What are your results?
Jeffrey Barnes
Chapter 9
Now what?
Once you have finished collecting the data
you are faced with the challenge of
making sense of them.
You designed your survey to test your
hypothesis - now you need to find out if
the results support it or not.
Next steps
Organize
Summarize
Present and then
Analyze
Quantitative Data
If you have 20 questionnaires filled out
and each one has 20 questions then you
are looking at 400 bits of information.
This is too much to look at casually and
find patterns and relationships among the
bits at a glance.
The first step is to organize your raw
data
Raw data are figures and information that have
not yet been summarized or interpreted
Organizing the information
The is a great range of computer
software available
Spreadsheet
package - Excel
Statistical packages - Minitab, SPSS
More complicated statistical packages
SAS
Coding (quantitative data)
First step in data analysis is to code or
translate the primary data from their raw
form into forms that can be conveniently
analyzed and managed.
Coding involves using a set of rules to
regroup the data into categories identified
by numbers.
You should code only answers to close
ended data
Coding Examples
What gender are you?
Male
Female
Transgender
In
1
2
3
this case males are coded 1 and
females are coded as 2
Coding Examples
What kind of music do you like?
Rock
Jazz
Classical
Country
Other
No answer
1
2
3
4
5
9
If you gave your respondents these choices
then it is easy to code. If you left space for
them to tell you then you might have many
different categories, you must then choose the
categories and code accordingly.
Data Summary
You must create a data summary
sheet with Excel
This will help organizing
It will also help with calculation of
numeric data
Mean
Standard
deviation
Average
Create
charts
Univariate Analysis
Summarizing and analysis of one variable
Percentage distribution
The percentage of respondents who answered in a
particular way
Example:
you have 20 respondents
You asked them if they smoked (coded yes 1 no 2)
15 of them answered yes (1)
75% of respondents smoke
Frequency Distribution
The number of respondents for each category
Example:
f= 15
Levels of Measurement:
Nominal
Scale
Not all data
that you collect is measured
in the same way.
Nominal Scale
A list of categories to which objects can be
classified. Nominal measurement organizes
data into groups or categories that are
mutually exclusive.
Example:
Sex [male or female]
Type of music listened to [jazz, rock, classical,
other]
Ordinal Scale
A measurement scale that assigns values
to objects based on their ranking with
respect to one another. You can divide
answers into categories BUT you can also
rank the categories (in comparison to
each other)
Example: Answer to following question:
Smoking is dangerous to your health (strongly
Agree Agree- Neutral Disagree- Strongly
Dissagree)
Interval Scale
A measurement scale in which a certain
distance along the scale means the same
thing no matter where on the scale you
are, but where "0" on the scale does not
represent the absence of the thing being
measured.
Examples:
Fahrenheit and Celsius temperature scales.
Ratio Scale (another interval)
A measurement scale in which a certain distance
along the scale means the same thing no matter
where on the scale you are, and where "0" on the
scale represents the absence of the thing being
measured. Thus a "4" on such a scale implies twice
as much of the thing being measured as a "2."
Example: Approximate Household income ( round
from 0.5)
$0
$10,000
$20,000
$30,000
$40,000
Measures of Central Tendency
The term central tendency refers to
the middle value or perhaps a
typical value of the data.
Number that summarizes certain
information about the data.
It is measured using the means,
median or mode.
The MODE
The most frequent value in a distribution.
Example:
In the data set [1,1,1,2,4,3]
The mode is equal to 1
A data set can have more than one mode
Example:
In the data set [1,1, 3,3, 4]
The mode is 1 and 3
The Median
The middle point in the frequency distribution. It
is the point at which half of of the scores are
above and half are below
It is described as the number separating the
higher half of a sample from the lower half.
The median of a finite list of numbers can be
found by arranging all the observations from
lowest value to highest value and picking the
middle one.
It is used to determine the typical value.
The Mean
This is what is commonly known as
the average.
Calculated by adding all the values
of the distribution and then dividing
by the total number of values.
Mean =X
N
