Online College Courses for Credit

4 Tutorials that teach Selection and Deliberate Bias
Take your pick:
Selection and Deliberate Bias

Selection and Deliberate Bias

Author: Jonathan Osters

Determine selection and deliberate bias in a study.

See More

Try Our College Algebra Course. For FREE.

Sophia’s self-paced online courses are a great way to save time and money as you earn credits eligible for transfer to many different colleges and universities.*

Begin Free Trial
No credit card required

46 Sophia partners guarantee credit transfer.

299 Institutions have accepted or given pre-approval for credit transfer.

* The American Council on Education's College Credit Recommendation Service (ACE Credit®) has evaluated and recommended college credit for 33 of Sophia’s online courses. Many different colleges and universities consider ACE CREDIT recommendations in determining the applicability to their course and degree programs.


Selection Bias

Source: Image of pot of soup created by Jonathan Osters; Poll Chart created by Joseph G; Image of Clinton, Public Domain

Video Transcription

In this tutorial you're going to learn about selection bias. Selection bias deals with not selecting the right group of people for your sample.

And I just want you to think about sampling is in a pot of soup analogy. We want to be representative in who we obtain for our sample. And that would be like selecting a little bit of all the ingredients in a pot of soup. But things can go wrong with the taste test that limits our ability to draw conclusions about the whole pot of soup as a whole.

Selection bias is also called undercoverage bias. And it occurs when a significant subset of the population is a left out of the sample. Somehow they were systematically ignored from the sample. Now notice this is not necessarily intentionally left out. But they were systematically ignored by whoever was taking the sample.

So an example would be the 2008 presidential primary. Almost every poll, if you look down here at the bottom, in the days leading up to the New Hampshire presidential primary in 2008 every poll showed Barack Obama leading by at least 5 percentage points. All of these were based on random digit dialers calling a random sample of New Hampshire households. It was a well done survey by all accounts.

However what happened was Clinton gained some support in the last few days. And mainly a lot of college students ended up coming out in support of Hillary Clinton in the last days when a lot of people were expecting all college students to come out in support of Obama. She ended up winning because a lot of those college students were not counted. Because they aren't actually New Hampshire residents. They're not from the state. They go to college there. So they can vote. But they aren't official residents. They're not households in the state. So they weren't counted as being part of the sample. As a result the sample got every prediction wrong.

Now I mentioned on the previous slide that the New Hampshire primary used random digit dialers. So random digit dialing involves using a machine to select random phone numbers from within selected area codes. So it doesn't randomly select the area code necessarily. But once it's in the area code it can randomly just select digits and dial that particular phone number after which the poll can be conducted.

And the biggest advantage of using random digit dialers, instead of say the phone book, is that random digit dialers will be able to reach mobile phones, cellphones, and unlisted numbers that you wouldn't be able to obtain using the phone book. So it makes everything a little bit more even of a playing field. Anyone can be selected for that sample, so long as their phone number is within that particular area code.

Now how does selection bias affect the soup? How does it affect what we think is in the soup? Imagine that there were certain ingredients that were only located in certain locations in the pot. Imagine there were stuff that only were on the bottom, stuff that sunk to the bottom. If you took a taste only from the top it doesn't matter how big that taste is. If you missed the stuff on the bottom you wouldn't even know what was there. You wouldn't get the right taste of the soup. That's the same as dealing with selection bias. Because you didn't select the representative group of ingredients from the population. And so you don't get the right idea of what's going on.

And so to recap selection bias occurs when some subset of the population is left out. It might be intentional. It's probably not. And the terms we used here are selection bias, which is also known as undercoverage. Good luck. And we'll see you next time.

Deliberate Bias

Video Transcription

Download PDF

This tutorial is going to teach you about deliberate bias. Now, deliberate bias is what it sounds like. It's bias that's done on purpose. Now, this doesn't happen very often. Deliberate bias can occur when there's a conflict of interest between the people performing research and the people funding or benefiting from that research.

So for example, suppose a drug company funds a study to determine if its latest drug is effective. The researchers stand to gain a lot of money and prestige for having tested the drug and proven it effective, so they might not be the best choice to test the drug. Or an environmental research group is hired by a real estate developer to investigate the effects of a new building.

Now, the thing is they might get another contract with that developer if the results are favorable. And they might think, well, if we don't give him a favorable interpretation here, then someone else will, and they'll get the next contract. And so the environmental research group stands to gain by being hired by the developer again on another project. So there's a little bit of a conflict of interest, and they can maybe pull some punches, or not make it seem like it's quite as bad.

Typically, deliberate bias is motivated by an interest unrelated to the integrity of whatever you're researching. Most research is done with integrity, but when personal prestige, advancement of some ideology, or money get in the way, then it's harder to prove that your intentions are pure.

Sometimes-- this happens fairly often in politics-- people will call with a poll and put into their survey a leading question in order to cause the person to lean one way or the other, or to put an idea in someone's head. So for example, a questionnaire sponsored by the makers of Drug B, which are right here, might say, if you knew Drug A was linked to cancer, would you be more likely to choose B, less likely to choose B, or equally likely to choose B?

Well, I mean, obviously it would make you more likely to choose B, and now look at what they've done. They've put it in the person's mind that Drug A is linked to cancer. Did they ever explicitly say that? No. They said if it was linked to cancer. But that doesn't make any difference. They placed the association in the participant's mind, and subconsciously they're beginning to steer them away from Drug A and towards Drug B. When this is done in politics, it's called push polling, and it's very highly suspect.

And then finally, there's unintentional bias. Unintentional bias occurs when there's simply an error in the design of the study. So unintentional bias might be response bias due to wording of questions, or people feeling like they have to lie. Or selection bias, which has to do with how the sample got selected, where people got not covered representatively. These are simply errors. They're not intentional.

And so to recap, most of the time this isn't an issue. Most of the time deliberate bias is not something that we need to think about. Most of the time research is done with integrity, and when bias occurs, it was on accident. However, sometimes people with personal interests-- like the advancement of an ideology or financial gain-- they can steer results towards outcomes that are favorable to them, and that's called deliberate bias. Good luck, and we'll see you next time.

Terms to Know
Deliberate Bias

The purposeful misrepresentation of data for the purpose of advancing an agenda.

Random Digit Dialing

A method of contacting people on the phone. Random numbers are dialed, so this allows researchers to sample people with unlisted phone numbers.

Selection Bias

A bias that results from systematically excluding certain subsets of the population from the sample. It is not necessarily intentional.

Unintentional Bias

Bias that is not purposeful. It exists because of errors in the design of the study.