a difference from the adequate performance of the internal control. So if we were to, for example, look at this document, be expecting some initial that would indicate the verification, and we don't find that, then that would be the deviation. We have to say, okay, there's going to be an item that we have found that's a deviation. Doesn't mean that the whole population is now wrong, because we might expect, depending on the type of controls that we will have some deviation, but we're testing the amount of deviation within that basic sample size that we're then going to apply to the entire population. Then if we go to the set the sample sizing, size using desired confidence level or risk of incorrect acceptance. So we're thinking about the setting of the sample size, looking specifically at the desired confident level or risk of incorrect acceptance. Confidence level is this desired level of assurance that sample results will support the conclusion that the control is functioning effectively. Usually, when the auditor has decided to rely on controls, the confidence level is set at 90% or 95%. So notice we're getting very specific in our testing here using statistical sampling, actually using the units of 90 to 95%. This means the auditor is willing to accept a 10% or 5% risk of accepting control as effective when it is not. So that means that within our statistical sampling, we're recognizing that we're at a 90 to 95% statistical sampling, which means we're willing to accept that the sample is incorrect or the results from it are incorrect at 5% or 10% in this example. Tolerable deviation rate, the maximum deviation rate from a prescribed control that the auditor is willing to accept while still considering the control effective. For example, if a control is highly important, the tolerable deviation may be set to 5%. But if it's only moderately important, we may set it to 10%. So once again, tolerable deviation, what is going to be tolerable within the deviation, the maximum deviation rate. So with the deviation rate now, that's going to be the maximum deviation rate from a prescribed control that the auditor is willing to accept while still considering the control effective. So we're going to say we're accept these deviations, and we're still going to basically come to the conclusion that the control is effective. Expected population deviation, this is the expected population deviation rate is the rate the auditor expects actually exists in the population, the larger the expected population deviation, so the deviation that basically deviation from what we're testing, the larger the sample size must be. So if we're considering that if we look at it, we consider that there's going to be a larger deviation, then we would want to increase the sample size because there's going to be more risk, not considering any other factors. Attribute sampling population size. Although it would seem so, population size is not an important factor in determining sample size for attributes sampling. So let's read that again, because this is a bit counterintuitive if we're not a statistician here, the population size is not an important factor in determining the sample size. And if you're not a statistician, you would probably think that it would be, you'd probably say, well, how do we know what the sample size would be? Well, wouldn't we first need to know how large the population is? In other words, if you're talking about basically trying to pull the entire country and determine what their opinion is about a certain who they're going to vote for or something like that, you would think that you'd have a bigger poll just based on how big the country is. And that's since the population size being the thing that's going to determine what your sample size would be, you need a bigger sample, you would think in order to represent a larger population. But that's not the case generally when you're talking about large number type of items. Now, if you're talking about small populations, that may well be the case. The population size has little or no effect on sample size, except when the population is relatively small, say less than 1000. So if you're talking about you want to basically take a sample of something that's less than 1000 and think about how big the sample size should be, well, then you might adjust it based on how big the sample the population is. If it's something under a 1000, you might adjust then your sample to coincide with the population that was 500, 600 up to 1000. But if you're talking about large populations, then that no longer is necessarily the case. We do have these relationships below. So we're going to have these relationship factors in this table, expected population deviation rate. So if we want the expected population deviation rate to go lower, now this is the expected population deviation rate, then the effect on the sample size would be to decrease. So if we want the expected population deviation rate to increase, then we're going to increase the sample size. So these are the factors we're taking into consideration. And then we have the tolerable deviation rate, the tolerable deviation rate, if we want it to go lower, we're actually going to increase the sample size. if we want the tolerable deviation rate to go higher, we're going to decrease the sample size. So in other words the tolerable deviation rate has that inverse relationship and then we have the desired confidence level and that's going to be a straight relationship again. If the desired confidence level we want it to go lower then the effect on the sample size is to decrease. The desired confident level if we want it to go higher the effect on the sample size is to increase and then again the population size, decrease size only when the population is small say less than something like a thousand.