Welcome. Let's continue this section of the course where we're talking about  testing hypotheses with data by now moving into the next step in hypothesis  testing, gathering your data and calculating the test statistic. The test statistic  

basically summarizes the amount of information that your sample provides you  can sort of think of the test statistic like evidence in a court case, and in all  honesty, it'd be so much easier if court cases actually just did this with a single  number, because that's what we're going to calculate. We're going to calculate a single number, and that single number is going to represent all of our evidence,  and again, like I said, it'd be so much easier if court cases were like that, you  know. The prosecution stands up, looks confidently at the jury, and goes 27 and  the jury goes, "Oh, wow, okay, it's done, it's over, you know what, guilty.  Whereas the prosecution may stand up again, trying to look all confident, and  they say something like 1.2 and the jury's like, I'm not impressed. Nope, nope,  innocent until proven guilty. So we're going to say not guilty again. See how  much easier it would be if that were the case. But either way, so test statistics  again are sort of a numerical summarization of the amount of information, the  amount of evidence that a sample provides, and the nice part is that test  statistics have a common form. A test statistic is basically your sample statistic  minus the null value divided by the standard error. Luckily, you've seen all three  of those numbers before. Again, the statistic is just the samples information for  sample means, it would be exactly that, it would be just the sample mean for  sample proportions, it would be just the sample proportion. So, whatever  number you're testing from your sample, the statistic, that's what this first  number is. The null value comes from the null hypothesis, it's the number that  you think the null hypothesis is, so you have some initial thoughts, some initial  number in your null hypothesis, so that is what this null value basically  represents. So, again, with this numerator in this ratio, we're looking at what  does our sample say, and what did we think was going on beforehand? That is  going to be what we're looking at the difference between. Remember, in our last  lecture, we were looking at the difference, right? We said, well, here's our  sample average daily users. Let's subtract off the total number of daily users, or  the average daily users we thought it was. Of course, last but not least, we have the standard error. This comes from that idea of variability from the sampling  distribution of the statistic. Again, statistic, we can compare where a number is  on a distribution, but you have to have some idea of scale, you have to have  some idea of variability, right? So, if I told you that I was only estimating, well, I  was only off in estimating something by $30 maybe that's impressive, maybe it's  not. If I was talking about the US GDP, then wow, if I was only off by $30 I was  really close. If I was talking about how much money I spent in McDonald's  yesterday. Well, that no, that was off by a lot. So, again, it all has some notion of scale. That's what the standard error is. The standard error has some measure  of scale. So, when it comes to sample means, remember when we were dealing

with confidence intervals, when it came to confidence interval, sample means  had to look at a t distribution because we didn't know the value of the population standard deviation. It's actually the same thing here. So, when looking at the t  distribution, we're just going to call the test statistic for sample means t, just sort  of after the distribution that it comes from, so t is going to equal our statistic,  which here x bar minus our null value, our original thought, it's the number from  the null hypothesis, we call this mu zero, mu naught, and then we divide it by the standard error of x bar, which is just the sample standard deviation s divided by  the square root of n, and that's it. That is our test statistic that will essentially tell  us how far away our sample data is from our original thought. If our sample data is really far away from our original thought, we start to question our original  thought. If our sample data is really close to our original thought, then you know  what, our original thought may be right. That's the general idea. The nice part is  we could do the same thing for proportions as well. So again, sample  proportions use the normal distribution, so we can take a look at the same idea.  We can take a look at a statistic p hat. We can subtract off a null value, maybe  some original thought about proportions, like for example, I think that only half of the days in DC are clear or cloudy, so that could be some original thought, and  then we divide again by some notion of a standard error, the square root of p  zero over, I'm sorry, times one minus p zero over n. So let's summarize the test  statistic, really is just some numerical summary of the amount of information that your sample provides, that's really all it is. And to calculate this test statistic, you  typically only need three things. First, information that you obtain from the  sample itself, basically the statistic you're trying to compare. Next, you need  information about your original claim, your null hypothesis. We call this the null  value, and last but not least, you need some measure of variability to be able to  scale this comparison between the statistic and the null value that we use the  standard error, but okay, so you've collected enough data, you have all of this  data that's here. How do you know how much evidence is enough evidence?  When is something rare enough? Well, that's what deals with the next step of  hypothesis testing, the p value, as well as the significance level. When we talk  about p values, the p stands for probability, and the p value is the probability you got your sample or something even crazier, more extreme than your sample  underneath the null hypothesis. So again, remember, why do we think the null  hypothesis is true? Well, that's your original thought, that's your original claim.  It's just like a court case, remember, innocence until proven guilty. So we're  going to assume innocence, we're going to assume the null hypothesis is true,  and the p value is going to represent the probability we see all of the evidence  that we do, the probability we get the sample that we do underneath that null  hypothesis. Again, that's how a case in a court of law should work. A jury should  go in, for example, and not assume guilt. They should assume innocence, and if  the prosecution can gather enough evidence, then the jury starts to question 

that original thought of innocence and says, "You've captured enough evidence  to say for us to say that this person is guilty, right? That's the idea, but again, we have to figure out what's the probability we got our sample. Go back to that coin  

flip example I gave you. I flip a coin once, it's heads, you still think the coin is  fair. I flip it two times, both of them are heads, you probably still think the coin is  fair. I flip it five times in a row, and it's all heads. Yes, could that happen? Sure,  but the probability of that happening really small. You're no longer starting to  believe that null hypothesis. Now, if the p value is low, so again, if that  probability is really small, this implies that the sample we obtain from the  population is extremely rare. Again, if we were to assume that null hypothesis is  true, again think about it in that fair coin example, could a fair coin get five flips  in a row that were heads. Yes, it could. It's probable. I'm sorry, it's possible. It's  just not probable. Could it happen? Yes. Is it likely to happen? No. And so this  leads us to question the validity of that null hypothesis and If we no longer  believe the null hypothesis, we reject that null hypothesis if the p value is low  enough. If the chances are small enough, we're no longer going to believe that  null hypothesis is true. The question, though, is how low is low enough. How  rare is rare enough? That's what we call the significance level alpha. If the p  value is less than or equal to the significance level, the sample is so rare. We no longer believe the null hypothesis is true, and we call this rejecting the null  hypothesis. So, you can think about it this way: going in, you think to yourself,  you know what, I'm going to have him flip this coin, and if what he flips happens  less than 5% of the time I'm no longer going to believe that that coin is fair, and  so I flip a coin once, it's heads, 50/50 chance, I flip a coin twice, it's still heads,  now there's only a 25% chance, I flip it three times, it's heads, there's a 12.5%  chance, I flip it four times its heads, it's a 6.25% chance. I flip it five times its  heads, and now it's a three point something percent chance. And you're like,  that's it. I said, if this got less than 5% I would no longer believe it. You are below 5% that is my significance level. For example, I am no longer going to believe  that null hypothesis that this is a fair coin. That's the idea. The significance level  is sort of that definition of how rare is rare enough. The p value is the probability  you actually saw what you did, so maybe it's rare, maybe it's not. We don't know that ahead of time. That's the whole idea. That's why we're testing these things.  If it is rare enough, if the p value is smaller than the significance level, then we  no longer believe the null hypothesis. We reject the null hypothesis. Now, there  are two possible outcomes from a hypothesis test. Again, if the p value is  smaller than or equal to alpha, we no longer believe the null hypothesis is true.  We call this rejecting the null. However, if the p value is bigger than alpha, so  again I flip the coin four times in its heads, there's only a 6% chance of that  happening, but you said that if it had to be less than 5% then you'd no longer  believe me. So, at 6% you're still good, you still believe the coin is fair. So, you  do not have enough evidence to say the coin isn't fair, or you do not have 

enough evidence to say the null hypothesis isn't actually true, so here we say  we do not reject the null hypothesis. This goes back to that idea of guilty versus  not guilty, like I mentioned in the last lecture. We don't actually say innocent at  the end of a court case. We're not collecting data for innocence; we assumed  innocence. We're collecting data for guilt. If you have enough data, if you have  enough evidence for guilt, then you reject innocence. You claim guilty. If you do  not have enough evidence for guilt, then you just say not guilty. You don't have  enough evidence to reject innocence, so innocence still holds true. That's the  idea. Let's try and view this, you know, on a graph. It may help a little bit. So,  let's imagine we were testing the alternative hypothesis that mu was less than  some number, so we're going to say that mu is equal to some number, that's our initial null hypothesis. So mu is going to equal some number. I'm going to collect  a sample that is my sample, I'm going to represent it with t notice how my  sample is far away, quote unquote, from the original null hypothesis, but how far  away is far enough away. Well, I shaded in the probability that I got a sample  that far away, or even further. Again, I'm testing what's the probability in my  alternative hypothesis of being below this number, so the chances of me being  smaller than or equal to t is that green shaded p value you see. Notice the  original shaded area, alpha was the original shaded area. If my evidence was in  that original shaded area, if it was smaller than that, then I'm no longer going to  believe my null hypothesis. And that's exactly what happened. I'm rejecting the  null hypothesis. My p value, that shaded area that's green is smaller than the  blue shaded area, so I no longer believe the null hypothesis is true. Again, my  sample is so far away from my initial thought, at least according to p value, I no  longer believe it. What if it was this? On the other hand. In this scenario, my  data was a lot closer to the null hypothesis. In fact, if we look at the green  shaded p value here, it actually is rather large compared to the alpha. In fact, my p value is bigger than my alpha, so I don't have enough evidence to reject my  null hypothesis. My p value is bigger than alpha. I said I had to be at least alpha  far away, and I'm not, so my values are close together according to the p value,  and because of that, I can't not believe the null. The null said innocent. I'm going to stay with innocence. I don't have enough data to prove otherwise. The same  thing could be done on the other side. We could be testing if a number is bigger  than the null hypothesis. Same idea holds true if it's really far away. If your data  is really far away from your initial thought, the probability of seeing it is really  small, and so it's so small it's smaller than that alpha level. Then you know what, we no longer believe that null hypothesis, because these values are far apart.  So things don't have to be done just on one side of the distribution, lower or  upper, they can be done on both. So, again, what if I had an alternative where  I'm like, I don't know if it's going to be too high, and I don't know if it's going to be too low, but I just think it's different. Again, we can do the same idea. We just  sort of have to split our p value into two pieces. We can say, well, maybe we're 

high, maybe we're low, and so if we were to add the two pieces of our p value  together, is that less than or equal to adding our two pieces of our alpha  together? That's the idea. Again, imagine you had, I'm willing to be wrong 5% of  the time. Imagine that if it's less than 5% I no longer believe it. Well, okay, but if  you can say high or low, then that 5% could be split into two pieces, 2.5% on the low end, 2.5% on the upper end, and we'll do the same thing with our p value,  we'll split that into two pieces as well, but again, the notion is these values are  still far apart or close together. Are you close enough to the null to where you  can't reject innocence, or are you far enough away from your original thought  where you can reject that innocence, so again let's take a look at our hypothesis testing coin example. So we have our five flips of a coin. The probability of me  getting five heads in a row is 3.125% again just over 3% you no longer believe  the coin is fair, but could it be fair? Yes, it could be fair. It could. There's a 3%  chance that it is fair, but you just don't believe it, because that number is so  small, that's the idea, that's the idea of significance level in p values, the p value  is the probability, the significance level is how small is small enough, where you  no longer believe the null, so again, this significance level is something, in all  honesty, you should do this before you even run the hypothesis test. It basically  defines where the unlikely values of the sample are going to be under the  assumption that the null hypothesis is true. Another name for this is called the  rejection region, so if we were to look back, for example, at this chart here, the  blue shaded area highlighted by alpha, that's the rejection region. Any data  sample that's in that region, you're no longer going to believe the null, your data  is too far away from the null, whereas here our data was not in that rejection  region, our data was closer to the null than where that rejection region started.  That's another way of thinking about this idea of significance level. There are a  lot of typical things that people use: 1% 5% 10% Those are some typical values, so let's summarize the p value is the probability that you got your sample or a  sample that's even crazier than the one you've seen, all under the assumption  that the null hypothesis is true. Now, if that p value is low, that would imply that  the sample that we obtained from the population is extremely rare if we are to  assume the null hypothesis is true, but again, How rare is rare enough? That's  where the significance level comes in. The significance level defines the unlikely values of the sample statistic, if that null hypothesis is actually true, and so if our p value is below the significance level, we reject our null. If the p values are  greater than the significance level, then we don't have enough evidence to reject the null hypothesis. Awesome, so now we've worked through all the steps of the  null hypothesis, and in our next lecture, we'll work through an example, but that  is the end of this lecture, and I look forward to seeing you in the next one.



Last modified: Monday, June 29, 2026, 8:28 AM