Introduction to Statistical Analysis SPSS Test Summary - IBCOM Year 1

SPSS TEST SUMMARY SHEET

Making a basic frequency table & measures of central tendency

 Analyze  descriptive statistics  Frequencies
 Choose the variable you want to use
 Make sure ‘display frequency tables’ is chosen
 Go to ‘statistics’: choose mean, median, mode, std deviation, etc. and click continue
 Go to ‘charts’: choose anyone, usually bar chart and click continue
 Press ok

How to Select cases (for example, you have a dataset that gives data of various happiness
measures for all countries, but you are only interested in Turkey.)

 Data  select cases (at the bottom)
 Choose ‘If condition is satisfied’ and click ‘If…’
 Choose the variable you’re interested in (e.g. country), put ‘=’ and write whatever the
code number is for the country you’re interested in, which you can see from variable
view, values.

Understanding Quartiles

 Analyze  descriptive statistics  frequencies
 Choose the variable you want to choose
 With huge data, you can skip the frequency table
 In ‘statistics’ choose mean, median, mode, Std deviation, Range, min, max, and
QUARTILES
 To find interquartile range, subtract the 25th percentile from the 75th percentile.
 50% of the data lie between the 25th percentile and the 75th percentile

Scatterplots

 Graphs  legacy dialogs  scatter/dot  simple scatter, click ‘define’
 Put the IV on the x axis and the DV on the y axis, click ok

Calculating Pearson’s r

What is it?

- Measure of the direction & strength of the relationship of two factors in which the data
for both factors are measured on an interval or ratio scale of measurement
- Coefficient of determination (R2): used to measure the proportion of variance of one
factor that can be explained by unknown values of a second factor
- 0-.3 - weak, .3-.6 - moderate .6-.8 - strong .8 - 1 - very strong

, Steps

 Analyze – Correlate – Bivariate
 Pick your two variables
 Pick ‘pearson’ as the Correlation Coefficient, pick ‘two tailed’, check the flag significant
correlations, click ok
 Evaluate the direction and the strength of the correlation

Creating New variables (allows for between group comparison)

 Transform –> recode into DIFFERENT variables
 Choose the variable you want to code into different groups
 Give the new variable a name and click old and new values
 Ex. If you want to divide the components of a variable into three groups, there will be
three components in the new variables. The components will be labeled 1, 2, & 3. If the
old variable had 90 data, then the first group (new value = 1) can have the old values of
lowest to 30, the second group (new value = 2) can have the old value range 31-60, and
the third group (new value = 3) can have the old values of 60 through highest.
 Once you have created the new variable, you can go to variable view and change the
properties from the labels.

Crosstabs (summarize the relationships between the different variables of categorical data.
Shows the proportion of cases in subgroups)

 Analyze  descriptive statistics  crosstabs
 Always put IV in the columns and DV in the rows
 Include column percentages for easy interpretation
 Go to cells, pick ‘Observed’ in counts and ‘column’ in percentages, click continue
 Click ok

One sample t test

What is it?

- Used to compare a mean value measured in a sample to a known value in the population
- Specifically used to test hypotheses concerning a single group mean selected from a
population with an unknown variance
- Does the sample lead us to retain or reject the null hypothesis that was made about the
population?

Steps

 Compare means  one sample t-test
 Choose the variable the hypothesis is about
 Put the null hypothesis value in the test value, click ok
 When analyzing, look at sample mean. Write down t and p (= sig. 2 tailed)