Are you ready to learn how to use SPSS
for your introductory statistics class? You've come to the right place.
My name is Dr. Todd Daniel and this is SPSS for Beginners from the RStats
Institute at Missouri State University. I use SPSS, pretty much on a daily basis, so
I developed this series of videos for people who are brand new to SPSS, to get
you started quickly and easily. This series is intended as an introduction.
Once you're ready to run an analysis for class, you can move on to our other
videos that cover those topics in much greater detail. We are going to start
with the basics where I teach you about the SPSS workspace, how to create
variables, and how to enter data. From there we will move on to simple
statistics, and common statistical tests. So, as you can see, we have a lot to cover.
If you are ready, let's get started with SPSS for Beginners. SPSS is a popular program for
statistical analysis. It's used often in the behavioral sciences, like psychology,
but it works well for lots of other fields.
So why has SPSS become so popular? The biggest strength of SPSS is its user
interface. Now, I might argue that it's biggest strength is actually with data
handling, but its popularity is no doubt because of that user interface, which
relies on drop-down menus, making it very easy to teach and to learn. The common
criticism of SPSS is because of its user interface. Because it makes statistical
analysis simple, it also risks making analysis simplistic. It allows people to
run tests without really knowing what they're doing, and it encourages mindless
analysis. So in this set of videos for beginners, I confess that I am showing
you how to use SPSS a bit mindlessly. But I WILL teach you about the other tests
and interpretations in other videos. So for now, you get comfortable with SPSS
software, and later we are going to learn about theory and research design. The letters SPSS used to stand for
"Statistical Package for the Social Sciences."
SPSS was created for social sciences like psychology, sociology, Health and
Human Services, way back in 1968. In 2009, SPSS was purchased by IBM and because it
is now used in a variety of fields other than the Social Sciences, SPSS is an
acronym like BP, KFC, AOL, BNSF, AT&T, or IBM. The letters no longer stand for anything
and its proper name is now IBM SPSS Statistics. This introduction is for
people who have had little to no experience with SPSS. Start by opening
the SPSS software on your computer. When the splash page pops up, just dismiss it
and then we can get to work. I am going to be using SPSS version 24, but what I
show you will look very familiar even if you're using a version as far back as
SPSS 16. Let's get started with the basics. There are two view modes to SPSS:
there is Data View and Variable View. Data View - which we're in right now - is
basically just a spreadsheet, and this is where you enter numbers. Each row
represents one participant, or subject, or case, and each column is dedicated to a
single variable, or type of measurement. Right now, all of the cells are gray.
Let's just try popping in some numbers. I'll do 1, 2, 3... you'll see that as you
enter a number into a column, that column comes to life. The variable automatically
gets named, and its properties are set by default; however, the name is
VAR00001. That stands for "variable 1". If you type in more numbers...
more variables get defined. Their default names will be VAR00002, VAR00003, VAR00004,
and this can get a little confusing, especially if you have lots of variables
and they're all named almost exactly the same thing. AND also, the default
properties for each variable may not be exactly what you want, so we should learn
how to change them, and we're going to do that in Variable View. To get to Variable
View, click on this tab at the bottom of the screen. We can now see our four
variables. In Variable View, each variable is in a row, and the properties are in
columns. We will begin by changing our variable names. There are a few things
that you need to know about naming variables in SPSS. First of all, you can
name a variable pretty much anything that you want, but you cannot use spaces,
you cannot use most special characters, and the name cannot begin with a number. If you want to use a space ,use an
underscore. CamelCase works equally well where you omit the spaces, but you
capitalize each new word. So let's settle on some more descriptive names. The first
variable is going to be a random identification number that we call "ID."
Next, we will have a variable for "Gender", and then a variable for "Height" and one
more for "Weight." Now, variable names are good, but
sometimes you want something even more descriptive, and in that case, add a label.
Labels allow you to describe your variable with much more detail. For
example, ID is a "random identification number," and this is "height in inches," and
"weight in pounds." Another important property is Type. The default type is
Numeric, because we're using numbers, but you can change the Type to Dates, if
you're recording dates, or to Currency amounts. A String variable includes
letters or words in the data, but honestly, for most of what we're going to
be doing analyzing data, the numeric variable is going to be exactly what you
want. Probably the only other property that you need right now is
Measure. Measure specifies the scale of measurement that you will be using. Any statistics textbook will tell you that there are four scales of
measurement: nominal, ordinal, interval, and ratio. In SPSS, measure nominal is
called "nominal." Ordinal it's called "ordinal." But
interval and ratio are both called "scale." Both of these variables are nominal.
We'll leave these two set to scale. I will quickly mention some other properties.
Width specifies how wide or narrow the string variable entries can be. We won't
be using string variables, so we can safely ignore that. Decimals specifies
how many decimal places will be shown. Two decimals is the default, but we can
increase or decrease them. The nominal variables don't need decimals because
they are whole numbers. Scale variables we can leave set to two decimals. Column
specifies how wide or narrow the columns will appear in Data View. Change the
column value to 25... and the column becomes wider. You can also adjust the
width of the columns by hand in Data View...and you will see those changes
reflected back in Variable View. Align helps you to set your data to be left
justified, right justified, or centered. I like to leave all the numeric variables
right justified. There are some other properties like Values, Missing, and Role,
which are useful once we've learned the basics. So here is what you need to know:
you can create a new variable simply by typing a new name. It's that easy. Give it
a label, adjust the decimals, and set the measure. Leave all of the
other settings at their default. And if you want to delete a variable, select it
and then choose Clear. So now you know some basics for SPSS, how to create a
variable, and adjust its settings. Next, we're going to begin plugging in numbers
and running some simple analyses.