Data collection & Analysis
Module 7
Data collection in quantitative & qualitative research
Data analysis in quantitative & qualitative research
Quan vs. Qual information
"Not everything that counts can be counted."
Source: [Link]
5 (Quantity) Happy (Quality) Kids
Quan vs. Qual research:
differences
Qualitative Quantitative
Purpose To describe a situation, gain insight To measure magnitude-How
to particular practice ... (words) widespread is a practice ...
(numbers)
Format No pre-determined response Pre-determined response
categories categories, standard measures
Sampling Theoretical - Open ended and less Statistical - Random sampling
structured protocols (Flexible)
Tools Depend on interactive interviews Structured data collection
instruments
Data In-depth explanatory data from a Wide breadth of data from large
small sample statistically representative sample
Analysis Draws out patterns from concepts Tests hypotheses, uses data to
and insights support conclusion
Results Produce results that give meaning, Produce results that generalize,
experience and views compare and summarize
Qualitative data collection
methods
Method Brief explanation
Observation The researcher gets close enough to study subjects to observe
(with/without their participation) usually to understand
whether people do what they say they do, and to access tacit
knowledge of subjects
Interview This involves asking questions, listening to and recording
answers from an individual or group on a structured, semi-
structured or unstructured format in an in-depth manner
Focus group Focused (guided by a set of questions) and interactive session
discussion with a group small enough for everyone to have chance to talk
and large enough to provide diversity of opinions
Other methods Participation Action Research (PAR), Free listing, Pile sort,
ranking, life history (biography)
Focus of qualitative questions - experience, opinion,
feelings, knowledge & input
Participation Action Research
(PAR)
With PAR, the communities are included as
“experts” in deciding the focal point of
research (problem conceptualization); and
investigation strategy (research design) to
help the community.
Research is conceived as a tool of
community empowerment.
◦ You as researcher are guide.
◦ This is a substantial departure from traditional
models where research expert objectifies
subjects of research, extracts data, and leaves
without further contact.
When choosing methods,
consider…
The purpose of your evaluation
◦ will the method allow you to gather information that can be
analyzed and presented in a way that will be credible and
useful to you and others?
The respondents
◦ what is the most appropriate method, considering how the
respondents can best be reached, how they might best
respond, literacy, cultural considerations, etc.?
What kind of data will your stakeholders find most
credible and useful
Resources available.
◦ Time, money, and staff to design, implement, and analyze
the information. What can you afford?
Type of information you need.
◦ Numbers, percents, comparisons, stories, examples, etc.
Instrument to collect the
information
What will you use to collect the data?
◦the term “instrument” is the tool on which the data
is actually recorded e.g. a recording sheet,
questionnaire, a video or audio tape, cell phone, etc.
Ifyou select a survey as your method, you
automatically know that you will need a
questionnaire.
But, if you choose a method such as focus
group or interview or observation, think about
what you will use for recording the
information.
Population – the set of ALL
individuals, items, or data e.g. the
Choices total number of people living in a
town or country
When will data be collected?
◦Before and after the program
◦At one time point
◦At various times during the course of the program
◦Continuously through the program
◦Over time – longitudinally
Sampling:Will you collect information from
everyone or use a sample?
A sample is a portion or a
subset of elements taken
from a population.
Source: [Link]
Validity and Reliability
Both Quantitative and Qualitative research
designs seek reliable and valid results.
For example:
◦ Quantitative reliability: data that are consistent
or stable as indicated by the researcher's ability
to replicate the findings.
◦ Qualitative: validity of findings are paramount
so that data are representative of a true and full
picture of constructs under investigation.
Significance is derived socially, not statistically
Definitions
A variable is any measured characteristic or
attribute that differs for different subjects.
◦ Quantitative variables are measured on an ordinal,
interval, or ratio scale, whereas qualitative variables are
measured on a nominal scale.
◦ Continuous variable – a variable which can have any
numerical value e.g. time.
◦ Discrete variable - a variable which can only have whole
numbers (integers) e.g. the number of people in a group.
Data analysis in quan research
Statistical analysis is a mathematical method of
interrogating data.
The general idea of statistical analysis is to
summarize and analyze data so that it is useful
and can inform decision-making.
There are two types of statistics:
◦ Descriptive statistics: numerical summaries of samples
Frequency distribution / normal distribution
◦ Inferential statistics: tests for significant differences
between and among groups
t-test, chi-square, ANOVA, etc.
Descriptive statistics
Measures of central tendency
◦ Present data in form of an average:
Mean =
Mode = most frequently occurring attribute
Median = Middle attribute in the ranked distribution of
observed attribute
Dispersion
◦ Distribution of values around some central value, such an
average.
Range = Distance separating the highest from the lowest
value.
Variance = To describe the variability of the distribution.
Standard deviation = An index of the amount of variability in
a set of data.
Inferential statistics
Inferential statistical analysis is used to understand a
relationship and either generalize or predict based on
this understanding.
The analysis of the simultaneous relationships among
several variables
Inferential statistics are more often analyzed in
specialist statistical packages e.g. SPSS, SAS, etc.
Example: The effects of religious attendance, gender and age.
TABLE 1: Multivariate Relationship: Religious Attendance,
gender, and Age
Age
Gender
Religious
Attendance
Source: General Social Survey, 1972 – 2006, National Opinion Research Center.
What is Qualitative Data
Analysis?
Qualitative data are forms of information gathered in a
non-numeric form e.g. Interview transcript, field notes
(notes taken in the field being studied), video, audio
recordings, images, documents (reports, meeting
minutes, e-mails), etc.
Qualitative data analysis is the range of processes and
procedures whereby we move from the collected
qualitative data into some form of explanation,
understanding or interpretation of the people and
situations we are investigating.
Approaches:
◦ Deductive approach – use your research questions to group the
data and then look for similarities and differences
◦ Inductive approach – use emergent framework to group the
data and then look for relationships
[Link]
[Link]
Types of qualitative analysis
Content analysis
Narrative analysis
Discourse analysis
Framework analysis
Grounded theory
[Link]
Common qualitative software
◦ Atlas ti 6.0 ([Link])
◦ HyperRESEARCH 2.8 ([Link])
◦ Max QDA ([Link])
◦ The Ethnograph 5.08
◦ QSR N6 ([Link])
◦ QSR Nvivo ([Link])
◦ Weft QDA ([Link]/qda)
◦ Open code 3.4 ([Link])