Introduction to Research Design Speaker: Hoàng Thị Hạnh
Dec 02, 2014
Introduction to Research Design
Speaker: Hoàng Thị Hạnh
Acknowledgement
Slides and content consultation: Hà Thanh
Provision of extra materials: Đặng Trang
Phùng Hà ThanhPhùng Hà Thanh
Research
A systematic investigation into reality to gain knowledge
Phùng Hà ThanhPhùng Hà Thanh
Phùng Hà ThanhPhùng Hà Thanh
Contents
Definition & Elements1
Sampling2
Common Research Methods3
Phùng Hà ThanhPhùng Hà Thanh
Research design
a detailed plan outlining how a research project will be conducted
Phùng Hà ThanhPhùng Hà Thanh
Research design
a plan of what data to gather, from whom, how and when to collect the data, and how to analyze the data obtained (conditions and procedures)
secondary primary
Sources of information/data
RealityGeneral sources: Newspapers,
magazines, the InternetSecondary sources: Textbooks,
reviews, critiquesPrimary: Journal articles, research
reports
Phùng Hà ThanhPhùng Hà Thanh
Phùng Hà ThanhPhùng Hà Thanh
Basic elements of research design
What data would we want, and from what sources?
How would we collect the data?
How would we analyzed the data?
1. SAMPLING
2. DATA COLLECTION
3. DATA ANALYSIS
Phùng Hà ThanhPhùng Hà Thanh
Research methods
procedures used to collect and analyze data
1. SAMPLING
2. DATA COLLECTION
3. DATA ANALYSIS
Research DesignResearch Design
Research methodsResearch methods
Sampling strategiesSampling strategies
Phùng Hà ThanhPhùng Hà Thanh
Contents
Definition & Elements1
Sampling2
Common Research Methods3
Common Research Designs4
Phùng Hà ThanhPhùng Hà Thanh
Problem
“If you had it to do over again, would you have children?”70% of the nearly 10,000 respondents said that they would not have children if they could make the choice to be a parent again.
Phùng Hà ThanhPhùng Hà Thanh
Problem
However, when a statistically designed opinion poll on the same issue a few months later was conducted, it was reported that 91% of parents said that they would have children again! (Mooore & McCabe, 1993, p. 248)
Phùng Hà ThanhPhùng Hà Thanh
Sampling
the process of selecting subjects for research
the process of selecting a number of people/things- a sample- from a population (the group to whom we want to generalize findings) not feasible to survey the entire group of interest (the
population) select a subgroup (a sample). the sample must be similar to the population in
important ways if the results of the study are intended to apply to (be representative of) that population.
Phùng Hà ThanhPhùng Hà Thanh
PROBABILITY-BASED SAMPLING
Simple Random SamplingSystematic SamplingStratified Sampling
Proportional stratified sampling Disproportional stratified sampling
Cluster SamplingMultistage Sampling
Phùng Hà ThanhPhùng Hà Thanh
Phùng Hà ThanhPhùng Hà Thanh
Non-probability sampling
PURPOSIVE/JUDGEMENTAL
CONVENIENCE
Based on availability
Based on knowledge of a population, its elements, & the purpose of the study (selecting people who would be ‘good’ informants).
Phùng Hà ThanhPhùng Hà Thanh
Contents
Definition & Elements1
Sampling2
Common Research Methods3
Common research methods
Survey: a means of gathering information about the characteristics, actions, or opinions of a large group of people through self-report
Case study: an in-depth investigation/study of a single individual, group, incident, or community
Phùng Hà ThanhPhùng Hà Thanh
Survey research
To produce quantitative descriptions of some aspects of a large population
Unlike most approaches that involve direct observation of behavior, surveys rely on self reports.
Main way of data collection: asking people structured and predefined questions.
Information is generally collected about a fraction of the study population- a sample- but in such a way as to be able to generalize the findings to the populationAhluwalia (2002)Ahluwalia (2002)
Sir Francis Galton (1822 – 1911)
author of over 340 papers and books
creator and promoter of some key statistical concepts
the first to apply statistical methods to the study of human differences and inheritance of intelligence
introducer of the use of questionnaires and surveys for collecting data on human communities
Sir Francis Galton (1822 – 1911)
Francis Galton's surprise: the crowd at a county fair accurately guessed the weight of an ox when their individual guesses were averaged the average was closer to the ox's true weight
than the estimates of most crowd members, and also closer than any of the separate estimates made by cattle experts
The wisdom of crowds
Argument: the aggregation of information in groups result in decisions that are often better than could have been made by any single member of the group.
Evidence: numerous case studies and anecdotes (several fields, primarily economics and psychology.
Phùng Hà ThanhPhùng Hà Thanh
Data collection methods
QuestionnaireInterviewObservation
field observation testing observation of documents or/and artifacts
Questionnaires
A series of questions or statements to which they are to react either by writing out their answers or selecting from among existing answers
Aiming to find facts, bahaviours, attitudes, opinions, beliefs, interests, and values
Practice: Examining your own research topics/questions. Can you use questionnaire as data collection instrument for them?
Advantages
Efficiency in terms of researcher time researcher effort financial resources
Disadvantages
Simplicity & superficiality of answersUnreliable and unmotivated
respondentsLittle or no opportunity to correct the
respondent’s mistakesSocial desirability (saying vs real to
sensitive questions)Self-deceptionAcquiescence bias (AQ – yessayers)Halo effectFatigue effect
“Questionnaires can be designed to minimize, but not eliminate, dishonest, and careless reporting.”
(Aiken, 1997, p.58)
Qualities of Good Questionnaires
Have a clear purpose or construct(s) Be valid and reliable Be simple in terms of
interface/presentation Be appropriate for the population
• Content – can the respondent answer?• Language – will the respondent understand
Be efficient in gathering information
Developing the Purpose
Think about what, specifically, you want to Think about what, specifically, you want to know, why a questionnaire is appropriate, know, why a questionnaire is appropriate, and what you want to do with the data.and what you want to do with the data.
Creating the Conceptual Framework
a multi-step process with a great deal of brain storming.
Step 1: List all the questions/areas you might want Step 1: List all the questions/areas you might want to know/Pool ideas from focus groupto know/Pool ideas from focus groupStep 2: Organize these questions into categories Step 2: Organize these questions into categories and subcategoriesand subcategories
Step 3: Define these categoriesStep 3: Define these categories
Step 4: Make sure that you are asking items that Step 4: Make sure that you are asking items that will provide enough data to fully answer your will provide enough data to fully answer your research questions.research questions.
Step 1: Brainstorming
Don’t limit yourself. This is the time for you to say “wouldn’t it be nice to know…”
At this phase, don’t focus on the At this phase, don’t focus on the wording of your questions. Just write wording of your questions. Just write questions.questions.
Work collaboratively with friends and Work collaboratively with friends and consult supervisorsconsult supervisors
Step 2: Organize Questions into Categories
Group similar questions and think about what these questions are asking.
This process may spark even more This process may spark even more questions and categories. If so, add questions and categories. If so, add them to your list.them to your list.
Step 3: Define these Categories
Think about how you can break down your large topic in meaningful categories. Define each category.
Step 4: Check Your Measurements
Ask yourself if you have enough questions to measure each category.
This step will last until the questionnaire is complete.
Always keep in mind the your research question and see the purpose of each question item
Rules about item wording
Aim for short and simple items - only one complete thought
Use simple and natural language Avoid ambiguous or loaded (leading)
words and sentencesAvoid negative constructionsAvoid double-barrelled questionsInclude both positively and negatively
worded items
Phùng Hà ThanhPhùng Hà Thanh
Contents
Qualities of Good QuestionnairesQualities of Good Questionnaires11
Process of Questionnaire DevelopmentProcess of Questionnaire Development22
Develop the Purpose
Create the Conceptual Create the Conceptual FrameworkFramework
Write the QuestionsWrite the Questions
Design the QuestionnaireDesign the Questionnaire
General Features
LengthLayout (booklet format, appropriate
density, orderly layout, paper quality, sequence marking)
Sensitive topics and anonymity
Parts of a Questionnaire
TitleInstruction (general & specific)Questionnaire ItemsAdditional InformationFinal “thank you”
PilotingAdministering
Phùng Hà ThanhPhùng Hà Thanh
Case study
an in-depth investigation/study of a single individual, group, incident, or community
Purposive sampling: selecting cases must be done so as to maximize what can be learned, in the period of time available for the study
Multiple cases – replicatory, not sampled
Phùng Hà ThanhPhùng Hà Thanh
Critical caseGeneralization - Falsification – critical reflexivity Black swan
evidence
Information-oriented sampling: exploration and description
Phùng Hà ThanhPhùng Hà Thanh
Practice
Topics for case studies?
Phùng Hà ThanhPhùng Hà Thanh
Data collection
Participant and direct observationsInterviewsTests Examinations of records, and
collections of writing samplesJournals, notes Multiple sources of data for
triangulation
Phùng Hà ThanhPhùng Hà Thanh
Interview
Unstructured: guided by response of the interviewees
Semi-structured: Structured: lists of pre-determined
questions
Phùng Hà ThanhPhùng Hà Thanh
Semi-structured interview
giving the interviewee a degree of power and control over the course of the interview
giving the interviewer a greater deal of flexibility
giving one privileged access to other people’s lives
Phùng Hà ThanhPhùng Hà Thanh
Purdue University Writing LabPurdue University Writing Lab
Setting up the Interview
Contact the potential interviewee in advance
Be sure that you ask for the interview. This person is doing you a favor
Arrange a specific time and place, and let the interviewee know how much time it will take
Identify the topic that you will be discussing during the interview
Purdue University Writing LabPurdue University Writing Lab
Preparing for the interview
Be sure to write out a list of questions in advance
Find out whatever information you can about the person you’re interviewing
Decide which questions are highest priority if time runs short
Decide what your goals are for the interview
Purdue University Writing LabPurdue University Writing Lab
Coming up with Questions
Ask yourself: “What is it that I need to know?
Write down a list of things that you are hoping to find out
Write a list of questions that you think will lead to these answers
Check the questions carefully to see if the wording could be offensive to your interviewee
Question wording
Open-endedNeutral – avoiding evocative,
judgmental, leading, loadedOne at a timeClearCareful with “why”
Phùng Hà ThanhPhùng Hà Thanh
Carrying Out Interview
Tape record if possible – with permissionAttempt to remain as neutral as possibleEncourage responses: reflecting, asking
further questions, clarification, elaboration
Summarizing or paraphrasing to verify your understanding
Be careful about the appearance when note taking
Don't lose control of the interview
Phùng Hà ThanhPhùng Hà Thanh
Practice
A successful learner’s reading practice
RQ: 1. How does a successful learner practice reading in terms of amount, sources and strategies? 2. What motivates this successful learner?
Phùng Hà ThanhPhùng Hà Thanh
Phùng Hà ThanhPhùng Hà Thanh
Data analysis methods
Concept-based analysis/Content analysiscategorization, classification and analysis
according to selected conceptual frameworks
Pattern matching
Data analysis
Show that the analysis relied on all the relevant evidence
Include all major rival interpretations in the analysis
Address the most significant aspect of the case study
Use the researcher's prior, expert knowledge to further the analysis
Phùng Hà ThanhPhùng Hà Thanh