Source: staircase_20261101-140830 (logit_staircase v1.3.0), temperature 0, 120 tokens. Prompt md5 d78a0cc67c870050941cdfc719e0a365.
It's been said that there are three kinds of lies: lies, damned lies, and statistics. And here are four of the most common ways that people will use statistics to try and manipulate you so that you don't get manipulated. And right now, more than ever, you need to understand statistics. Imagine I tell you that a new medication reduces your risk of getting a disease by fifty percent. That sounds extraordinary, doesn't it? But what if I told you that without the medication, two people in every one hundred thousand will develop the disease, and with the medication, one person in every one hundred thousand will develop the disease? That doesn't sound as good anymore, does it? The relative reduction in risk is indeed fifty percent, but the absolute reduction is point naught naught one percent. Some very common way that people will use statistics to effectively deceive you. So whenever you hear that something increases or decreases a risk by a certain percent, you need to be asking, percentage of what? The second most common way of lying with statistics is something known as base rate neglect. Imagine there is a disease that affects one in every thousand people. You've just taken a test for that disease. And this test is ninety-nine percent correct, and that means that it detects the disease correctly in ninety-nine percent of people who have it, and detects correctly that people don't have the disease ninety-nine percent of the time when they don't have it. Now you test positive, so what's the chance that you actually have the disease? You might think it's ninety-nine percent. Actually, it's closer to nine percent, and this is why. Imagine you test one hundred thousand people. Roughly a hundred people will have the disease, and ninety-nine of those will test positive. Now of the ninety-nine thousand nine hundred people who do not have the disease, nine hundred and ninety-nine of those will also test positive. This is a false positive. Poor mistake was forgetting how rare the disease is within the population as a whole. And base rate neglect, while it commonly occurs in these medical statistics, it also comes up quite a lot in crime statistics and a lot of other places too. So be on the lookout. Third is survivorship bias, and this is a pretty common one right now. Imagine I tell you that so many. Of the world's most successful businesspeople and entrepreneurs drop out of university, so therefore dropping out of university is a good way of helping you become successful. You can probably see where this is going. The problem is I'm only talking about the people who succeeded. What about the people who dropped out and their companies failed or they never started one? These are missing from the dataset, and that's what survivorship bias is. It's drawing conclusions from the cases that you can see that are available to you and just ignoring all of the rest. You've definitely seen one of the most famous cases of survivorship bias before. It's this particular photo, and those are some of the things to look out for if you do not want to be manipulated by statistics. Fourth is the use of percentages to make things seem better than they are. For example, if you have a product that is 95 percent effective, that sounds great, but if you have a product that is 95 percent effective in a specific situation, that's a different story. So, the difference between a percentage and a specific percentage. So, for example, if you have a product that is 95 percent effective in the first week, but only 50 percent effective in the second week, that's a different story. So, the percentage is not a fixed.
Now the question: Which two things is survivorbias an explanation about in relation? What does that say?
Alright.
Alright.
Let’s go over what we need for a correct understanding here.
So first: we're looking into a particular statistical phenomenon that has two components that we have the need and opportunity, as a user or as the observer. That phenomenon we've already identified here. We need a name. And what does this tell me, the listener?
Okay.
Alright.
The user's problem seems straightforward but it requires us first and above, in this instance. We must identify and define