Research Design

Qualitative and Quantitative Research Design

Introduction

  • Quantitative researchers are more concerned about issues of design, measurement, and sampling because their deductive approach emphasizes detailed planning prior to data collection and analysis.
  • Qualitative researchers are more concerned about issues of the richness, texture, and feeling of raw data because their inductive approach emphasizes developing insights and generalizations out of the data collected.

Triangulation

  • By observing something from different angles or viewpoints, they get a fix on its true location. This process, called triangulation, is used by quantitative and qualitative social researchers.
  • Applied to social research, it means it is better to look at something from several angles than to look at it in only one way.
  • The most common type is triangulation of measures. Researchers take multiple measures of the same phenomena.
  • Another type is triangulation of observers. Multiple observers or researchers add alternative perspectives, backgrounds, and social characteristics and will reduce the limitations.
  • Triangulation of theory occurs when a researcher uses multiple theoretical perspective in the planning stages of research, or when interpreting the data.
  • Triangulation

of method means mixing qualitative and quantitative styles of research and data.

Qualitative and Quantitative Orientations toward Research

  • Qualitative and Quantitative approaches differ in the nature of the data. Soft data, in the form of impressions, words, sentences, photos, symbols, and so forth, dictate different research strategies and data collection techniques than hard data, in the form of numbers.
  • Qualitative and Quantitative researchers often hold different assumptions about social life and have different objectives.
  • Qualitative researchers often rely on interpretive or critical social science. They use a transcendent perspective, apply “logic in practice”, and follow a nonlinear research path.
  • Qualitative researchers speak a language of “cases and contexts”.
  • Quantitative researcher uses a technocratic perspective, apply “reconstructed logic”, and follow a linear research path. They speck a language of “variables and hypotheses”. Quantitative researchers s emphasize precisely measuring variables and testing hypotheses that are linked to general causal explanations.

Technocratic and Transcendent Perspective

A way to distinguish qualitative and quantitative styles of research is the contrast between technocratic and transcendent perspectives.
The technocratic perspective fits with positivism.
The transcendent perspective more closely fits the interpretive and critical approaches.

Reconstructed Logic and Logic in Practice

The way social researchers learn and discuss research usually follows one of two logics: reconstructed logic or logic in practice.
Quantitative researchers apply more of the reconstructed logic, whereas qualitative researchers tend to apply logic in practice.

Reconstructed logic means that the logic of how to do research is highly organized and restated in an idealized, formal, and systematic form.

Logic in practice is the logic of how research is actually carried out.

Linear and Non Linear Paths

The path is a metaphor for the sequence of things to do: what is finished first or where a researcher has been, and what comes next or where he or she is going.
Quantitative researchers follow more linear path than do qualitative researchers.
A linear research path follows a fixed sequence of steps.

Qualitative research is more nonlinear and cyclical.
A nonlinear research path makes successive passes through steps, sometimes moving backward and sideways before moving on.

Objectivity and Integrity

Qualitative researchers emphasize the human factor and the intimate firsthand knowledge of the research setting; they avoid distancing themselves from the people or events they study.

Quantitative researchers stress objectivity and more “mechanical” techniques. They use principle of replication, adhere to standardized methodological procedures, measure with numbers, and then analyze the data with statistics, an area of applied mathematics. Quantitative research eliminates the human factor.

Qualitative researchers emphasize trustworthiness as a parallel idea to objective standards in quantitative research design. This ensures that research activities are dependable and credible. Quantitative research addresses the issue of integrity by relying on an objective technology such as precise statements, standard techniques, numerical measures, statistics, and replication.

Qualitative researchers ensure that their research accurately reflects the evidence and have checks on their evidence.

Preplanned and Emergent Research Questions

  • All research begins with a topic but a topic is only a starting point, that researchers must narrow into a focused research question.
  • Qualitative researchers often begin with vague or unclear research questions. The topic emerges slowly during the study.
  • Quantitative researchers narrow a topic into a focused question as a discrete planning step before they finalize study design. They us it as a step in the process of developing a testable hypothesis and to guide the study design before they collect any data.
  • The qualitative researcher begin data gathering with a general topic and notions of what will be relevant.
  • Major limitations include time, costs, access to resources, approval by authorities, ethical concerns, and expertise.

Qualitative Design Issues

The Language of case and contexts

Qualitative researcher use a language of cases and contexts, employ bricolage, examine social processes and cases in their social context, and look at interpretations or the creation of meaning in specific settings.

Grounded Theory

A qualitative researcher develops theory during the data collection process.
This more inductive method means that theory is built from data or grounded in the data.

The context is critical

Qualitative researchers emphasize the social context for understanding the social world.
They hold that the meaning of a social action or statement depends, in an important way, on the context in which it appears.

Bricolage

Qualitative researchers are bricoleurs; they learn to be adept at doing many things, drawing on a variety of sources, and making do with whatever is at hand.
A bricolage technique means working with one’s hands and being pragmatic at using an assortment of odds and ends in an inventive manner to accomplish a specific task.

The Case and Process

In quantitative research, cases are usually the same as a unit of analysis, or the unit on which variables are measured. Quantiative researchers typically measure variables of their hypotheses across many cases.

Qualitative researcher tends to use a “case oriented approach places cases, not variables, center stage”.
The passage of time is integral to qualitative research.

Interpretation

Quantitative research is expressed in numbers, and a researcher gives meaning to the numbers and tells how they relate to hypotheses.

A qualitative researcher interprets data by giving them meaning, translating them, or making them understandable. Chinese

Quantitative Design Issues

The Language of Variables and Hypotheses

Variation and Variables

  • The variable is a central idea in quantitative research.
  • A variable is a concept that varies.
  • Quantitative research uses a language of variables and relationships among variables.
  • The values or categories of a variable are its attributes.
  • The attribute of one variable can itself become a separate variable with a slight change in definition.
  • Quantitative res

earchers redefine concepts of interest into the language of variables.

Types of Variables

Researchers who focus on causal relations usually begin with an effect, and then search for its causes.
Variables are classified into three basic types, depending on their location in causal relationship.

The cause variable is the independent variable.
The effect variable is the dependent variable.

Independent variables come before other type.
Independent variables affect or have an impact on other variables.
Research topics are often phrased in terms of the dependent variables because depdendt variables are the phenomenon to be explained.

A third type of variable is the intervening variable, appears in more complex causal relations. It comes between the independent and dependent variables and shows the link or mechanism between them.
In a sense, the intervening variable acts as a dependent variable with respect to the independent variable and acts as an independent variable toward the dependent variable.

Simple theories have one dependent and one independent variable, whereas complex theories can contain dozens of variables with multiple independent, intervening, and dependent variables.

Causal Theory and Hypotheses

The hypothesis and Causality

A hypothesis is a proposition to be tested or a tentative statement of a relationship between two variables.

Five Characteristics of Causal hypotheses

  • Has at least two variables
  • Expresses a causal or cause effect relationship between the variables
  • Can be expressed as a prediction or an expected future outcome
  • Logically linked to a research question and a theory
  • Falsifiable and can be tested against empirical evidence and show to be true of false

Words that can be used to stated causal relations

  • Causes
  • Leads
  • Is related
  • Influences
  • Is associated with
  • Produces
  • Results
  • If then
  • The higher, the lower
  • Reduces

Testing and refining hypothesis

Knowledge develops over times as researchers throughout the scientific community test many hypotheses.
A hypothesis needs several tests with consistent and repeated support to gain broad acceptance.
The strongest contender or the hypothesis with the greatest empirical support is accepted as the best explanation at the time.

Types of Hypotheses

A hypothesis is never proved, but it can be disproved.
Because a hypothesis make predictions, negative and disconfirming evidence shows that the predictions are wrong.
Positive or confirming evidence for a hypothesis is less critical because alternative hypotheses may make the same prediction.

Researchers test hypotheses in two ways: a straightforward way and a null hypothesis way.

Null hypotheses predict no relationship.
Researchers use the null hypothesis with a corresponding alternative hypothesis or experimental hypothesis.
The alternative hypothesis says that a relationship exists.
When null hypothesis testing is added to confirming evidence, the argument for an alternative hypothesis can grow stronger over time.
Double barreled hypothesis shows unclear thinking and creates confusion. A double barreled hypothesis puts two relationships in one hypothesis.

Aspect of Explanation

Clarity about Units and Levels of Analysis

A level of analysis is the level of social reality to which theoretical explanations refer. A level of analysis can be macro or micro.
The level of analysis delimits the kinds of assumptions, concepts, and theories that a researcher uses.

The unit of analysis refers to the type of unit a researcher uses when measuring.
Common units are individual, group, organization, social category, social institution, and the society.
The units of analysis determine how a researcher measures variables or themes.

Researchers use levels and units of analysis to design research projects, and being aware of them helps researchers avoid logical errors.

Potential Errors in Causal Explanation

A tautology is a form of circular reasoning in which someone appears to say something new but is really talking in circles and making a statement that is true by definition. Tautologies can not be tested with empirical data.

IT project failure causes low funding of IT project.

A teleology is something directed by an ultimate purpose or goal, and it takes several forms. Teleology cannot be empirically measured. They violate the temporal order requirement of causality and they lack a true independent variable because the “causal factor” is so extremely vague.
If we invest a lot of funding in IT project, it will be successful

The ecological Fallacy arises from a mismatch of units of analysis. It refers to a poor fit between the units for which researcher an empirical evidence and the units for which he or she wants to make statements. Ecological fallacy occurs when a researcher gathers data at a higher or an aggregated unit of analysis but wants to make a statement aobut a lower or disaggregated unit.

Majority of IS project are unsuccessful, therefore this case study fails.

Reductionism or fallacy of nonequivalence occurs when a researcher explains macro level events but has evidence only about specific individuals. It occurs when a researcher observes a lower or disaggregated unit of analysis but makes statements about the operations of higher or aggregated units.
SAP A faile, SAP B fail, therefore ERP product fails.
Spuriousness occurs when two variables are associated but are not causally related because there is actually an unseen third factor that is the real cause.

From the Research Question to hypotheses

Hints about hypotheses are embedded within a good research question.
Hypotheses are tentative answers to research question.
Several hypotheses can be developed for one research question.
A researcher can formulate a tentative research quesitn, then develop possible hypotheses; the hypotheses then helps the researcher state the research question more precisely.
Researchers use general theoretical issues as a source of topics.
Theories provide concepts that researchers turn into variables as well as the reasoning or mechanism that help researchers connect variables into research question.

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License