Cross Tables, Bivariate
and Multivariate Graphics
PhD Özgür Tosun
What is a Marginal Table?
is a table format presentation of the distribution of a single
variable based on n observations
tables generally consist of
◦frequency and percentage for qualitative variables
◦central tendency and dispersion measures for quantitative
variables
Gender:
• 2 categories
• Qualitative Data
Age of mother:
• Continous
• Quantitative data
Birth condition:
• 2 categories
• Qualitative Data
Cross Table
enables showing two or more
variables simultanously in table format
best way to include sub-group descriptive statistics
is good for demonstrating
possible relationships among variables
In these tables, generally two kinds of variables are shown:
• Dependent (output) variable
• Independent (input) variable The easiest way to identify the
independent variable and dependent variable is to ask the question:
Which variable depends on which?
Misreading the Table
it is important to correctly read the information given in a table
although the original data do not
change at all, tables can be arranged in several different views
looking at the table does not
necessarily show the reader about
possible relationships among variables
◦in order to decide on the existance of
relationship, «statistical hypothesis testing»
is required
ANOTHER EXAMPLE
WITH DIFFERENT DATA
MULTIVARIATE TABLES & CHARTS
Scatter Plot
illustrates the relationship between two characteristics when both are measured on a numerical scale
◦characteristic hypothesized to explain or predict or the one that occurs first
(independent) is placed on x-axis.
◦characteristic or outcome to be explained or predicted or one that occurs second (dependent) is placed on y-axis
each observation is represented by a small circle
Blood pressures vs Age
Which one is supposed to depend on the other variable?
◦Blood pressure determines age
Or
◦Age determines blood pressure