In this lesson, you're going to learn about bias. You've probably heard the term bias before. And it's probably in the context of the media. You might think about it as political spin doctoring. But in the context of research, bias mean something a little bit different. The fact is, with research, that the vast majority of the time, it's done with integrity. People want to get the job done right. They want to get the answer correct. But sometimes there's something that happens systematically in the experiment or the study that limits the accurate representation of the population that you're going for. All bias is to us, in the statistics world, is systematically misrepresenting the population. And the key word that I want you to focus on here is systematically. It's not necessarily intentional. It could be intentional, but it doesn't have to be.
There are many different types of bias, and we're going to talk about a few in this tutorial. And some will get their own tutorial. Selection bias is a way of selecting the sample for your study such that the sample doesn't accurately reflect the population. And that's not good. Sometimes it can't be avoided, though.
Another kind is publication bias. This is done when researchers only want to publish the most sensational findings that they have come up with. Or, when publication articles only want to publish the articles that they get that are the most sensational. So, only the positive ones. Only the ones that people will want to read, are the only ones that make it to people's eyeballs. So, that idea of people not wanting to read things that they've deemed boring is publication bias.
And there are lots of other kinds too. Nonresponse, response bias. All of those are big deals, and they're covered in a separate tutorial. There's one more that we want to talk about. And it's called the Hawthorne Effect. The idea with the Hawthorne Effect is that people will behave differently if they know that they're under observation.
Let's take, for example, a weight loss study. Maybe one group is told to take a pill every day, and the other group also takes a pill, but it doesn't have any ingredient in it. They're told not to change their behavior. Don't exercise anymore, and don't need any differently. However, these are people in a wight loss study. They're trying to lose weight. We think that they might go ahead and change their behavior anyway. Maybe they'll want to help the study along by exercising some more, or starting to think more about what they eat. People might change their behavior based on the fact that they know they're going to be weighed in later. And so this idea that people might change what they would normally do based on the fact they're under observation is a type of bias called the Hawthorne Effect.
So, to recap, bias is bad. Bias is a very problematic influence in many experiments and samples. Unfortunately, when bias exists, the results we get aren't generalizable to the population. They're not reliable.
We talked about several types of bias in this tutorial. And other types of bias will appear in another tutorial. We talked about, in this tutorial, selection bias, publication bias, and the Hawthorne Effect. And the biggest deal that I want you to come away with is that bias is not always intentional. It's some systematic flaw in the sample or in the experiment, but it's not always on purpose. Good luck, and we'll see you next time.
The tendency for collected data to differ from what is expected in a systematic way. Biased data can often favor a specific group of those studied.
People have the tendency to change their behavior when they know they are being monitored.
Bias that occurs when a sample consists entirely of volunteers. People with strong opinions may be the only ones who volunteer.
The desire of researchers (and research publications) to only print the most sensational or interesting articles.
Bias that occurs when a respondent tells the interviewer "what they want to hear" or lies due to the sensitive nature of the question.
Selecting a sample in such a way that certain subsets of the population are systematically excluded.