data analysis.pptx

Objectives
• Difference between qualitative and
quantitative data and analysis.
• Analyze data gathered from questionnaires.
• Analyze data gathered from interviews.
• Analyze data gathered from observation
studies.
• Software packages for data analysis.
• Pitfalls in data analysis, interpretation, and
presentation.
• Presenting your findings.

Qualitative and quantitative
• Quantitative: numbers,
translated into numbers.
• Qualitative: difficult to
express in numerical terms in a
sensible fashion.
Be careful in translating
qualitative data into
quantitative data.

Simple quantitative analysis
Simple quantitative analysis techniques:
• Percentages: for standardizing data
(compare large sets of data).
• Averages:
Mean: commonly understood average.
Median: middle value of the data.
Mode: most commonly occurring number.
Initial Analysis: finding averages, outliers,
depict any patterns from the graphical
representation of data on a spreadsheet.

Initial analysis example: data
gathering
• Evaluation study
of an e-commerce
website: identify
transactions’ difficulties
faced by users.
• Data gathering
methods:
 Questionnaires.
 Observation of a
controlled task.
 data logging.

Initial analysis example:
Visualization of data
Number of errors made
0
0.5
1
1.5
2
2.5
3
3.5
4
4.5
1 3 5 7 9 11 13 15 17
User
Number
of
errors
made
Internetuse
< once a day
once a day
once a week
2 or 3 times a week
once a month

Initial analysis example:
Visualization of data
0
1
2
3
4
5
6
7
8
9
10
0 5 10 15 20
Number
of
errors
made
User
Numberoferrors made • Outlier:
Removed from the
larger data set since it
distorts the general
patterns.
Interesting case for
further analysis.

Activity(1)
• The data in the table represents the time
taken by a group of users to select and buy
an item from an online shopping website.

Activity(2)
Further investigation:
• The values for users
N(24) and S(26) are
higher than the others.
• Trends:
- Users at the beginning
of the testing time
performed faster than
those towards the end of
the testing.
- O is at the end of the
testing but performed

How question design affects
data analysis

Comparing two products: 2
Phone designs

Initial analysis from data logs (1)
• Research question: investigate how
effective Massively Multiplayer Online
Role-Playing Games (MMORPGs) are at
encouraging interactivity between users.
• Data: data logs and video recordings of
players interactions in SWG.
• Ethnography study to identify the
locations heavily used by players.

Initial analysis from data logs (2)

• Qualitative analysis –expresses the nature
of elements and is represented as themes,
patterns, stories
• Qualitative data: difficult to measure
sensibly as numbers.
e.g. counting number of words to measure dissatisfaction
.
Simple Qualitative Analysis

• -The first step is to gain an overall
impression of the data and start looking for
patterns.
- Next comes more detailed work using
structured frameworks or theories to
support the investigation.
- Patterns may relate to a variety of aspects.
e.g. behavior, user groups, places or situations where
certain events happen.

• In terms of structure:
- Unstructured: Not directed by a script. Rich but
not replicable.
e.g. video material.
- Structured: Tightly scripted. Replicable but may
lack richness.
e.g. questionnaire.
- Semi-structured: Guided by a script but
interesting issues can be explored in more depth.
Provides a good balance between richness and
replicability.
e.g. interviews.

• When Should I Use Qualitative Vs.
Quantitative Research?
http://www.youtube.com/watch?v=63
8W_s5tRq8&feature=related

Three types of qualitative
analysis
1. Identifying recurring patterns and
themes
2. Categorizing data
3. Analyzing critical incidents

1. Identifying recurring patterns
and themes

1. Identifying recurring patterns
and themes
• Emergent from data, dependent on observation
framework if used
• Patterns in Quantitative can be find identified by
graphical representation but for Qualitative, requires
researcher to be immersed in data
- Studying the data
- Focusing on the study goals
- Keeping clear records of the analysis as it progresses and
close description of themes or patterns that are
emerging.
- e.g. Box 8.4, Themes in European culture.

2. Categorizing data
• Can be at a high level of detail such as identifying stories
or themes OR at a fine level of detail in which each word,
phrase or gesture is analyzed.
• Most challenging aspects :
1. Determining meaningful categories that are orthogonal
(do not overlap each other in any way).
2. Deciding on the appropriate granularity for the
categories (word, phrase, sentence, or paragraph level).
• The categorization scheme used must be reliable so that
the analysis can be replicated!
- Categorization scheme may be emergent or pre-specified

3. Looking for critical incidents
• It is a flexible set of principles that emerged from work
carried out in the United States Army Air Forces where the
goal was to identify the critical requirements of “good” and
“bad” performance by pilots.
• Two basic principles:
1. Reporting facts regarding behavior is preferable to the
collection of interpretations, ratings and opinions based on
general impressions.
2. Reporting should be limited to those behaviors which
make a significant contribution to the activity
- Helps to focus in on key event
- e.g. Box 8.5, analyzing video material

Tools to support data analysis
• Qualitative data analysis tools
– Categorization and theme-based analysis
• N6 can be used to search a body of text to identify
categories or words for content analysis
• N6 is used to handle large set of data.
– Quantitative analysis of text-based
data- Focuses on the number of
occurrences of words or words with
Similar meanings.

CAQDAS
CAQDAS Networking Project, based at the University
of Surrey (http://caqdas.soc.surrey.ac.uk/)
 support theory-building through the visualization of
relationships between variables that have been coded in the
data.
CAQDAS is useful
– Grounded Theory
– Qualitative Content Analysis
– Ethnography

SPSS
SPSS is Statistical Package for the Social Science
– It is used by market researchers, health researchers,
survey companies, government, education
researchers, marketing organizations and others
Statistical packages, e.g. SPSS
– You can access, manage, and analyze enormous
amounts of data with SPSS.
– SPSS offers statistical test for frequency
distributions, rank correlations, regression analysis,
and cluster analysis

Observer Video-Pro
• The Observer Video-Pro is a system for
collecting, managing, analyzing, and
presenting observational data.
– It integrates The Observer software with time code
and multimedia hardware components.

Observer Video-Pro
The software allows the user to summarize research
findings in numerical, graphical, or multimedia format
http://www.noldus.com/human-behavior-
research/products/the-observer-xt

Theoretical Frameworks for
Qualitative Analysis
• Structuring the analysis of qualitative data
around a theoretical framework can lead
to additional insights that go beyond the
results found from the simple techniques
introduced earlier.
• Three frameworks are discussed in this
section: Grounded theory, Distributed
Cognition, and Activity theory.

Grounded Theory
• Grounded theory aims to develop theories from
systematic analysis and interpretation of empirical
data, i.e. the theory is grounded in the data.
• A grounded theory is developed through
alternating data collection and data analysis:
– Data is first collected and analyzed to identify
categories, then that analysis leads to the need for
further data collection, which is analyzed, and more
data is then collected.
– Data collection is driven by the emerging theory.
– Approach continues until no further insights emerge
and the theory is well developed.

Grounded Theory
• Analysis is mainly to setup Categories.
• Category identification and definition is achieved by
“coding” the data, i.e. marking the data up according
to the emerging categories.
• Coding has three aspects:
– Open coding – the process through which categories are
discovered in the data.
– Axial coding – the process of systematically fleshing out
categories and relating them to their subcategories.
– Selective coding – the process of refining and integrating
categories to form a larger theoretical scheme. Categories
are organized around one central category that forms the
backbone of the theory.

Grounded Theory
• Researchers are encouraged to draw on
their own theoretical backgrounds to help
inform the study, as long as they are alert
to the possibility of unintentional bias.
• Emphasizes the important role of
empirical data in the derivation of theory.

Distributed Cognition
• The people, environment and artifacts are
regarded as one cognitive system
• Focuses on information propagation and
transformation
• A distributed cognition analysis results in
an event-driven description which
emphasizes information and its
propagation through the cognitive system
under study.

• It is recommended to have a deep
understanding of the domain under study.
Even taking steps to learn “the trade”
under study. This could take more time
than a research team has available.
• Alternatively, it is possible to spend a few
weeks immersed in the culture and setting
of a specific domain to become familiar
with it.

• The framework can reveal where
information is being ‘distorted’ resulting in
poor communication or inefficiency.
• The framework can show when different
technologies and the representations
displayed via them are effective at
mediating certain work activities and how
well they are coordinated.

Activity Theory
• Activity theory (AT) is a product of Soviet
psychology that explains human behavior
in terms of our practical activity with the
world.
• AT provides a framework that focuses
analysis around the concept of an ‘activity’
and helps to identify tensions between the
different elements of the system.

Activity Theory
• AT outlines two key models:
– A model that outlines what constitutes an
‘activity’
– A model that outlines the mediating role of
artifacts
• AT models activities in a hierarchical way.
– ‘Activity’ – Provides a minimum meaningful
context for understanding the individual
actions.
– ‘Actions’ – behavior that is characterized by
conscious planning.
– ‘Operations’ – routinized behaviors that
require little conscious attention.

Activity Theory
• Activity is motivated.
• Actions are to accomplish a goal.
• Actions involve operations.

Activity Theory
• AT models artifacts in two ways:
– Physical
– Abstract
• Physical artifacts have physical properties that cause
humans to respond to them as direct objects to be
acted upon. The object usually embody a set of social
practices.
– A spoon
• Abstract artifacts follow the idea of ‘mediation’. A
fundamental characteristic of human development is
the change from a direct mode of acting to one that is
mediated by something else.
– A set of rules or symbols

Presenting Your Findings
• Only make claims that your data supports.
• The best method for presenting your finding
depends on the audience, the purpose of the study,
and the data gathering and analysis techniques
used.
• Graphical representations (numbers, tables,
graphs, etc.) may be appropriate for presenting
your findings.
• Other techniques are:
– Rigorous notations
– Using stories
– Summarizing your findings

Rigorous Notations
• UML is an example of rigorous notation
because it uses notations that have clear
syntax and semantics.

Using Stories
• Used as a basis for constructing scenarios.
• May be employed in three ways:
– Stories told by the participants
– Stories about the participants
– Stories constructed from smaller anecdotes or
repeated patterns that are found in the data.

Summarizing the findings
• Summarizing the data by presenting the
headline findings, overviews, and detailed
content list.
• Numbers and statistical values can be very
valuable in a summary.
– If you found 800 out of 1000 users preferred
design A over design B. This statement would
be a quick indication of your findings.

Summarizing the findings
• Activity
• Consider each of the findings below and
the associated summary statement about
it.
• What is correct or incorrect about each
finding’s statement?

Conclusion
• The kind of data analysis that can be done depends
on the data gathering techniques used.
• Qualitative and quantitative data may be collected
from any of the main data gathering techniques:
interviews, questionnaires, and observation.
• Quantitative data analysis for interaction design
usually involves calculating percentages and
averages.
• There are three different kinds of averages: mean,
mode and median.

Conclusion
• Graphical representations of quantitative
data help in identifying patterns, outliers,
and the overall view of the data.
• Qualitative data analysis may be framed by
theories. Three such theories are grounded
theory, activity theory, and distributed
cognition.

data analysis.pptx

More Related Content

Similar to data analysis.pptx (20)

Recently uploaded (20)

data analysis.pptx