 In this presentation, we will take a look at non-statistical sampling for tests of account balances. Note that we took a look at non-statistical sampling in a prior presentation with relation to tests of controls. Here, we're applying non-statistical sampling for account balances. So, you will see some similarities within the application of the non-statistical sampling. 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. Bayer Dynamic, not sure if I said that right, but this is the DT770 Pro 250 OHM Studio Reference Closed Back Headphones. I wear headphones basically every day for a large part of the day. They are important to me. Therefore, I've gone through many different kinds of headphones. I've had these for some time and they've worked quite well. They fit over my ears, but I'm still able to put my glasses on under the headphones. The headphones not pinching too tight on the glasses to give me a headache which is nice. The quality of the patting is good and it has lasted for some time. I've had these for some time now and they haven't gotten all torn up on me or anything like that. I also like that I have a cord when I'm doing my recordings as opposed to a USB centered headphone because that frees up a USB port and I find the USB headphones to be less reliable. They come with an audio jack that looks like this which is useful for me because that plugs into my audio interface. However, if you want to use the headphones for some other purpose, I believe it's fairly easy to get a converter to other types of audio jacks. 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. Sampling unit for non-statistical sampling is generally a customer account, an individual transaction or a line item on a transaction. The following items must be considered when we're thinking about non-statistical sampling. Identify individually significant items. So we're going to consider those items that are individually significant. We'll talk more about that shortly. Determining the sample size, selecting sample items and calculating the sample results. We'll add some of these items in more detail now starting with identifying individually significant items. Items to be tested individually are items that may have a potential misstatement that individually exceeds the tolerable misstatement. So let's read that one more time. Items to be tested individually are items that may have the potential misstatements that individually in and of themselves, in other words, exceeds the tolerable misstatement. So if we look through the data and we have these types of areas that misstatement themselves for that individual item could exceed the tolerable misstatement, we want to pick those items out. These items will be tested 100% because the auditor is not willing to accept any sampling risk with regards to these items given their nature as significant items. Determining the sample size and selecting the sample. So how do we determine what the sample size is? This is going to be our formula. Sample size will be equal to the sampling population in the book value. So the book value population, then we have the tolerable minus the expected misstatement. So tolerable misstatement minus the expected misstatement will be divided into the sampling population book value or sampling population book value divided by tolerable misstatement minus expected misstatement times a confidence factor. Now this confidence factor might be given in basically our audit papers. We might have some standardized kind of factors that we would use something like a table such as this where the assessed risk of the material misstatement is here and then the desired level of confidence is going to be here. So if we have a high assess risk of material misstatement and a high desired level of confidence, then we're going to have a higher number that we're going to be used as the confidence factor in this case 2.9. If we have a high assess risk of material misstatement and a moderate desired level of confidence, then we'll have a lower factor high assess risk of material misstatement and a low desired confidence. Then we have a lower factor if we have a moderate and then of course in a high desired level of risk we're at this number. If we have moderate and then a desired we're at this number and so on and so forth. And you can see what the desire or what the effect would be in the formula given those numbers here in the confidence factor section of the formula. Calculate the sample results ratio projection method. So we're going to have two methods that we could use to calculate the sample results. This will be the ratio projection method. Apply the misstatement ratio in the sample to the population. So we're going to get the misstatement ratio in the sample, apply it to the population. It would look something like this. Assume the auditor finds $1,000 misstatement in a sample of 10,000. So we have a $1,000 misstatements in the sample of 10,000. The misstatement ratio then is 1,000 over 10,000 or 10%. Now if we apply that to the population, we could say, well, what if the population totals 300,000? The projected misstatement would then be 30,000 because we're going to take that 300,000 times the 10% and get the 30,000. So that's the ratio projection method, not the only method though, because we could use the difference projection method projects the average misstatement of each item in the sample to all items in the population. For example, assume the misstatement in a sample is 100 items that total $400. So 100 items, which total $400 is the misstatement for an average misstatement of $4. So we have the $4, which is the 400 divided by 100, and the population contains 15,000 items. The projected misstatement would then be 60,000 or the $4 times the 15,000 items. So that's going to be the difference projection method.