Research Concepts and Processes
Language of Research
Researchers use specific terms to discuss business problems.
Concept: A bundle of meanings associated with unambiguous events, objects, conditions, or situations.
Construct: A definition invented to represent an abstract phenomenon for a research project.
Conceptual Scheme: The interrelationship between concepts and constructs.
Operational Definition: Defines a variable in terms of specific measurement criteria.
Variable: Used as a synonym for the construct being studied.
Proposition: A statement about observable phenomena that may be judged as true or false.
Hypothesis: A proposition formulated for empirical testing.
Theory: A set of interrelated concepts, definitions, and propositions that explain or predict phenomena.
Model: A representation of a system constructed to study an aspect of that system.
Conceptualization and Measurement
Concepts must be measured clearly to avoid confusing answers.
Job Redesign Constructs and Concepts
Concepts like format accuracy, manuscript errors, and keyboarding speed are concrete and easily measured.
Presentation Quality: A construct defined by the concepts of format accuracy, manuscript errors, and keyboarding speed.
Concepts like vocabulary, syntax, and spelling are grouped into the construct of Language Skill.
Hypothetical Constructs: Constructs inferred only from data, presumed to exist without direct measurement (e.g., job interest).
If research supports the interrelation of concepts and constructs, it forms the beginning of a conceptual scheme.
Operational Definitions
Operational definitions are stated in terms of specific criteria for testing or measurement; specifications must be clear for consistent classification.
Example: Classifying college students by class level using credit hours completed as the most precise measure.
Variable
Variable is a synonym for the property being studied - a symbol of an event, act, characteristic, trait, or attribute that can be measured and assigned categorical values.
Types of Variables
Numerical values are assigned to variables based on their properties.
Dichotomous Variables: Have only two values reflecting the presence or absence of a property.
Used in hypothesis testing and comparison.
Discrete Variables: Take on values representing added categories.
Used in survey research and demographic studies.
Continuous Variables: Take on values within a given range or an infinite set.
Used in statistical analysis and regression models.
Independent and Dependent Variables
Independent Variable: Manipulated by the researcher to cause an effect on the dependent variable.
Dependent Variable: Expected to be affected by the manipulation of an independent variable.
Moderating Variables (MV)
Moderating variables have a significant contributory or contingent effect on the IV-DV relationship.
Example: The introduction of a four-day week (IV) will lead to higher productivity (DV), especially among younger workers (MV).
Example: The switch to commission from a salary compensation system (IV) will lead to increased sales (DV) per worker, especially more experienced workers (MV).
Example: The loss of mining jobs (IV) leads to acceptance of higher-risk behaviors to earn a family-supporting income (DV) – particularly among those with a limited education (MV).
Extraneous Variables (EV)
Extraneous variables could conceivably affect a given relationship and may be treated as independent, moderating, or control variables.
Example: With new customers (EV-control), a switch to commission from a salary compensation system (IV) will lead to increased sales productivity (DV) per worker, especially among younger workers (MV).
Example: Among residents with less than a high school education (EV-control), the loss of jobs (IV) leads to high-risk behaviors (DV), especially due to the proximity of the firing range (MV).
Intervening Variables (IVV)
An intervening variable affects the observed phenomenon but cannot be measured or manipulated; it's a conceptual mechanism.
Example: The switch to a commission compensation system (IV) will lead to higher sales (DV) by increasing overall compensation (IVV).
Example: A promotion campaign (IV) will increase savings activity (DV), especially when free prizes are offered (MV), but chiefly among smaller savers (EV-control). The results come from enhancing the motivation to save (IVV).
Propositions and Hypotheses
Proposition: A statement about observable phenomena that may be judged as true or false.
Hypothesis: A proposition formulated for empirical testing.
Case: The entity or thing the hypothesis talks about
Generalization: Hypothesis based on more than one case.
Descriptive Hypothesis Formats
A descriptive hypothesis is a statement about the existence, size, form, or distribution of a variable.
Advantages over research questions:
Encourages crystallized thinking about likely relationships.
Encourages thinking about implications of findings.
Useful for testing statistical significance.
Relational Hypotheses Formats
A relational hypothesis is a statement about the relationship between two variables.
Correlational Hypothesis: Variables occur together in some specified manner without implying causation.
Causal Hypothesis: One variable leads to a specified effect on the other variable.
Theory within Research
Theories are complex, abstract, and involve multiple variables.
Hypotheses are simple, limited-variable statements involving concrete instances.
Theory: A set of systematically interrelated concepts, definitions, and propositions that explain or predict phenomena.
The Role of Reasoning
Business models are developed through inductive and deductive reasoning.
Inductive Reasoning: Drawing conclusions from facts or evidence.
Uses existing theory, managerial experience or judgment, or facts.
A Model within Research
Model: A representation of a system constructed to study some aspect of that system.
Models represent or describe; theories explain.
Types of models: descriptive, predictive, and normative.
Descriptive Models: Visualize numerous variables and relationships.
Predictive Models: Forecast future events and facilitate business planning.
Normative Models: Indicate necessary actions for control.
Models allow researchers to specify hypotheses that characterize present or future conditions.
The Scientific Method
Good business research is based on sound reasoning and guides our approach to problem-solving.
Empirical Testing: Observations and propositions based on sensory experience or derived from inductive logic, including mathematics and statistics.
Sound Reasoning
Exposition: Statements that describe without attempting to explain.
Argument: Explains, interprets, defends, challenges, and explores meaning.
Deduction: Conclusion necessarily follows from the premises given.
Induction: Conclusion drawn from particular facts or evidence.
Induction and deduction can be used together in research reasoning.
Induction asks "Why is this?" to form a tentative explanation or hypothesis.
Deduction tests whether the hypothesis can explain the fact.
Tracy's Performance (Example of Induction and Deduction)
Induction: Begins with facts about Tracy's poor performance and lateness.
Hypothesis: Tracy is lazy.
Deduction: This laziness results in excessive tardiness and fewer customer calls.
Clarifying the Research Question
State the basic dilemma and develop questions by breaking it down into more specific ones.
*Key Terms:
*Management Dilemma: an opportunity for a problem that the manager has discovered because of one or more symptoms.
*Management Question: a restatement of the manager’s dilemma in question form.
*Research Question: the hypothesis that best states the objective of the research; the question that focuses the researcher’s attention.
*Investigative Question: the question the researcher must answer to satisfactorily answer the research question.
*Measurement Question: the question asked of the participant or the observations that must be recorded.
Evaluating the Value of Research
Managers must prove research meets ROI objectives.
Option Analysis: Formal analysis of alternatives judged by costs and benefits.
Decision Theory: Assesses outcomes of each action.
Alternatives are explicitly stated.
A decision variable is defined by a measurable outcome.
A decision rule is determined to compare outcomes.
Prior or Interim Evaluation: Costs reviewed at each stage.
Ex Post Facto Evaluation: Occurs after research but guides future decisions.
Proposing Research
Research must be proposed to allocate resources.
Types of budgets:
Rule-of-Thumb Budgeting: Fixed percentage of some criterion.
Departmental Budgeting: Portion of total expenditures allocated to research.
Task Budgeting: Specific projects supported on an ad hoc basis.
The Research Proposal
/
A written proposal is desirable for establishing agreement and an oral proposal is more likely when a manager directs his or her own research.
Designing the Research
Three components: research design, sampling design, and pilot testing.
Research Design: Blueprint for fulfilling objectives and providing insight to answer the management dilemma.
Sampling Design: Identify the target population and determine whether a sample or census is desired.
Census: Count of all elements in a population.
Sample: A portion of the target population.
Pilot Test: Tests weaknesses in methodology and data collection.
Data Collection & Preparation
Factors characterizing data:
Abstractness
Verifiability
Elusiveness
Closeness to the phenomenon
Data Types
Secondary data: Originally collected to address a problem other than the one which requires the manager’s attention at the moment.
Primary data: Data the research collects to address the specific problem at hand.
Reporting the Results
Provide insightful information adapted to the client’s needs.
Research report includes:
Executive summary
Research overview
Implementation strategies
Technical appendix
Research Process Problems to Avoid
*Unresearchable questions: Not all management questions are researchable and not all research questions are answerable.
Ill-defined Problem: Addresses complex issues and cannot be expressed easily.
Politically-Motivated Research: Intended to win approval for a pet idea.
Favored-Technique Syndrome: Researchers recast management questions to fit their favorite method.
Company Database Strip-Mining: Managers want to evaluate existing data before collecting more.
Exploratory Phase Search Strategy
Exploration develops concepts, establishes priorities, develops operational definitions, and improves the final research design. Consists of one or more of the search strategies:
Discovery and analysis of secondary data sources
Expert interviews
IDIs- interviews with individuals involved with the problem.
Formal or informal group discussions
Objectives of Secondary Searches
Expand understanding of management dilemma.
Gather background information.
Identify information that should be gathered.
Identify sources for and actual questions that might be used.
Identify sources for and actual sample frames that might be used.
Conducting a Literature Search
Review of books, journal articles, and professional literature related to the management dilemma.
If results of a literature search provides a solution to the management dilemma, then no further research is necessary; otherwise, a research proposal is generated.
Levels of Information
Primary Sources: Original works of research or raw data without interpretation.
Secondary Sources: Interpretations of primary data.
Tertiary Sources: Aids to discover primary or secondary sources.
Types of Information Sources
Indexes: Secondary data source that helps to identify and locate a single book, journal article, author, etc. from a larger set.
Bibliographies: Information source that helps locate a single book, article, photograph, etc.
Dictionaries: Secondary sources that define words, terms, and jargon.
Encyclopedias: Secondary sources that provide background or historical information about a topic.
Handbooks: Secondary source used to identify key terms, people, or events relevant to the management dilemma or management question.
Directories: Reference sources used to identify contact information.
Evaluating Information Sources
Marketers evaluate and select information sources based on five factors:
Purpose: The explicit or hidden agenda of the information source.
Scope: The breadth or depth of topic coverage.
Authority: The level of the data and the credentials of the source author.
Audience: Characteristics and background of the people or groups for whom the source was created.
Format: How the information is presented and the degree of ease in locating specific information within the source.
Data-Mining Process
Involves five steps: sample, explore, modify, model, and assess.
In the sample step, the researcher decides between census data and sample data.
Explore involves identifying relationships with the data.
In the third step, data are modeled and/or transformed
In the fourth step, a model is developed that explains the data relationships.
Finally, the model is tested for accuracy.
Formulating the Research Question
The management-research question hierarchy process is designed to move the researcher through various levels of questions, each with a specific function within the overall marketing research process.
The Research Question
A research question best states the objective of the marketing research study and incorrectly defining the research question is the fundamental weakness in the marketing research process.
Fine-Tuning the Research Question
After the exploration process is complete, the researcher must fine-tune the research question.
Examine variables to be studied and assess whether they are operationally defined.
Review the research questions to break them down into second and third-level questions.
If hypotheses are used, be sure they meet the quality tests.
Determine what evidence must be collected to answer the various questions and hypotheses.
Set the scope of the study by stating what is not a part of the research question.