Major Research Paradigms and Methodologies | Quizlet

Five major paradigms

Positivism, Post-Positivism, Interpretivism/Constructivism, Pragmatism, Critical/Advocacy/Participatory.

Positivism

A paradigm that focuses on objective truth through scientific methods.

Post-Positivism

A paradigm that accepts that observations are fallible but still seeks objective truth.

Interpretivism/Constructivism

A paradigm that emphasizes understanding multiple realities shaped by social constructs.

Pragmatism

A paradigm that focuses on practical outcomes and problem-solving.

Critical/Advocacy/Participatory

A paradigm that aims to empower marginalized groups through research.

Research paradigm

A worldview or framework for understanding knowledge and research.

Research

The systematic gathering of observations or data to advance collective knowledge.

Theory

A set of statements describing general principles about how variables relate to each other.

Data

Sets of observations collected during research.

Hypothesis

A specific, testable prediction derived from a theory.

Falsifiable

A theory must be able to be proven false by evidence.

Non-falsifiable theories

Claims that cannot be tested, like 'invisible forces influence behavior'.

Basic research

General knowledge.

Applied research

Research aimed to solve specific problems.

Use-inspired research

Research that combines both basic and applied research.

Seven types of research contributions

Empirical, Artifact, Methodological, Theoretical, Dataset, Survey/Review, Opinion.

Peer review process steps

Submission → Desk Review → Reviewer Assignment → Reviews → Revisions → Acceptance/Rejection.

Double-blind peer review

Neither authors nor reviewers know each other's identities.

Single-blind peer review

Reviewers know authors, but authors don't know reviewers.

Open peer review

Both authors and reviewers know each other's identities.

File drawer problem

Negative results are not published, leading to bias in research literature.

Critique of peer review

Bias, slow turnaround, lack of compensation for reviewers, or failure to catch fraud.

Principles of the Belmont Report

Respect for Persons, Beneficence, and Justice.

IRB

Reviews and approves research involving human subjects to ensure ethical standards.

Informed Consent

Users' emotions were manipulated without their knowledge.

Challenges of ICT Research

Scale, consent, speed, and unclear human subject definitions.

Menlo Report Fourth Principle

Respect for Law and Public Interest.

Probabilistic Sampling Techniques

Random and stratified random sampling.

Non-Probabilistic Sampling Techniques

Convenience, snowball, judgment, opt-in, and self-selected surveys.

External Validity

The generalizability of study results to other settings, people, and times.

Threats to Internal Validity

Confounding variables, Hawthorne Effect, Social Desirability Bias, Demand Characteristics, Investigator Effects.

Construct Validity

How well variables measure the intended theoretical construct.

Statistical Validity

How reasonable and replicable the statistical conclusions are.

True Experiment

Subjects are randomly assigned to conditions.

Quasi-Experiment

No random assignment but manipulation of independent variables.

Natural Experiment

Independent variables are manipulated by natural events, not researchers.

Factor and Level

Factor = independent variable; Level = different values of the factor.

Between-Subjects Design

Each participant experiences only one condition.

Within-Subjects Design

Each participant experiences all conditions.

Rejecting the Null Hypothesis

There is enough evidence to conclude the independent variable affected the dependent variable.

Type 1 Error

False positive.

Type 2 Error

False negative.

Alpha Level

The probability threshold for rejecting the null hypothesis, often set at 0.05.

P-Value

The probability that results occurred by chance if the null hypothesis is true.

Beta

The probability of making a Type 2 error.

Statistical Power

The probability of detecting an effect if there is one (1-beta).

Factors Increasing Statistical Power

Large effect size, low variability, bigger sample size, and higher alpha.

T-Test Usage

One categorical independent variable (2 levels) and a numeric dependent variable.

ANOVA Usage

More than two levels of one independent variable or multiple independent variables.

Correlation Analysis Usage

When studying relationships between two numeric variables.

Chi-Squared Test Usage

When studying relationships between two categorical variables.