Speaker 1: Hello and welcome to SPSS in 15 minutes. My name is Alexander. The goal of this video is to get you up and running with SPSS to start using it in just under 15 minutes. In this video I'll tackle defining variables, entering data and analyzing your data using descriptive statistics such as frequencies and other summary statistics. So I think we should get started right away. Right so I've opened SPSS. You see that the interface may look similar if you have ever used Microsoft Excel. It looks like a spreadsheet. This spreadsheet is divided into two. There is the data view here which is where you see your actual data and there's the variable view which is where you actually define and edit the questions that you've been asking on your survey or whatever questionnaire that you have. The first thing that you do when you come to SPSS if you don't have data is obviously to bring data in and what I will do is I'll show you how you can create variables and enter data. Right so I have a little questionnaire that I'll be using. The first variable I have on my questionnaire is interview ID. The rule of the variable names is such that you need to not include any spaces in the name and no symbols and or special any special characters. Okay so I'll just say interview ID. The type of the variable, I'll just click the button here, is basically how in which format is the variable is the data of that variable going to come in and for interview ID it's obviously going to be numeric. It's basically just numbers. I'll just go ahead and click okay. All right the width is just the maximum number of characters that will be allowed for this variable when I'm entering data. For this variable eight is quite generous so I'm just going to leave it like that. Decimals, as you have suggested it, it's actually how many decimal places this variable is going to have. For interview IDs, no decimal places. I'll just remove this so that it's zero. Right I'm using the tab key on my keyboard to move to the next. So the label is how the name of this variable should actually appear when I'm doing analysis of which I'm just going to say interview with a space now ID. The values are the list of responses that are allowed for that question. This is mostly for questions that are multiple choice which the interview ID is not going to be multiple choice. Missing is basically values that you are using to refer to missing values like not applicable or if the question was not answered. We're not going to set this in this video. Columns is basically just how wide the column for this data is for this variable is going to be when you go to the data view. Alignment is just whether it should the data should be on left, right, or center. Measurement level is the basically the type of the variable that you're dealing with as regards to how you are measuring it. To make this easily understood, I'll just say that scale variables are variables that are talking about quantities. These are genuinely quantitative variables like how many people are there in your household. You're talking about a number of people which is obviously a quantity. Or how old are you? You're talking about the quantity of time. Or how long is it from here to the next boho, which is the quantity of distance, length, and so on and so forth. That would be scale variables. Ordinal variables are variables that are represented by words but you can say that one category or one value is obviously on top of another value in terms of quantity or in terms of quality. For example, if you think about education levels, somebody who is at secondary school obviously has more education than someone who is at primary school. Or someone who is at tertiary school has more education than someone who is at secondary school, which means the variable education level should definitely be an ordinal variable. While nominal variable, basically this is quite similar to the ordinal variable in that it's represented by words. But then you may not actually be able to say that one category or one value has more of the variable than another value in that variable. For example, gender. Gender, we cannot say that male has more gender or more sex than female. So this variable obviously is not ordinal but rather it's nominal. Other nominal variables examples would be race or tribe or religious affiliation. We cannot say that Christianity or being Christian is more religion than Islam. They're just names of religions. That's where nominal is coming from. So for interview ID, it's neither scale or ordinal because these are just random numbers we are assigning to people. So it's going to be nominal. Let's go to the next one. The next one is going to be the name of this person. So name. Now name cannot be numeric. Obviously people, we have to type as text. So you click the button and you're going to select string. String means text variables. Go ahead and click okay. And then you go ahead to insert the label, which is just going to be name. Are we going to have any values? No, I may not be able to possibly know all the names so that I can fill them beforehand. So this is just going to be an open-ended question. No values, no multiple choice whatsoever. Most of string variables are nominal. So I'll just leave nominal as a default. The next variable is gender. Now gender is going to be a numeric variable, which begs the question, why? Gender, you have male and female, which are words. Yes, but then we don't want people to have problems entering the data, missing spellings and so on. This variable is very important. So what we do is we specify values. So we have numbers that represent the values of gender, which are words. So for example, say one is going to be standing for male and two stand for female. Before we get there, decimals, I'll change this to zero. The label is going to be gender. Then we go to values, click the button, and the value one is going to stand for male. Then you click add. The value two is going to stand for female. And I'll click add. And that's enough. You click okay. That's how you set the values or multiple choice of a variable in SPSS. Then we go to measurement level. If you remember, I just mentioned that gender is a nominal variable, because you cannot say that male has more gender than female. The next variable is going to be age. Age is traditionally a numerical variable. It's quantitative. You may want it to have decimals or leave it like that. The label, I'll just say age. We're not going to put values because it's going to be open-ended. If you're 15 years old, you say 15. If you're 10 years old, you say 10. If you're 50 years old, you said 50. The measurement level, since this variable has a unit of measurement in years, and it's obviously numerical quantitative, you're talking about quantity of time, then it's going to be scale. The last variable is a question. Did you eat rice in the past seven days? So to make the name easier to read, I'll just say rice. The type is going to be numeric. Why? Because the response says yes and no. I'm just going to quote them or give them value. So zero is going to stand for no and one for yes. No decimals. I have to type the whole question this time. So did you eat rice in the past seven days? I have to set the values. So I'll click the button. The values will be zero is no and one is yes. Click add and click okay. So we may debate here on the measurement level. Is this a scale variable? Sorry, is this an ordinal variable or a norm? It cannot be scale because obviously you're talking about no and yes, which are words. But is it nominal? Can we say that yes is more than no? Yes, it is. Or is it nominal? So for this variable, I'm just going to put it at ordinal. Once you do that, it means we have defined all the variables. The next thing is to enter data. The way you have to switch data view to enter the data. Now the way that we enter data is actually very straightforward. It's basically how you enter data in Microsoft Excel. But before we go there, I would say that go ahead and click this button here, which says value labels. That allows us to see especially when the variable has values. So if we type one for male, it should actually show us male instead of showing us one. So you turn that on. Then we'll go ahead and start entering data. So now that we have all the data in, the next step is now to analyze our data. Okay, so to analyze your data, what you're going to do is go to analyze, descriptive statistics. We'll start by looking at frequencies. Frequencies are just counts or a matter of how many of this value do we have. This works much better for variables that don't have too many values. For example, for age, we have too many values of age, too many different values of age. While on gender, we only have a few values of gender. And did you eat rice in the past seven days? We will actually also do have just two values. So when you are running frequencies, I would very much recommend that you run frequencies for variables that have a few categories like gender and did you eat rice in the past seven days. So what I'll do is I'll drag the variable to the right-hand side. I'll drag the other one to the right-hand side as well. The next thing is I want to throw in a few options. I'll go to charts and say I want some bar charts, okay, with frequencies, not percentages. And I'll go ahead and click continue. Make sure that we are displaying frequency tables, especially if the variables are categorical or they are either nominal or ordinal. Go ahead and click okay. And we have our analysis agenda. There are, wow, 10 males and 10 females. It's interesting. And then did you eat rice in the past seven days? We had eight people who did not eat rice and 12 people actually ate rice. This is the charts for males, sorry for gender, and this is the chart for rice. If you want to get this chart or the table in another program like Microsoft Word, all you have to do is right click and copy. In Microsoft Word, you just go ahead and paste. And then you write whatever narrative you want to write. Let's go back to SPSS. How about a variable like age? All right. Okay. Go to analyze descriptive statistics. We'll go back to frequencies. This time I'll reset this, okay, by clicking the reset button. And then I'll throw in the variable age, which is a scale variable or a continuous variable. Now, for continuous variables, you may not want to use frequencies because there's a high probability that you have so many different values of this variable. What you want to do is to probably just go to statistics and say you want probably the mean, the median. Maybe you also want the standard deviation and the range, maybe the minimum and the maximum. You may also want the quartiles and click continue. When it comes to charts, you probably want to have the histogram, which is much, the graph that you may want to actually run for variables that are continuous like age. And you want to show the normal curve on the histogram and click continue. The next thing that you should not forget is to turn off display frequency tables, because again, you have too many values, different values for this variable. So the table, which shows all the values and how many people there are on each of the value, that is not going to work very well. So turn off this and you click K. And now you will see that we have a table of statistics, which show us that the average age is 20 years old, but the median age is 21, which is quite close. The standard deviation for age is 3.5. And it's age ranged from a minimum of 13 and maximum of 28. At the top of the first 25% people is an 18 year old. And the median, which is also known as a 50th percentile is 21. And at 75% of the distribution, you have someone who is 22.75 And we have our histogram, which shows us that our data is roughly normally distributed with more people at the center, which is at the median of 21. And it's basically coming down here and coming down. So this is a very good variable if you want to go ahead and do other advanced analysis. If you want more learning, check out our YouTube channel or our website, uniquemultimedia.net forward slash learning. But for me at this point, it's been under 15 minutes. Thank you.