Advanced Geographic Research Design

CHAPTER 1 The Selection of a Research Approach

CHAPTER 1 The Selection of a Research Approach

Introducing Key Terms in This Chapter

• Research approaches (or methodologies) are procedures for research that span the steps from broad assumptions to detailed methods of data collection, analysis, and interpretation.
• Keywords:
  • Philosophical assumptions: point of view and a set of beliefs about the research process
  • Research approaches: ≈ research methodology (quantitative, qualitative, and mixed methods)
  • Research designs: the ways of conducting research within a broad methodology
  • Research methods: gathering data, analyzing, and making an interpretation

Three Approaches or Methodologies in Research

• It’s not rigid, distinct categories, opposites, or dichotomies. They represent different ends on a continuum
• A more complete
  • Qualitative research: an approach for exploring and understanding the meaning individuals or groups ascribe to a social or human problem
  • Quantitative research: an approach for testing objective theories by examining the relationship among variables or comparison among groups
  • Mixed methods research: an approach to inquiry involving collecting both quantitative and qualitative data

Three Major Components of a Research Approach

 

Figure 1.1 A Framework for Research—The Interconnection of Worldviews, Design, and Research Methods

 

• Worldview: general philosophical orientation about the world and the nature of research that a researcher brings to a study
  • ≈ a basic set of beliefs that guide action, paradigms, epistemologies, ontologies, or broadly conceived research methodologies

Philosophical Worldviews

• Postpositivism
  • ≈ scientific method, positivist/postpositivist research, empirical science
  • Determination, Reductionism, Empirical observation and measurement, Theory verification
  • Usually used in quantitative research
  • Challenge or prove the traditional notion of the absolute truth of knowledge
  • The problems reflect the need to identify and assess the causes that influence outcomes
  • Develop numeric measures of observations and study the behavior of individuals
• Constructivism
  • Understanding, Multiple participant meanings, Social and historical construction, Theory generation
  • A philosophical position used in qualitative research
  • Individuals seek an understanding of the world in which they live and work and develop subjective meanings of their experiences
  • Participants’ own backgrounds shape their interpretations, and they position themselves
• Transformative
  • Political, Power and justice-oriented, Collaborative, Change oriented
  • Includes groups of critical theorists, participatory action researchers, community-based participatory researchers, Marxists, feminists, and racial and ethnic minorities, etc
  • Research inquiry needs to be intertwined with politics and a political change agenda to confront social oppression at whatever levels it occurs
• Pragmatism
  • Consequences of actions, Problem centered, Pluralistic, Real-world practice-oriented
  • Arises out of actions, situations, and consequences rather than antecedent conditions
  • Emphasize the research problem and question and use all approaches available to understand the problem
  • In mixed methods research, investigators use both quantitative and qualitative data because they provide the best understanding of a research problem
  • Mixed methods studies may include a postmodern turn, a theoretical lens that reflects social justice and political aims

Research Designs

• Types of inquiry within qualitative, quantitative, and mixed methods approaches that provide specific direction for procedures in a research study
• Quantitative
  • Experimental and quasi-experimental, single-subject, nonexperimental, surveys, longitudinal
    • Include structural equation modeling, hierarchical linear modeling, and logistic regression
  • Survey research, experimental research
• Qualitative
  • Descriptive method, Narrative research, Phenomenology, Grounded theory, Ethnography, Case study
  • Descriptive method, narrative research, phenomenological research, grounded theory, ethnography, case studies
• Mixed Methods
  • The collection of both quantitative and qualitative data neutralized the weaknesses of each form of data
  • Convergent mixed methods design, explanatory sequential mixed methods design, exploratory sequential mixed methods design, complex mixed methods design

Research Methods

• Involve the forms of data collection, analysis, and interpretation
• Quantitative
  • Predetermined; Instrument-based questions; Performance data, attitude data, observational data, and census data; Statistical analysis; Statistical interpretation
• Mixed Methods
  • Both predetermined and emerging methods; Both open- and closed-ended questions; Multiple forms of data drawing on all possibilities; Statistical and text analysis; Across databases interpretation
• Qualitative
  • Emerging methods; Open-ended questions; Interview data, observation data, document data, and audiovisual data; Text and image analysis; Themes, patterns, and interpretation

Interconnecting Worldviews, Designs, and Methods

Criteria for Selecting a Research Approach

The Research Problem and Questions

• (a) The identification of factors that influence an outcome, (b) the utility of an intervention, or (c) understanding the best predictors of outcomes, then a quantitative approach is best
• Qualitative research is especially useful when the researcher does not know the important research questions or variables to examine
• A mixed methods design is useful when the quantitative or qualitative approach is inadequate to study a research problem, and the strengths of both quantitative and qualitative research can provide the best understanding

Personal Experiences

Audience

CHAPTER 2 Review of the Literature

CHAPTER 2 Review of the Literature

Introduction

• Search databases, prioritize the importance of literature, write abstracts, and evaluate the quality of the literature

The Research Topic

• Before considering the literature review, identify a topic to study and reflect on whether it is practical and useful to undertake the study

A Draft Title

• Draft a title early in the development to gain insight
• Try completing the sentence starting with “My study is…”
• Begin with straight, uncomplicated thoughts that readers can easily understand
• Consider a title no longer than 10 to 12 words
• Or, pose the topic as a brief question

A Significant Topic

• Reflect on whether the topic can and should be researched
  • Can: willing to serve in the study
  • Should: whether the topic adds to the pool of research knowledge in the literature available on the topic
• Provide a new perspective or angle to the existing literature
  • Studying an unusual location
  • Examining an unusual group of participants
  • Taking an unexpected perspective that reverses an expectation
  • Provide novel means of collecting data (e.g. collect sounds)
  • Present results in unusual ways
  • Study a timely topic
• This sketch includes information about the problem or issue, the central research question, the types of data collected, and the overall significance of the study

The Purpose and Organization of a Literature Review

• Before searching the literature, consider the intent or purpose

Purpose of a Literature Review

• Share the results of other studies
• Provide a framework for establishing the importance of the study and a benchmark for comparing the results with other findings

The Organization of the Literature Review

• General Forms
  • Brief and provide a summary of the major studies addressing the research problem
  • Integrate what others have done and said, criticize previous scholarly works, build bridges between related topics, and identify the central issues in a field
• A Qualitative Structure
  • Use the literature consistent with the assumptions
  • Not prescribe questions needing answers from the researcher’s standpoint
• A Quantitative Structure
  • Include substantial literature at the beginning of a study to provide direction for the research questions or hypotheses
  • Revisit the literature and compare the results
  • An introduction, Topic 1 (about the independent variable), Topic 2 (about the dependent variable), Topic 3 (studies that address both the independent and dependent variables), and a summary
  • Overall, use the literature to introduce and advance a theory, describe related literature, and compare findings
• A Mixed Methods Structure

Steps in Conduction a Literature Review

• Capture, evaluate, and summarize the literature
  • Identify keywords, search the databases, locate about 50 reports, skim reports, begin designing a literature map, draft summaries of the most relevant articles, and assemble the literature review

Searching the Literature

Computer Databases

Types of Literature

• Priority of the Literature
  • Start with broad syntheses of the literature (e.g. encyclopedias)
  • Next, turn to journal articles in respected scientific journals
  • Turn to books
  • Recent conference papers
  • web
• Overall Evaluation Quality

Abstracting the Literature

• Components of an Abstract
  • Mention the problem being addressed
  • State the central purpose or focus of the study
  • Briefly state information about the sample, population, or subjects
  • Review key results related to the proposed study
  • Point out technical and methodological flaws
• Theoretical, Conceptual, and Methodological Abstracts
  • Mention the problem addressed by the article or book
  • Identify the central theme
  • State the major conclusions
• A Literature Map
  • Organize the literature
  • Present a visual summary of the literature**, position** the current researcher’s study within this existing literature, and represent this alignment in a figure
  • Educate readers, take the time necessary, limit the branches, consider the broad topic, revise the map, and draw with a software program

Style Manual Use

• APA style
  • et al. is needed with three or more authors
  • the location of publishers is no longer needed

The Definition of Terms

General Guidelines

• Define a term when it first appears in the proposal
• Write definitions at a specific operational or applied level
• Do not define the terms in everyday language
• Search process
  • Keywords, authors, techniques, reference, study group, journals, publication time, citation index, dissertation, literature review paper

CHAPTER 3 The Use of Theory

CHAPTER 3 The Use of Theory

Introduction

• Quantitative: often test hypotheses derived from theories
• Qualitative: use of theory is more varied

The Varied Use of Theory

• A Prediction of what the researcher expects to find or an inductive or deductive framework
• Identify the theory, Place the theory at the beginning of the article as an a priori framework to guide the questions or hypotheses in the study, Write about the theory, Discuss the studies using the theory, Include a diagram of the theory, Have the theory provide a framework, and return to theory at the end of the study to review its role

Quantitative Theory Use

• Define theory, assess the types of variables and their measurement, introduce the concept of causality, view forms of stating theories, place a theory

Definition of a Theory in Quantitative Research

• specifying how and why the variables and relational statements are interrelated

Variables in Quantitative Research

(source: https://significantlystatistical.wordpress.com/2014/12/12/confounders-mediators-moderators-and-covariates/)

• Independent variables, dependent variables, predictor variables, outcome variables
• intervening or mediating variables (매개 변수): in the middle of dependent and independent variables
• moderating variables (조절 변수): on top
• confounding variables (교란 변수): affect both dependent and independent variables

Testing Causal Claims in Quantitative Research

• Causality means that we would expect variable X to cause variable Y

Stating Theories in Quantitative Research

• interconnected hypotheses (e.g. The higher one’s rank, the greater one’s centrality)
• if-then statements (e.g. if the frequency increases, the degree will increase)
• visual model

Placement of Quantitative Theories

• Use theory deductively and place it toward the beginning

Writing a Quantitative Theoretical Perspective

Qualitative Theory Use

• Deductive explanation, as a theoretical standpoint, and as an endpoint for a study

Variation in Theory Use in Qualitative Research

• Can be a broad and deductive explanation, use a theoretical standpoint

Locating the Theory in Qualitative Research

• Theory occurs in the opening passages

Mixed Methods Theory Use

• It is important to distinguish between the use of a worldview and a theory

Types of Mixed Methods Theory Use

• Discipline-based: drawn from the social, behavioral, or health science literature
• Social justice: e.g. feminist, racial or ethnic, disability, lifestyle research

Importance of a Theory

• Provide a framework, bring together separate investigations, develop a common understanding, provide a prediction, link concepts, pand rovide a visual model

Distinctions Between a Theory and a Worldview

CHAPTER 4

 

CHAPTER 5 The Introduction

CHAPTER 5 The Introduction

Introduction to a Study

• Deficiencies model for an introduction:
  • Describe deficiencies in past research
  • (a) the research problem, (b) evidence from the literature justifying the problem, (c) deficiencies in the evidence, (d) the importance of the problem for the audience

The Importance of Introductions

• Research problem is a problem of issue, whereas research questions raise questions to be answered by gathering and analyzing data

An Abstract for a Study

• The abstract can be the most important single paragraph in a study
  • accurate, non-evaluative (by not adding comments beyond the scope of the research), coherent, readable, concise
• Start with the issue or problem → data sources → study method → ****basic findings → conclusions and implications
• The issue that this study addresses is the lack of women in martial arts competitions. To address this problem, this study will explore the motivation of female athletes in Tae Kwon Do competitions. Interviews with 4 female Tae Kwon Do tournament competitors were conducted to gather data. The interviews were transcribed and analyzed. This data leads to the following 3 themes: social support, self-efficacy, and goal orientation. These themes will be useful for understanding the optimal way to increase motivation in female martial artists. (Witte, 2011, personal communication)

Qualitative, Quantitative, and Mixed Methods Introductions

• Announces a problem and justifies why it needs to be studied
• Quantitative: problems often arise from a need to understand what factors influence an outcome
• Qualitative: problems are described to be understood by exploring a concept or phenomenon
• Mixed methods: can employ either quantitative or qualitative approach

A Model for an Introduction

• ⭐ State the research problem → review evidence from literature justifying the problem → indicate deficiencies in the evidence → state the importance of the problem for audiences

An Illustration of an Introduction

 

Table 5.1 Illustration of an Introduction to a Study With Annotated Markers of Components

 

The Research Problem

• A narrative hook of sufficient generality, encouraging the reader to understate the topic lowers a barrel

Evidence From the Literature Justifying the Problem

• Summarize large, general, and recent studies to justify the study’s importance and create distinctions

Deficiencies in the Evidence

• To locate deficiencies, examine future research sections of the paper
• Discuss how a proposed study will remedy these deficiencies and provide a unique contribution

Importance of the Problem for Audiences

• There are several reasons how the study helps improve practice

CHAPTER 6 The Purpose Statement

CHAPTER 6 The Purpose Statement

Introduction

• The purpose statement establishes the intent or objective of the research study
• Clear, specific, informative

Significance of a Purpose (or Study Aim) Statement

• Indicate why the researcher conducts the study and what the study intends to accomplish
• need to distinguish clearly among the purpose statement, the research problem, and the research questions

 

Figure 6.1 Relationship Among the Problem, the Purpose (Aim), the Research Questions, and the Data

 

A Qualitative Purpose Statement

• Contain information about the central phenomenon (one single concept)
• Use words such as purpose, intent, study aim, objective
• Focus on a single central phenomenon
• Use action verbs (e.g. understand, develop, explore, examine the meaning of, generate, or discover)
• Use neutral words
• Provide a general working definition of the central phenomenon or idea
• Include words denoting the qualitative approach used for data collection
• Mention the participants (e.g. individuals, groups, or organizations)
• Identify the site for the research (e.g. homes, classrooms, or events)
• May delimit the scope of participants or research sites in the study

The purpose (or study aim) of this _____ (qualitative study or more specifically a qualitative approach, such as ethnography, case study, or other type) study is (was? will be?) to _____ (understand? explore? develop? generate? discover?) the _____ (central phenomenon being studied) for _____ (the participants, such as individuals, groups, or organizations) at _____ (research site). At this stage in the research, the _____ (central phenomenon being studied) will be generally defined as _____ (provide a general definition). 

 

A Quantitative Purpose Statement

• Include words to signal the major intent of the study (e.g. purpose, intent, objective)
• Mention the specific type of quantitative approach (e.g. survey, experimental research)
• Identify the theory, model, and conceptual framework
• Identify the variables (e.g. independent, dependent, mediating, moderating variables)
• Indicate the relationship among the variables (e.g. relationship, comparison, determinants, correlation, prediction)
• Order the variables
• Refer the participants
• Define key variables

The purpose of this _________ (experiment? survey?) study is (was? will be?) to test the theory of _________ that __________ (explains, predicts) that the _________ (independent variable) _________ (compares? relates?) to __________ (dependent variable). This study aims to recruit __________ (participants) at __________ (the research site). The independent variable(s) __________ will be defined as __________ (provide a definition). The dependent variable(s) will be defined as __________ (provide a definition).

 

A Mixed Methods Purpose Statement

• Signal intent, overall intent, type of mixed methods design, purpose, insight to result

This mixed methods study will address _________ (overall intent of study). A convergent mixed methods design will be used, and it is a type of design in which qualitative and quantitative data are collected to provide multiple perspectives on a problem or question. In this study, _________ (quantitative data) will be used to test the theory of _________ (the theory) that predicts or explains that _________ (independent variables) will _________ (positively, negatively) influence the _________ (dependent variables) for _________ (participants) at _________ (the site). The _________ (type of qualitative data) will explore _________ (the central phenomenon) for _________ (participants) at _________ (the site). The insight to emerge from combining the two databases will _________ (provide a more complete understanding of the problem, examine convergence of the databases, validate one database with the other).

CHAPTER 7 Research Questions and Hypotheses

CHAPTER 7 Research Questions and Hypotheses

Introduction

• signposts
  • purpose statement: establishes the central intent for the study
  • research questions of hypotheses: narrows down the purpose statement t o predictions about what will be learned or questions to be answered in the study

Quantitative Research Questions and Hypotheses

• Research questions: pose questions about the relationships among variables in a study
• Hypotheses: predicts expected relationships among variables
  • statistical procedures: draws an inference about a population from a study sample
  • experiments or intervention studies: compares among groups
• Guidelines
  • state variables, include theory, descriptive or relationship questions, create a directional alternative hypothesis (null, alternative hypothesis), use directional words (e.g. affect, influence, predict, impact, determine, cause, relate)

Qualitative Research Questions

• Central questions: major open-ended
• Sub questions: divides the central phenomenon into sub-topics to learn more about the central phenomenon
• Guidelines
  • Ask one or two central research questions, ask no more than five to seven sub-questions, related the central questions to the specific approach, begin the research questions with the words what or how, focus on a single central phenomenon or concept, use exploratory words, expect the research questions to evolve and change during the study, use open-ended questions, specify the participants and the research site

Mixed Methods Research Questions and Hypotheses

• Guidelines
  • both qual and quant research questions needed, include a mixed methods research questions, consider the placement of the questions, attention to the order of the research questions

CHAPTER 8 Quantitative Methods

CHAPTER 8 Quantitative Methods

Introduction

• This chapter focuses on survey and experimental designs. These designs reflect postpositivist philosophical assumptions. For example, determinism suggests that examining the relationships between and among variables is central to answering questions and hypotheses through surveys and experiments. In one case, a researcher might evaluate whether playing violent video games is associated with higher rates of playground aggression in kids, which is a correlational hypothesis that could be evaluated in a survey design.
• In each case, these quantitative approaches focus on carefully measuring (or experimentally manipulating) a small set of variables to answer theory-guided research questions and hypotheses.

Putting Quantitative Research in Context

• The quantitative method section has a formal structure and intended audience
• The method section has four primary elements: (a) a description of the study population and the sample characteristics (i.e., who are you studying?), (b) a description of the study procedures and variables (i.e., how will you formally test your study hypotheses?), (c) a description of the instruments used (i.e., how will you measure your variables?), and (d) a description of the data analytic plan (i.e., how will you analyze your data?)
• The intended audience of a quantitative method section is other scientists, and the method section should provide sufficient detail that these other scientists could carry out the same study in their research setting

Quantitative Designs

• A survey design provides a quantitative description of trends, attitudes, and opinions of a population, or tests for associations among variables of a population, by studying a sample of that population
  • Survey designs help researchers answer three types of questions
    • (a) descriptive questions (e.g., What percentage of company employees support hiring women of color in executive leadership positions?)
    • (b) questions about the relationships between variables (e.g., is there an association between the number of women of color in executive roles and overall perceptions of company satisfaction among employees?); or in cases where a survey design is repeated over time in a longitudinal study
    • (c) questions about predictive relationships between variables over time (e.g., Does Time 1 hiring of new women of color executives predict greater Time 2 company satisfaction?).
• An experimental design systematically manipulates one or more variables to evaluate how this manipulation affects an outcome (or outcomes) of interest
• Advantages and disadvantages
  • Surveys can be relatively inexpensive and easy to administer in contrast to experimental studies where a researcher aims to systematically manipulate a variable (or variables) while holding all other variables constant.
  • Survey designs offer a tool for describing a study population and testing for associations between study variables. However, experiments can go beyond these survey design features to address causal relationships.
  • In the nurse experiment example here, manipulating expressive writing (and keeping all other variables constant) permits inferences around whether writing about one’s deepest thoughts and feelings causes less burnout in the months following the intervention. Whether a quantitative study employs a survey or experimental design, both approaches share a common goal of helping the researcher make inferences about relationships among variables and generalize the sample results to a broader population of interest (e.g., all nurses in the community).

Components of a Survey Study Method Plan

• purpose and type of survey design, population and size, etc.

The Survey Design (+ sample sentences)

• The first parts of the survey method plan section introduce readers to the basic purpose and rationale for survey research. Begin the section by describing the rationale for the design. Specifically:

The Purpose

• The primary purpose is to answer a question (or questions) about variables of interest.

Rationale for Using the Survey Method

• Indicate why a survey method is the preferred type of approach for this study. In this rationale

Type of Survey Method

• Indicate whether the survey will be cross-sectional—with the data collected at one point in time—or whether it will be longitudinal—with data collected over time.

Specify the Form of Data Collection

• mail, telephone, the internet, personal interviews, or group administration

The Population and Sample

• A study population refers to all people you aim to make inferences about (e.g., all nurses across the world) whereas a study sample refers to the (sub)group of participants examined in the survey study (e.g., nurses drawn from five hospitals in your city). Ideally, the sampling of participants is done in such a way as to minimize sources of bias and permit inferences about the study population of interest
  • state the size
  Sampling Design
  • Identify whether the sampling design for this population is single-stage or multistage (called clustering). Cluster sampling is ideal when it is impossible or impractical to compile a list of the population’s elements (Babbie, 2015). A single-stage sampling procedure is one in which the researcher has access to names in the population and can sample the people (or other elements) directly. In a multistage or clustering procedure, the researcher first identifies clusters (groups or organizations), obtains names of individuals within those clusters, and then samples within them.
  Type of Sampling
  • random sample, systematic sample, nonprobability sample (convenience sample)
  Population Stratification
  • Identify whether the study will involve stratification of the population before selecting the sample. This requires that the characteristics of the population members be known so that the population can be stratified first before selecting the sample (Fowler, 2014). Stratification means that specific characteristics of individuals (e.g., gender—females and males) are represented in the sample and the sample reflects the true proportion in the population of individuals with certain characteristics.
  Sample Size Determination
  • Indicate the number of people in the sample and the procedures used to compute this number
  Power Analysis
  • If your analysis plan comprises detecting a significant association between variables of interest, power analysis can help you estimate a target sample size
• The Population

Instrumentation

• The Survey Instruments Used to Collect Data
  • Discuss whether you used an instrument designed for this research, a modified instrument, or an instrument developed by someone else.
• Instruments and Measures
  • Instruments are the devices for collecting measures of variables
• Validity of Scores Using the Instrument
  • To use an existing instrument, describe the established validity of scores obtained from past use of the instrument
• Reliability of Scores on the Instrument
  • Also, mention whether scores resulting from past use of the instrument demonstrate acceptable reliability
• Inter-Rater Reliability
  • Although survey designs typically focus on establishing reliability across items within a single instrument (internal consistency), some study designs may involve judges or experts who all complete the same instrument
• Sample Items
  • Include sample items from the instrument so that readers can see the actual items used
• Content of an Instrument
  • Indicate the major content sections in the instrument, such as the cover letter, the items, and the closing instructions

Pilot Testing

• Discuss plans for pilot testing or field-testing the survey, and provide a rationale for these plans

Administering the Survey

• For a mailed survey, identify steps for administering the survey and for following up to ensure a high response rate

 

Variables in the Study

• it is useful in the method section to directly state the variable names, operational definitions, and actual instruments used to measure those variables

Data Analysis

• R, IBM SPSS, Microsoft Excel, JMP, Minitab, SYSTAT 13, SAS/STAT, Stata
• The data analysis plan describes the sequential series of steps for analyzing the survey data: STEP 설명?

Preregistering the Study Plan

• After drafting a method plan, it is important to step back and consider whether the goal of your survey research is exploratory and aimed at generating new hypotheses or whether the goal is confirmatory and directed at formally testing hypotheses. If the research goal is formal hypothesis testing, it is important to preregister the plan. Preregistration is the act of publishing your plan and hypotheses in a public registry prior to data collection

Interpreting Results and Writing a Discussion Section

Chapter 8 explains how to design quantitative research. It introduces survey and experimental designs. I will introduce an overview of quantitative research and survey, and Munir will introduce the experimental design after. These designs reflect postpositivist philosophical assumptions. This postpositivist philosophy follows determinism. It focuses on examining the relationships between and among variables.

 

When you plan and write a quantitative method section, there is a formal structure and intended audience. My question here is, what are the four primary elements? You can refer to 158 pages of the book (192 pages of the ebook).

1.    a description of the study population and the sample characteristics (i.e., who are you studying?)

2.    a description of the study procedures and variables (i.e., how will you formally test your study hypotheses?)

3.    a description of the instruments used (i.e., how will you measure your variables?)

4.    a description of the data analytic plan (i.e., how will you analyze your data?)

Who is the intended author of the quantitative method section? It’s other scientists. The method section should provide sufficient detail so that other scientists can carry out the same study in their research setting.

 

Let's look at what survey and experimental designs are. First, survey design provides a quantitative description of trends, attitudes, and opinions of a population, or tests for associations among variables of a population by studying a sample of that population. Survey design helps answer the following three questions.

1.    descriptive questions (e.g., What percentage of company employees support hiring women of color in executive leadership positions?)

2.    relationships between variables (e.g., Is there an association between the number of women of color in executive roles and overall perceptions of company satisfaction among employees?) or in cases where a survey design is repeated over time in a longitudinal study

3.    predictive relationships between variables over time (e.g., Does Time 1 hiring of new women of color executives predict greater Time 2 company satisfaction?).

I have a question here. I haven’t used survey methods before. So, if anyone conducting quantitative or mixed-method research uses surveys, could you share your research question and explain which type of question it is closest to?

 

Let’s move on to experimental design. Experimental design systematically changes one or more variables to see how this change affects the outcome or outcomes.

Surveys and experiments each have their own advantages and disadvantages. Surveys are cheaper and easier, while experiments are harder because they need to control variables. Surveys help describe a group and find connections between variables, but experiments go further and can examine causal relationships. However, both methods help researchers understand variable relationships and apply the results to a larger population.

 

Also, on page 160 of the book (ebook page 194), there is a checklist of questions for designing a survey study plan. If you use the survey method, it would be helpful to come back to this checklist when working on your thesis or dissertation.

---------------

Now, let's take a closer look at planning a survey design. The primary purpose is to answer a question about variables. First, you need to describe the purpose of the survey in your research. And you need to explain why the survey is the preferred type of approach. And then, you need to indicate if the survey will be cross-sectional, meaning you collect data only once at a single point in time, or longitudinal, meaning you collect data multiple times over a period of time. You can conduct the survey through mail, telephone, the Internet, personal interviews, or group administration. You need to explain the strengths and weaknesses, costs, data availability, and convenience of the method you choose.

 

A survey studies a sample from a larger population. So to make fair conclusions, sampling should reduce bias and represent the whole group well. So, Let's look at sampling. You will identify whether the sampling design is single-stage or multistage (clustering). Can anyone explain the difference between single-stage and multistage? You can refer to page 162 or page 197 for ebook readers.

·       Single-stage sampling is used when you have a full list of people in the population and can directly select participants.

·       Multistage (clustering) sampling is used when you cannot list every individual, so you first choose groups (clusters) and then select participants from within those groups.

 

After that, you will explain how to select participants for your sample. I found three types of sampling in this book.

·       Random sampling is best because everyone in the population has an equal chance of being chosen.

·       Systematic sampling is similar, where you start randomly on a list and pick every Xth person (e.g., 1 out of every 80 people).

·       Convenience sampling is the easiest but least ideal, where you choose people based on availability rather than randomness.

 

Also, decide if the study will use stratification before selecting the sample. Stratification means dividing the population into groups based on characteristics (e.g., gender, income, education) to ensure they are properly represented in the sample. This helps ensure the sample reflects the true proportions of these characteristics in the whole population.

 

Next is instrumentation. Explain whether you used a new instrument, a modified instrument, or an existing instrument from another researcher. If you use an existing instrument, describe its validity based on past research. There are two common types.

1.    Construct validity. It’s about whether the survey accurately measures the concept it is meant to measure.

2.    Concurrent (or criterion) validity. It’s about whether the survey matches other well-established measures or predicts an expected outcome.

Also, mention whether past use of the instrument shows acceptable reliability. Reliability means the instrument gives consistent results when used multiple times.

 

The next part is variables. State the variable names, operational definitions, and actual instruments in the methods section.

 

Now, we move on to the data analysis stage. The data analysis plan includes the following steps:

1.    Report Survey Responses – Show the number and percentage of participants who returned or did not return the survey. A table can help present this information clearly.

2.    Check for Response Bias – Explain how you will determine if nonresponses affected the results. Methods include wave analysis (checking if late responses differ from early ones) or respondent/nonrespondent analysis (calling nonrespondents to compare answers).

3.    Descriptive Analysis – Provide means, standard deviations, and score ranges for predictor and outcome variables. Identify missing data and describe how you will handle it.

4.    Scale Analysis – If using multi-item scales, check whether reverse scoring is needed and explain how total scores are calculated. Also, report reliability using Cronbach’s alpha.

5.    Inferential Statistics – Identify the statistical tests and software used to analyze relationships between variables or compare groups. Explain why the test is appropriate and consider factors like data type (continuous or categorical) and normality of distribution.

6.    Present Results – Display findings using tables and figures, then interpret the statistical test results.

 

After drafting your method plan, consider your research goal. If the study is exploratory, it aims to generate new hypotheses. But, If the study is confirmatory, it formally tests hypotheses and should be preregistered. Preregistration means publishing your research plan and hypotheses in a public registry before collecting data. This improves accuracy and transparency in quantitative research.

 

Now, we are approaching the final stage. After finishing data analysis, report how the results answer the research question or hypothesis. You can use statistical tests to analyze hypotheses or research questions, such as t-test and ANOVA; you can learn these statistics from the 7301 Quant class. In addition to reporting the statistical test and p-value, two important practical measures can be included:

·       Confidence Interval (CI) – Shows a range of values that estimates the uncertainty around a result.

·       Effect Size – Measures the strength of differences between groups or relationships between variables.

 

The final step is to write the discussion section, where you summarize the main findings and connect them to past research.

CHAPTER 9

 

CHAPTER 10

 

 

 

Research Design

-

저자

John W. Creswell

출판

Sage Publications, Inc

출판일

2022.12.13