0% found this document useful (0 votes)
59 views53 pages

Analysis Methods

1) The document provides guidance on preparing qualitative and quantitative data for analysis in interdisciplinary agricultural science research. 2) For qualitative data, it recommends organizing data into folders, de-identifying personal information, and immersing yourself in the data to get familiar with it before analysis. 3) For quantitative data, it advises recording metadata on data collection methods, entering or transcribing data accurately, and cleaning the data by checking for errors or inconsistencies. Taking these steps ensures the data is properly structured and documented for rigorous analysis.

Uploaded by

Leo Mord
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
59 views53 pages

Analysis Methods

1) The document provides guidance on preparing qualitative and quantitative data for analysis in interdisciplinary agricultural science research. 2) For qualitative data, it recommends organizing data into folders, de-identifying personal information, and immersing yourself in the data to get familiar with it before analysis. 3) For quantitative data, it advises recording metadata on data collection methods, entering or transcribing data accurately, and cleaning the data by checking for errors or inconsistencies. Taking these steps ensures the data is properly structured and documented for rigorous analysis.

Uploaded by

Leo Mord
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 53

PREPARING FOR DATA ANALYSIS

Judife N. Magallanes, MSc.


PREPARING FOR DATA ANALYSIS
Lesson outcome
By the end of this lesson you will be able to:
 Identify best practice principles for organizing your data for qualitative and
quantitative analysis in interdisciplinary agriculture science research.
Time
 This lesson will take approximately 20 minutes to complete.
GLOSSARY
De-identifying data: removing or altering information from the research data that
can be used to directly identify a research participant - for example, names and
addresses. This protects participants’ privacy.
Iterative: a systematic, repeated sequence of tasks carried out in the same manner
each time. Qualitative data analysis is an immersive, iterative process of reviewing
the data to discover what the data reveals to you.
Transcription: the process of rendering data from another format (e.g. audio or
video interview recording) into text content for analysis.
Descriptive statistics: used to summarise or describe a variable or variables for a
sample of data. For example: a frequency table showing the number of times a
category of a variable appears in the data set.
INTRODUCTION
The lessons in this unit will build on the previous units by showing you how to correctly
interpret and analyze the qualitative and quantitative data that you have collected
from research activities.
1: PREPARING FOR QUALITATIVE ANALYSIS
Document analysis (secondary data) - e.g. of reports, policies, case studies, etc.
Field notes from observations.
Interviews - individual or group interviews (structured, semi-structured, and
unstructured), focus group discussions, and participatory workshops.
Open survey questions - e.g. field & farmer surveys.
This section of the lesson will show the steps to take before undertaking data analysis,
in order organise and prepare the qualitative data you've collected.
Responses to open-ended questions on a field survey
Complete transcripts, images, video or audio from interviews or focus group discussions
Images and outputs from collaborative participatory workshop activities
Text, audio, or video notes from a log or diary
Text, audio or video field notes and observations
The text of a published report
1: ORGANIZE YOUR DATA
Qualitative data is mostly in the form of words or
phrases, typically based on notes taken in interviews,
and from audio and video recordings. It may also
include images from visual participatory workshop
activities such as collaborative mapping.
To prepare for analysis, this mass of information has to
be organized. To do so:
 Set up clearly labelled folders - either physical or digital - in
which you can organise the materials gathered.
 If you have internet access, programs such as Google Drive,
Microsoft Teams, Basecamp and Slack allow you to share files
with other researchers, while being able to access data from
multiple devices.
2: DE-IDENTIFY DATA
De-identifying a participant at the beginning of the
data analysis process is an important ethical
requirement to protect the privacy of research
participants.
 For each respondent, assign code numbers or letters for all
content related to that participant.
 For example: an interview transcript of the first respondent can
be labelled IN01.

Note: you may keep a separate master file with de-


identified information for the duration of the research.
This must be secured - stored on a password protected
computer, or under lock and key in a filing cabinet.
3: GET TO KNOW YOUR DATA
Qualitative analysis involves immersing yourself in the
data completely so that you can interpret and analyse
its meaning accurately.
This is an iterative and often emergent process - your
data collection, interpretation, and analysis may
change during your research project in response to
what is learned in the earlier parts of the study.
Immersing yourself in the data early will help prepare
you for this iterative analysis process.
GUIDELINES FOR QUALITATIVE
ANALYSIS
1. Use your research questions to guide your analysis, but don’t narrow your search
for meaning in your data. Ideas may re-emerge from the data as you refine your
analysis.
2. Read and re-read your data so that you know it very well, (Esterberg, 2002). This
will stop you from only concentrating on the most interesting parts in the data
when you interpret, analyse, and report your findings.
3. Go back and forth from your ideas to the literature. Making sense of your data in
the context of previous findings from other research, and existing theories so you
can build on the scientific knowledge base
2: PREPARING FOR QUANTITATIVE (STATISTICAL)
ANALYSIS
Experiment data from field or on-station trial, or lab experiment
Text, audio or video field notes, measurements, and observations
Responses to close-ended questions on a field or farmer survey
Steps to prepare for quantitative data analysis:
 Record metadata
 Data entry and/or transcription of field observations
 Clean your data
1: RECORD METADATA
Metadata is the information that defines and
describes data.
It is often referred to as data about data or
information about data because it provides data
users with information about the purpose,
processes, and methods involved in the data
collection (abs.gov.au). Having a record of these errors allows you to
make better decisions during analysis. For
There is always the potential for error when we
measure and record our data. example: if one of these data points ends up as
an outlier in your dataset, you can delete it
Adding metadata allows other researchers to
understand the methods used for data collection. because you know it is caused by the error in
This helps them to interpret the data and findings data collection.
we report.
Metadata for individual observations should also Proper scientific practice requires us to keep all
be recorded. This allows you to record any data and only allows the removal of outliers if
errors during data collection - e.g. forgetting to
make a data entry on a particular day or time, there is justification for doing so.
or damaging a sample during data collection.
2: DATA ENTRY, EXPORT, AND/OR TRANSCRIPTION
OF FIELD OBSERVATIONS
Data entry
 If your data was recorded on paper-based data record sheets, it will need to be entered into the
program you will be using for statistical analysis (e.g. Excel, Google Forms, SPSS, etc).
 Enter your data directly into your analysis program, or into a text file that you later import into the
program.

Exporting data
 If you are using an online survey program such as KoboCollect Toolbox, you will probably download
your file for further analysis. You can export data in various formats. Consider which format will be
easiest for you to work with based on the program you will use to analyze the data.

Transcribe audio or video field observations


 If you have audio or video field notes, data, or observations, you may need to transcribe these
recordings to text for analysis. Do this the same way as you would for audio or video field
observations collected in qualitative research.
3: CLEAN YOUR DATA
Data cleaning is the process of Some of the most common errors are:
improving the quality of your data  Inconsistent data entry. For example, data for gender
before conducting any statistical might be entered as “F”, “f”, “fem” “female” or “1”.
analysis. It involves:  Misspellings. Running a frequency table against text
entry responses will allow you to audit all the text that
1. checking that your dataset does respondents typed in.
not contain data entry errors  Out of range values - for example a pH value of 7.0
incorrectly entered as 70. A frequency table will provide
2. that it is set up appropriately for all the possible values that were entered, enabling you
analysis. to correct the error.
 Errors resulting from transferring data between different
Data cleaning is an important step in software, for example from KoboCollect Toolbox to
quantitative analysis and should not Excel.
be skipped.  Duplicate records - for example, two records entered for
one survey. A frequency table including ID would identify
such an error.
Conclusion
In this lesson, you have considered the actions you’ll need to take in order to prepare
your qualitative and quantitative data for analysis.
QUALITATIVE DATA ANALYSIS
Judife N. Magallanes, MSc.
QUALITATIVE DATA ANALYSIS
Lesson outcome
By the end of this lesson you will be able to:
 Apply best practice principles to analyze qualitative data in interdisciplinary
agricultural science research.
Time
 This lesson will take approximately 20 minutes to complete.
INTRODUCTION
In this lesson, you will learn basic coding techniques that you can apply to interpret
and analyze qualitative research data.
Qualitative data analysis is the process of iteratively (systematically and repeatedly)
examining the data in raw or transcribed notes and interviews to identify underlying
themes.
Researchers extract sections of text - words, phrases, sentences, paragraphs, non-
verbal communication - and give each section a label which describes what it is
about. This process is called coding.
Coding is a technique to refine the raw data into themes. Those themes help the
researcher move towards an interpretation or argument related to the research
question.
INTRODUCTION TO QUALITATIVE CODING
There are a number of steps in forming codes. The steps shown here are from Tesch
(1990).
CODING STAGE 1: 1. Get a sense of the whole. When reviewing notes, or listening to recordings or
DISCOVER IDEAS AND MEANING reading transcripts jot down some ideas that emerge.
2. Pick one document (i.e., one interview)—the most interesting one, the shortest, the
one on the top of the pile. Go through it, asking yourself, “What is this about?”
Do not think about the substance of the information but its underlying meaning.
Write your thoughts in the margin.
CODING PHASE 2: 3. When you have completed the first two steps for several participants, make a list
CLUSTER TOPICS, of all topics. Cluster together similar topics. Form these topics into columns,
FIND EMERGING CODES perhaps arrayed as major, unique, and leftover topics.
4. Now take this list and go back to your data. Abbreviate the topics as codes and
write the codes next to the appropriate segments of the text. Try this preliminary
organizing scheme to see if new categories and codes emerge.
CODING PHASE 3: 5. Find the most descriptive wording for your topics and turn them into categories.
TURN CATEGORIES INTO CODES Look for ways of reducing your total list of categories by grouping topics that
relate to each other. Look for relationships between categories.
6. Make a final decision on the abbreviation for each category and alphabetize
these codes.
CODING PHASE 4: 7. Assemble the data material belonging to each category in one place and
PRELIMINARY ANALYSIS perform a preliminary analysis
AND RECODE 8. If necessary, recode your existing data.
Over to you: coding in practice
Research Objective: To examine the capacity development of women as community-based
agricultural leaders
Research question: What are the critical skills, knowledge and processes needed to develop
women’s leadership in rural agricultural settings?
Participant’s response to this picture in the photo-language activity:
Interpreting qualitative data
When you interpret qualitative data, you are trying to put the information in
perspective. You do this by:
 comparing your results to what earlier research results have found;
 your research expectations; or
 the original research objective.
3 GUIDING PRINCIPLES FOR QUALITATIVE
ANALYSIS
1. Identify findings, by examining commonality, examining differences and examining
relationships (Gibson and Brown (2009, pp. 128–129). Trends, patterns, extremes
and outliers can also all be significant and often worth analysing.
2. Be content with simple findings. If the process of creating and modifying
categories and codes has been effective, then identifying findings becomes quite
straightforward.
3. Find ways of expressing trends that avoid the use of numbers. Instead, other
words are found to provide indications of trends within the data.
The qualitative researcher must find their own language with which to identify trends
– findings are often expressed in terms such as ‘some’, ‘the majority’ and ‘a number’.
Conclusion
This lesson has covered the foundations of qualitative data analysis, and how to use
coding techniques to discover meaning in the data, and move towards an
interpretation or argument related to the research question.
There are many different methodologies for qualitative analysis, and coding that are
used for analyzing different types of qualitative data - you can explore some of
these through the lesson resources.
QUANTITATIVE DATA ANALYSIS
Judife N. Magallanes, MSc.
QUANTITATIVE DATA ANALYSIS
Lesson outcome
By the end of this lesson you will be able to:
 Apply best practice principles to analyze quantitative data in
interdisciplinary agriculture science research.
Time
 This lesson will take approximately 20 minutes to complete.
GLOSSARY
Variable: the characteristics or attributes that you are observing, measuring and recording
data for. In biophysical research, common variables include: rainfall, livestock weight, fish
length, crop yield, tree density, etc. In social science research common variables include
gender, age, household income etc.
Dependent variable (outcome variable): when testing for a relationship between pairs of
variables, the dependent variable is the one that is potentially influenced, affected or
predicted by the other variable.
Independent variable (predictor or exposure variable): when testing for a relationship
between pairs of variables, the independent variable is the one that potentially influences,
affects or predicts the other variable.
Distribution: the pattern that the data forms. For example, naturally occurring continuous data
forms a pattern in the shape of a ‘bell’ shape, called the ‘normal distribution’.
QUANTITATIVE DATA
TYPES
In the previous units and lessons you
learnt that 3 types of quantitative
data are commonly collected to
answer research questions in
agriculture science:
Text, audio or video field notes,
measurements, and observations
Responses to close-ended questions
on a field or farmer survey
Experiment data from field or on-
station trial, or lab experiment
QUANTITATIVE DATA TYPES AND STATISTICAL
ANALYSIS METHODS
Field observations and measurements, and survey data will usually be suited to
descriptive statistics.
 Descriptive statistics are used to summarize and describe a variable or variables for a sample of
data - often before doing more complex statistical analysis.
 Frequency tables, bar charts, pie charts, line graphs, histograms, and scatter plot diagrams are
common examples of ways that agricultural researchers may use descriptive statistics to display and
analyze data from field observations, measurements and survey data.

Experiment data involves correlational or causal research (i.e. comparing measures


and identifying statistically significant relationships between the independent and
dependent variable). This is also known as inferential statistics, because you are
using statistical analysis methods to draw conclusions about the larger population
that the sample was taken from.
 Hypothesis testing is a common example of inferential statistics that agricultural researchers use to
test their hypotheses statements using data from field, on-station trials, or lab experiments.
What quantitative analysis methods do you think you might be using
most:
 Descriptive statistics to analyse field observations, measurements, and/or survey
data?
 Inferential statistics to undertake hypothesis testing of experiment data from field,
on-station trials, or lab experiments?
What software will you be using to do the statistical analysis:
 Spreadsheet software (e.g. Excel, or Google Sheets) is commonly used for
descriptive statistics, and simple hypothesis tests of two treatments (e.g. paired
comparison t-test)
 Statistical software such as SPSS or R is often used for more complex tests of more
than two treatments (e.g. ANOVA)
CATEGORICAL VS CONTINUOUS DATA
Categorical data is data which is grouped into categories, such as data for a
‘gender’ or ‘satisfaction level’ variable. Categorical data can be further
classified as:
 nominal when the categories DO NOT have an order - e.g. ‘gender’ variable ; or
 ordinal when the categories DO have an order, - e.g. ‘satisfaction level’ variable.
Continuous data is data which is measured on a continuous numerical scale and
which can take on a large number of possible values, such as data for a
‘weight’, or ‘temperature’ variable. Continuous data can be further classified
as:
 interval when it DOES NOT have an absolute zero, and negative numbers also have meaning
- e.g. ‘temperature in degrees Celsius’ variable; or
 ratio when it DOES have an absolute zero, and negative numbers don’t have meaning - eg.
‘weight’ variable.
Descriptive statistics: categorical data
Measures of central tendency -
summarize the data set by finding the
average, central or typical member. For
example mean, median and mode.
Measures of dispersion - summarize the
data set by finding out how widely it is
spread or dispersed. For example range,
interquartile range, variance and
standard deviation.

Descriptive statistics: continuous data


THE NORMAL
DISTRIBUTION
Quantitative researchers are
usually interested in whether
continuous variables conform
to a normal distribution or
not.

This is a special kind of distribution that large amounts of naturally occurring continuous data often
approximates. The normal distribution is sometimes known as the ‘Bell’ or ‘Gaussian’ curve. It has two key
properties:
1. the mean, median and mode are all equal
2. fixed proportions of the data lie within certain standard deviations (SD) of the mean: 68% within one SD,
95% within two SDs and 99.7% within 3 SDs.
MEAN AND MEDIAN
DISTRIBUTIONS

Means and medians are the most fundamental parameters of a numerical dataset.
 The mean, or average, is the sum of all values over the number of measurements (n).
 If a data set is sorted, the median is the mid value, i.e. where half of the measurements are larger or
smaller than this value.

For a large dataset comparing the means and medians gives an indication that the
data is normally distributed if the average and median are similar or even identical.
For a small dataset you can use statistical procedures to assess if a distribution
follows the required normal distribution before you can apply statistical methods for
data analysis.
When data does not follow a normal distribution
pattern
In almost all natural systems, parameters are
normally distributed. If you find they are not, there
are generally two reasons:
1. Outliers are skewing the data
2. You need to transform the data so that it will
follow a normal distribution.
PARAMETRIC AND NON-PARAMETRIC TESTS
1: Parametric tests - follow a normal distribution, and use the mean and standard
deviations in their calculations. Common parametric tests you may use in your
hypothesis testing include:
 One sample t test
 Paired samples t test
 Independent samples t test
 One-way ANOVA or multi factorial ANOVA
 Correlation or regression analysis
2: Non-parametric tests - don’t require any continuous variables to be normally
distributed. Non-parametric tests use the ordinal position of data instead of the mean
and standard deviation in their calculations.
 One common non-parametric test you may come across is the Mann-Whitney U test. This may be used
as an alternative to the independent samples t test if your data is not normally distributed.
HYPOTHESIS TESTING IN PRACTICE: ONE SAMPLE
T TEST
A one sample t test is used to test whether the sample mean of a continuous variable
is significantly different to a ‘test value’ (some hypothesised value).

For example: field or on-station trials where you are comparing a treatment with a
control.
HYPOTHESIS TESTING IN PRACTICE:
PAIRED SAMPLES T TEST
A paired samples t test is
used to test whether there is a
significant difference between
sample means for continuous
variables for two related
groups.
HYPOTHESIS TESTING IN PRACTICE: INDEPENDENT
SAMPLES T TEST
An independent samples test is used to test whether there is a significant difference in
sample means for a continuous variable for two independent groups.

For example: field or on-station trials with a paired comparison design, where you
are comparing the difference between two treatments in different research sites.
HYPOTHESIS TESTING IN PRACTICE: ONE-WAY
ANOVA
One-way or multi factorial
ANOVA is similar to the
independent samples t test,
but is used when three or
more groups are compared.

For example: field or on-


station trials with a
randomised complete block
design, where you are
comparing the difference
between three or more
treatments.
Conclusion
This lesson has given you an overview of foundational concepts of quantitative data
analysis methods and common statistical methods and tests you are likely to use.
Note there are many more statistical methods and tests for quantitative analysis, that
are used for analyzing different types of quantitative data - you can explore some
of these through the lesson resources.
VISUALIZING AND
COMMUNICATING DATA
Judife N. Magallanes, MSc.
VISUALIZING AND COMMUNICATING DATA
Lesson outcome
By the end of this lesson you will be able to:
 Identify suitable data visualization methods (e.g. graphs, charts, diagrams,
case studies etc) for communicating the results of qualitative and quantitative
data analysis
Time
 This lesson will take approximately 20 minutes to complete.
1: QUALITATIVE DATA VISUALISATION &
COMMUNICATION
As you learned in the previous units and lessons on qualitative methods, the purpose
of qualitative research is to understand participants' experiences, thoughts, feelings,
aspirations, lives and living conditions.

Data collected from qualitative research activities is used by researchers to create


rich and meaningful representations of people's lives in a way that allows others to
fully understand the lives and local living conditions of the participant and their
communities.
REPORTING AND COMMUNICATING QUALITATIVE
RESEARCH
This will depend on the type of data collected, and the research question that researchers are
aiming to answer with the data. For example:
Semi-structured or unstructured interview data from focus group discussions, visual activities,
collaborative mapping activities, value chain analysis, farmer meets or field days are often
most suitably presented as narratives or case studies where participants tell their own stories,
or activities in their lives are documented using images, words, and/or video.
Structured interview data from surveys are often presented as reports. They will typically
include a range of formats, such as:
 key quotes from open survey questions (qualitative data);
 tables, charts and graphs from closed ended questions (quantitative data), analysed and presented using
descriptive statistics such as frequency tables, pie charts, bar charts for either categorical data (e.g. gender,
satisfaction level, education etc), or continuous data (e.g. household income, age range, market price etc).
Visual storytelling to communicate research
 Research makes excellent stories. But when you are communicating about a large, complex, diverse
project, it can be difficult to get the most important message across.
 A targeted, positive story using visual communication, with a specific focus creates more impact than
long, detailed ones.

Telling a story of research impact


To increase impact the story needs to:
 Be newsworthy or significant - in terms of your research question and objectives
 Have a human interest - for example: focused on making farmers, or researchers the hero
 Be well timed
 Social - shows people working together, and is shareable on social media
VISUAL COMMUNICATION FOR EFFECTIVE IMPACT
Tips for using visual communication:
 Create a catalogue of accessible photos (and if possible, videos) with
information and permission from people featured in the images to use
them publicly.
 Consider –is this story best told using photos or video? Or a different
format?
 When taking photos – look at composition, fill the frame, symmetry
focal point, use of lines, frame the subject, layers, and consider point of
view
 When filming videos – have a clean lens, avoid digital zoom, pay
attention to light. Also consider time lapse to show the passage of time,
or slow motion effects to highlight key moments.
2: QUANTITATIVE DATA VISUALISATION &
COMMUNICATION
As you learned in the previous units and lessons on quantitative methods, quantitative
research aims to observe, measure, predict, and control variables and actions in
order to understand how the world works.

Data collected from quantitative research activities is numerical and collected under
controlled conditions for statistical analysis.
REPORTING AND COMMUNICATING QUANTITATIVE
RESEARCH
When communicating and reporting on the findings of this research,
quantitative researchers must decide what formats are most suitable to
communicate and present results. This will depend on the type of data
collected, and the research question that researchers are aiming to answer
with the data. For example:
 Field observations and measurements, and survey data will usually be suited to
descriptive statistics and formats that describe the data visually using frequency
tables, bar charts, pie charts, line graphs, histograms, box plots, scatter plot
diagrams etc.
 Experiments using inferential statistics to test hypothesis statements will report
statistical values such as P values, 𝝰-probability values, and confidence levels that
indicate the level of confidence in the result of the experiment. The values reported
by quantitative researchers will vary depending on the type of statistical test that is
used to test the hypothesis.
COMMUNICATING RESEARCH: KNOW YOUR
TARGET AUDIENCE
Knowing your target audience and the story of why you are communicating to them helps to
decide the format or methods that will be most suitable to communicate with them.
For example: the way you communicate internally to your fellow field researchers will usually
be quite different to the way you communicate with external stakeholders, or your senior
leaders.
Think about the audiences that you will be communicating your research data or results to. For
example, will you be communicating with:
 Other field researchers?
 Senior Researchers?
 Project Leader?

Consider how you might need to adapt the format and way you communicate to suit different
audiences.
Communication etiquette refers to the accepted ways of communicating with others.
Good etiquette helps exchange information effectively while maintaining positive
relationships.
 Decide on level of formality - adjust your tone and language to suit the audience and purpose of
communication.
 Be respectful - listen, acknowledge others, and always offer constructive criticism.
 Consider the timing of your communication.
 Be concise but thorough- proofread all correspondence and reports.
 Use a suitable format to deliver the communication.
Conclusion
This lesson has introduced you to data visualisation methods, and visual storytelling
techniques that you can use to communicate the findings, outcomes and impact of both
qualitative and quantitative data and research.

You've also considered the importance of knowing your target audience, and
adjusting your communication formats and methods to suit the audience - and
maximise the impact of your research communication.

You might also like