Online College Courses for Credit

2 Tutorials that teach Importance of Experiments
Take your pick:
Importance of Experiments

Importance of Experiments

Author: Dan Laub

In this lesson, students will learn why experiments are important in the context of statistics.

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

29 Sophia partners guarantee credit transfer.

314 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 27 of Sophia’s online courses. Many different colleges and universities consider ACE CREDIT recommendations in determining the applicability to their course and degree programs.


Video Transcription

Download PDF

[MUSIC PLAYING] Hi, Dan Laub here. In this lesson, we're going to discuss the importance of experiments. Before we get started, let's discuss the objective for the lesson. We want to be able to identify independent and dependent variables. So let's get started.

The focus of the field of statistics is studying data and information while determining how to interpret this information in useful ways. The primary goal of statistics is to collect reliable information and interpret it to learn more about the world around us and the people and things in it. Statistical methods are often applied to questions about nature and society in order to learn more about them, and can also be applied in many different situations and contexts.

In our society, we are seemingly always encountering statistics in the media, in our jobs, at the doctor's office, and in a wide variety of other situations. For example, knowing statistics is important when looking at your exam grade and understanding how well you did relative to the rest of the class. Knowledge of statistics is also important when a doctor is explaining that there is a 5% chance that a drug they are prescribing you can have a specific side effect.

Knowing more about statistics and how they are created and analyzed can allow us a greater understanding of these situations and provide us with a greater ability to interpret the significance of the statistics that we come across. That being said, the goal of this course is to introduce basic statistical concepts in a relatable way, while applying these concepts to everyday life.

Now, there are many methods of gathering information and statistics, including observational methods and experimental methods. Observational method would simply be watching something, and kind of getting a sense for how it changes. The experimental method, on the other hand, would be when we actually devise an experiment, and when we change certain things that are involved in an experiment to see what kind of effect it actually has. In this course, we will focus on the experimental method, a very important approach to gathering information and statistics.

The experimental method involves conducting experiments to learn more about the cause behind something, or how one thing might impact something else. While we could disclose information simply by observing, using the experimental method is beneficial because it permits us to establish whether there is a cause and effect relationship existing between two things. For example, one would expect that the more time you spend studying, in all likelihood, you're going to get better grades. The experimental method, on the other hand, would track that. You record how much time you spend studying. And then you record the grades that you get and see if you can determine any kind of cause and effect relationship between those two.

Another example, one expects that the fewer calories they consume, in all likelihood, they're more likely to lose weight. We would engage in the experimental method by tracking those calories and tracking the weight. Another example, we would expect that the slower a person drives, the better gas mileage they're going to get. How will we actually engage in the experimental method with that? We would simply track how fast we drive, and then track what kind of gas mileage we received.

By using the experimental approach with these three scenarios, we would have the ability to determine whether one element of each pair is causing the other element. Now, with the experimental method, there are eight steps. And I want to go through these eight steps by using an example. And the example I want to use would be taking a specific medication in order to reduce the symptoms of a cold.

So maybe you've had a cold for a while, and you're trying to figure out what medication is going to help you feel better. And by using the experimental method, we could actually figure out a methodical way of tracking these results. And so the first step, step one, choose two things that you think might have a cause and effect relationship, where one might be causing the other. And so in this case, you're choosing a specific medication. And you think it has a cause and effect relationship, because if you take that medication, it will make you feel better or relieve the symptoms of a cold.

Step two, make a guess as to how these elements might have a cause and effect relationship. So if you take the medicine twice a day, you would imagine that it's probably going to make you feel better shortly after taking it. Step three, predict what you think will happen if changes are made to one thing, and how that will affect the other thing based upon your guess. So your prediction is, if I take this medication, I will feel better.

Step four, test your experiment with a prediction by trying to determine if, in fact, the things we are looking at share the cause and effect relationship that was predicted. How will we do that? Make changes to one element that may be affecting the other element. And then observe what happens to the other element after the changes in the first element are made.

So perhaps you're taking the medication for a few days and you don't notice feeling any better, so you stop taking it. And then you record what happens then. Maybe you do feel better, in which case, the medication wasn't doing much good. Or maybe you feel worse, which means that the medication probably was helping your symptoms.

The elements that are being changed or observed are called variables. The explanatory variable is the element that the experimenter actually changes, which in this case, would be taking the medication. The response variable is the element that is observed, which in this case, would be how well the person feels with regard to the symptoms of their cold. And that may be changing in response to the explanatory variable.

The idea here is that the experimenter will keep careful records and measurements as they make changes to the explanatory variable, and observe how the response variable responds or fails to respond. The fifth step of the experimental method is to analyze the results of the test to determine what the results tell you about the cause and effect relationship between the two variables. Analyzing the results here, take the medication, record how you feel after a specific period of time.

In step 5, the experimenter will then analyze the information from step four and used statistical tests to determine whether changes in the explanatory variable are, in fact, causing the changes observed in the response variable. The two variables would have a cause and effect relationship if changes to the explanatory variable affected the response variable, where the explanatory variable is the cause and the response variable would be the effect.

Step six, conclude whether or not the tests showed that the prediction was correct or incorrect. In this case, conclude whether or not taking the medication made you feel better or whether it didn't. While a conclusion may or may not indicate a cause and effect relationship between two things, the results are not absolute. If the environment or things being tested were to change, then the results may no longer be valid, and new tests should be conducted. So in a case like this, maybe you were taking more than one medication for the cold. And maybe the second medication was the one affecting it, and not necessarily the first one, or the one you were testing.

Step seven, revise your guess if the prediction was wrong and start from step two. Or if the prediction looks plausible, start testing again from step four to verify your results. In general, it is a good idea to conduct multiple tests, as doing so helps to confirm the prediction when multiple tests show similar results. Try it again. Take the medication for another few days. See if it works. If not, scrap the idea. Go back and try a second medication and test that one to see if it makes a difference.

And then step eight, the final step. Once satisfied, report the findings so that others can review and possibly test it themselves. And so let's use other example here besides the medication and the cold symptoms. Let's say you're interested in getting to work a little bit earlier than you have been. So say you've been running late and your boss is kind of frowning at you every time you walk in the door five minutes late.

And so in order to change that, you're interested in setting your alarm clock a little bit earlier to see if that makes a difference in terms of how late you are to work. And so in the case like this, by setting the alarm clock just a few minutes earlier every day, you can determine whether or not you would get to work earlier as a result.

In this instance, it would be important to use the experimental method rather than just an observational approach. As you would be able to determine just how much earlier you had to get up in order to get to work earlier, rather than simply just noticing a trend or maybe getting to work early by chance. The experimental method helps us realize if there is a strong cause and effect relationship between two things. Whereas just observing still leaves room for speculation on whether or not two things actually do have a cause and effect relationship.

Sometimes we come across explanations of experiments that have already been done, such as studies that have been conducted on new over-the-counter drugs, or surveys regarding how many people consider a particular politician trustworthy. It can be useful in better understanding the experiment and its results if one can recognize the explanatory and response variables.

So let's take a look at a couple different examples here to see if we can identify explanatory and response variables. Suppose there's a television commercial on that says taking a particular vitamin will assist with weight loss. Well, in this case, what's the explanatory variable? Taking the vitamin. What's the response variable? Your weight, whether or not you lose weight or not.

Second example, what about television viewing and the relationship it has with one's grades? In this case, we would suggest the explanatory variable would be how many hours of television somebody watches. Whereas the response variable would be their grade or grade point average. And so these are relatively simple things that we can look at to get a sense for what the explanatory and response variables actually are.

So let's go back to our objective just to make sure that we covered it. Our objective was to be able to identify independent and dependent variables, which we did. We went through several different examples talking about how one variable affects another one. We also discussed all eight steps of the experimental method to give us a sense for how that differs from the observational method. So again, my name is Dan Laub. And hopefully, you got some value from this lesson.

Terms to Know
Explanatory Variable

The quantity varied by the person conducting an experiment.

Response Variable

The quantity whose change is observed as a result of varying the independent variable.