Some SPSS procedures
Descriptive statistics:
Analyse → Descriptive Statistics→ Explore
Quantitative variables - The Explore procedure produces summary statistics and graphical displays,
either for all of your cases or separately for groups of cases. There are a lot of other procedures for
obtaining statistics such as the arithmetic mean, the median, etc:
Analyse → Reports→ Summarize cases (includes the geometric mean)
Analyse → Descriptive Statistics→ Frequencies
Analyse → Descriptive Statistics → Descriptives …
Analyse → Descriptive Statistics→ Frequencies
Qualitative variables – Frequencies.
Analyse → Descriptive Statistics→ Crosstabs and the conditional distribution can be obtained in the Cells
sub-dialogue box by checking Column or Row
Two-way tables
Graphs → Legacy Dialogs→ Histogram
Graphs → Legacy Dialogs→ Bar and Pie
Graphs → Legacy Dialogs→ BoxPlot or Analyse → Descriptive Statistics→ Explore
Graphs → Legacy Dialogs→ Error bar …
Graphs → Legacy Dialogs→ Scatterplot
To add a reference line from an equation: Options → Reference line from equation
You can customize the equation used to draw a reference line from an equation (use ** for raised to the
power, exp( ) for e raised to the power n, where e is the base of the natural logarithms, etc). More
detailed information about the Equation Syntax can be found in Help from SPSS.
Examples: N=967,8e0,165t : 967,8*exp(0,165*x); Comprimento=2,134 Largura1,5: 2,134*x**1,5;
y=4ln(x): 4*log(x)
Data file handling
Data → Split File→ Organize output by groups. (Deactivate: Data → Split File→Analyse all cases)
Split File splits the data file into separate groups for analysis based on the values of one or more
grouping variables.
Data -> Select Cases->If condition is satisfied ->If…
Select Cases provides several methods for selecting a subgroup of cases based on criteria that include
variables and complex expressions
Data → Weight cases
Weight Cases gives cases different weights (by simulated replication) for statistical analysis. The values
of the weighting variable should indicate the number of observations represented by single cases in your
data file.
Transform → Visual Binning
Transform → Compute variable
Transform → Recode into different variable
Used to generate new variables.
Biostatistics I - Master Degree Public Health 2016/2017 1/2
Some SPSS procedures
Inference about means
Analyse → Compare means → One Sample t test and Analyse → Descriptive Statistics→ Explore
(confidence interval)
Analyse → Compare means → Paired Sample t test
Analyse → Compare means → Independent Sample t test
Inference about a proportion
Analyse → NonParametric tests→ One Sample
The Objective tab allows you to specify a Custom analysis.
The Fields tab specifies which fields should be tested.
In the Settings tab select Compare observed binary … (Binomial test)
Option: specify Hypothesized proportion, Confidence Interval – Clopper-Pearson, Specify success
values
Output: to display the confidence interval, select the first table and then: View ->Confidence Interval
Summary View
Chi-squared test
Analyse → Descriptive Statistics → Crosstabs and then click the Statistics button and select Chi-Square
MCNemar test
Analyse → Descriptive Statistics → Crosstabs and then click the Statistics button and select McNemar
Linear Regression
Analyse→ Regression → Linear
Click Statistics and check the fields Estimates, Confidence intervals and Model fit
In Save you can select Standardized Residuals
One-Way Analysis of Variance (ANOVA)
Analyse → Compare Means → One-Way ANOVA
ANOVA (One-way, two-way and others)
Analyse → General Linear Model → Univariate
In Options you can select Descriptives
In Save you can select Standardized Residuals
In Post Hoc you can select Tukey, LSD or Sheffe
In Plots you can generate profile plots
etc.
Biostatistics I - Master Degree Public Health 2016/2017 2/2
