- Hi, everybody. In this lesson, we're going to talk about what and the why of statistics to get us started. We're going to explore what statistics and data are. We're also going to talk about the concept of independent and dependent variables. And lastly, we'll explore the concept of levels of measurement. So statistics refer to procedures that allow social scientists and everyday people to basically organize data, to use it for analysis, and to be able to come to conclusions using that data. So for example, something as simple as the percentage of Americans who are getting enough sleep is an example of a statistic. If you have ever wondered about crime rates in your area, that is also an example of statistical analysis. And then, lastly, the gender breakdown of your workplace. You can think about it in your head. How is your workplace split up in terms of gender? Even something like that can be referred to as statistics. So as you can see, data and statistics are all around us. Data typically comes from collecting responses in survey questions. And we use those responses and that data to answer questions about the world and test theories. This all leads into the research process. The research process is a way to test our ideas. So it all starts off by asking a good research question. A good research question is one that's measurable, and it explains the purpose of our study. After we have a good research question, we can formulate a hypothesis. A hypothesis is basically your thoughts on what you're going to find once you start your study. After that, you can start collecting your data. And in terms of this class, it's typically going to involve responses from survey respondents. So we typically look at survey data in this class. And then we're going to analyze the data. So we can take the information, organize it, and come to conclusions about our results. Lastly, we evaluate what our results are in terms of our hypothesis. Did the result support our ideas? Or were we proven wrong about our ideas, and perhaps we need to look in another direction? Let's talk a little bit about variables before we jump into independent and dependent variables. Put simply, a variable is a characteristic that measures from one person-- that varies from one person to the next. So an example of this would be age. So what is your age? That's something that varies from one person to the next. Number of children. Some people have zero children. Some people have one, two, three. So that's something that varies. But also, things like views on death penalty, or if you've ever committed a crime. Notice that views on death penalty refer to an opinion. That's a variable. And ever committed a crime, that refers to a behavior. So behaviors, opinions, and characteristics can all form variables because they vary from one person to the next. In most research studies, you're going to have an independent and a dependent variable. The independent variable is the one that we think is causing changes. So an independent variable example would be studying and good grades. The independent variable is studying. Studying is the IV, or the independent variable. And it is said to lead to good grades-- the dependent variable. Next up, we're going to talk a little bit about the levels of measurement. So first up, we have a nominal level of measurement. Our variables are split up into different levels of measurement. The lowest level is known as the nominal level of measurement. And in this level of measurement, you have variables that are made up of categories or answer choices that cannot be ranked. So for example, the type of transportation that you use-- car, bus, bike, or other. Notice that these choices have no inherent order to them. You can't say that one has less or more transportation than the other. You can also think of this as just having names for things. So what type of transportation? And we have the names of a car, a bus, a bike, or other. So there's not really a ranking order to these categories at all. Another example is gender. Gender is just simply a characteristic of a person or an identity. And there's no really low or high amounts of gender. There are just different names or different categories of identification, like non-binary, woman, man, or other. Compare this to ordinal levels of measurement. So ordinal levels of measurements are variables that have answer choices where, yes, you do have categories that have a ranking. So these choices can be ranked from low to high, from least to most, from the smallest amounts to the most extreme amounts. So there is some kind of least to most feeling, or what is known as ordering principle to our variable answer choices. So notice that in this case, my variable is political activeness. It is a little vague to measure political activeness. And so we kind of have to come up with categories that sit on a spectrum from low to high. So we have not at all, somewhat active, and very active. Notice that you have a spectrum of low to high political activeness. This is also called a Likert scale. And it's very common in psychology and sociology. Next, we have gun control views. And again, you see a spectrum of attitudes, from we should have less strict gun control, should stay the same, or we should have more strict gun control. So again, ordinal variables have to have categories that you can rank from low to high, or have some kind of ordering principle to them. The last one, interval ratio, also has an ordering principle. You can also rank them from low to high. The only difference is the answer choices are actually going to be individual numerical units. So the answer choices are numbers we're talking about. So, simple example. Number of children. How many children do you have? If you answered zero, that's an individual numerical unit. If you answered one, again, you're answering in a number. So any time that you're answering a question in a number, you know that it's interval ratio. Another example-- hours of work. How many hours of work do you spend each week? 5 hours, 12 hours, 18, 26, 30, 40? So that numerical unit makes it interval ratio. That's how we know. Let's do a quick self-assessment before wrapping things up. What is the independent variable in the following scenario? A researcher concludes that number of close friends and mental health are related. They determine that having close friends decreases the chance of poor mental health. Which one is the independent variable? Is it mental health? Chance of poor mental health? Number of close friends? Or the researcher? Remember that the independent variable is the one that causes the change. And in this case, the researcher is saying, number of close friends seems to cause changes in mental health. Having close friends decreases the chance of poor mental health. So the correct answer is C. Number of close friends. That's the independent variable. Let's do something related to levels of measurement. Which variable is measured at the ordinal level of measurement? Remember that ordinal variables are ranked from low to high, but they are made up of categories, not numbers. So let's give this a shot. Could it be age? Number of children? Approval of President-- disapprove, neutral, approve? Or favorite genre of music-- rock, alternative, rap, hip hop, pop, Latin, or other? Which one of these is made up of categories that you can order from the least amount of the variable to the most amount? So in this case, let's take a look at age. Age is a numerical unit, which makes it interval ratio. Number of children, same thing-- interval ratio. C, approval of President, the variable is approval. And the way that they rank it is on a spectrum from low to high. So this is our correct answer. This is ordinal. So the correct answer, again, is C. D, on the other hand, favorite genre of music, none of these have more or less music than the other. So genres are just simply names of different categories. So it is nominal. Last thing we'll talk about is statistical competency. So knowing statistical procedures and being familiar with them not only helps you get a good grade in this class, but it also helps you figure out which types of data are reliable and which are unreliable, misleading, or just straight out false. Statistics also helps you make better decisions because you're going to become a more well-rounded person that relies not only on qualitative data-- data that comes in the form of words and text-- but quantitative data as well, which is data that comes in the form of numerical information. So understanding statistical procedures can help us navigate everyday life a little bit better because we have that computational understanding, and that conceptual understanding of statistics and numbers. And it also helps us identify reliable information because we understand research methods a little bit better after taking this class. We also get an insight on just how systematic and rigorous research is, and how much effort and critical thinking goes in conducting research and analyzing results. So I hope you found this presentation helpful in our introduction week. And reach out if you have any questions whatsoever.

Purchase answer to see full
attachment