 So now, this is what we made the change on, we increased the ace of spades and we removed entirely the three of diamonds. So then if I populate our results here, we have our assigned numbers again on this column. This is the card number with the suit, one through the king of spades, one through the king of hearts, or ace through the king, and then these are the results. Now the results, we're doing the same thing, we're saying count if, meaning I'm telling Excel to count this number, these numbers, but we adjusted it to remove all of the three of diamonds and replace them with a spade, ace of spades. So we did a count that column, and we said count if, and then according to this number. And so the results we get, now we've got these results and we can say, okay, if I do my same analysis, I can say, well this 181 ace of spades came up out of 5000 divided by 5000, that came out to 3.62, which obviously looks quite high because you would expect it to be 1 over 52, if you did it infinite amount of times 1.92, right? And then you could do this for the rest of them. This one came out to 108 divided by 52, 108 divided by 5000 comes out to that. This one came up to 94 divided by 5000 and so on. So these are hovering around kind of what we would expect. So this is the actual, this is what we would, what it would be if we did an infinite amount of times or the fair amount. And then of course, if we get down to here, we see there are zero diamonds or three of diamonds. Obviously that's an indication that that would be very rare to happen if we drew 5000 times out of the deck. We didn't get any of those, right? So that would be unusual. So obviously this would be an indication that the null hypothesis that it's a fair deck would be incorrect and we'd probably, we can also do the same thing if we counted the spades, right? So if I counted up all of the cards, because we increased the ace of spades, you would expect the ace of spades to be higher. So now we've got, we've got the spades came out to be 1364 out of 5000, which is 27.28 This is 25%, which would be the ace of spades, there's 13 out of 52. If it was fair, 25%, right? And so, so you can do that kind of analysis and you can do the analysis with each, you know, card, but I won't, we won't do that again here. Let's just take a look at the, at the charts. So here are the results here. So here's the histogram of the results. So that's a histogram of this one. And again, you would expect if I had a histogram of the results that, that the results would be around, I mean, if I drew one out of 52, that's 1.92% times 5000. So you would, you would think it would be hovering around 96. And so you've got a kind of an around here, but you've got these kind of funny outliers that and sometimes those are the things that, you know, depending on what we're looking for the outliers might be something that, you know, that is, that we're, is going to draw our attention, right? And then we've got, if we did it this way, this is just a histogram of the, of the full data set again. So we took the full data set and said count them. And this one gives us a pretty good picture of something funny going on because, because this would be, I tried to get the histogram to do something similar to listing just one out of 52, right? And we get obviously this one is looking quite high and this one's at zero. And we would expect that this would be hovering around one over 52 times 5000 around the 96, right? So this one, like that was obviously that looks funny. So that will give us some indications on the random draws. And I can, and then I just regenerated the bar chart this way. So now I can actually have the numbers one to 52, not using a histogram, but the bar charts. In this case, I used this column for the X and then the results for the Y. So these are just a couple of different ways we can see the data and analyze and analyze the data in a similar way we did with the coin flips so that we can then use our kind of sampling, the sampling concept being that the whole population would be as though we drew the cards an infinite amount of times. And if we did that, again, then we can think what we know the whole population theoretically in this case, right? We know the whole population would be one out of 52 percent, right? And so again, we can compare that to the sample being whatever finite amount of times that we run that test. And then of course, we can take a look at the results from the sample and see how different they are from the null hypothesis or what we would expect the entire population to be if it was fair. And then if there's a substantial difference between the two, that's the evidence that we might have that we would then reject the null hypothesis and come to a different conclusion.