Crash Course: Data, Scientific Method, and Ethics

Comprehensive vocabulary flashcards based on the lecture notes covering basic data terms, steps and variables of the scientific method, data protection regulations, research ethics, and data protection lapses.

Big Data

Data defined and characterized by three key dimensions: Volume, Velocity, and Variety.

Complex/ Multivariate Data

Data involving multiple variables or multifaceted inputs, exemplified by Yelp reviews, doctors asking for a Likert scale along with what you feel, and end-of-semester evaluations.

Scientific Method Steps

The sequential process of inquiry: Observe, Question, Hypothesis, Experiment and Collect Data, Analyze, Test Hypothesis, Conclusion and Outcome.

Causation vs. Correlation

A critical distinction analyzed within the scientific method to determine whether one variable directly causes an effect in another versus merely sharing a relationship.

Scientific Theory vs. Scientific Law

Two foundational scientific concepts evaluated and compared under the scientific method framework.

Independent, Dependent, Confounding Variable

The three variable classifications identified in scientific experimentation: the factor that is changed, the outcome that is measured, and extraneous factors that may influence the results.

Data Mining

A practice categorized under data analysis used to extract patterns and findings from collected data.

Data Analysis Types

The four categories of data analysis identified in the scientific method: Descriptive, Diagnostic, Predictive, and Prescriptive.

Data Protection Laws

Regulatory and legal frameworks governing data handling, including HIPAA, FERPA, Consumer Protection Laws, the Belmont Report, and the IRB.

Core Ethics

Ethical research standards that encompass Autonomy, Beneficence, Justice and Equity for participants, Informed consent, Anonymization vs. Confidentiality, Deception, Debriefing, Data Integrity, Ethical Collection and Retention, Transparency, Security, and Harm Reduction.

IRB

Institutional Review Board; an ethics and regulatory entity associated with the oversight of research experiments and ethical considerations.

Milgram Shock Experiment, Stanford Prison Experiment, Tuskegee Experiment

Key historical studies cited as examples requiring IRB ethical considerations.

Examples of Data Protection Lapses

Major organizational security and privacy failures, specifically citing Yahoo, Meta, Equifax, and Google Location Tracking.

Evaluation Framework for Data Protection Lapses

The analysis required when examining data lapses: determining what happened, how many individuals were impacted, and what the main issue was ethically or legally.

Qualitative Data vs. Quantitative Data

The primary categorical division of data into descriptive, non-numerical qualities versus numerical measurements.

Sample vs. Population

The distinction between an entire group of individuals or items being studied (population) versus a representative subset selected from that group (sample).

Mean, Median, Mode

Crash course statistical measures of central tendency used to understand what a dataset represents.

Anonymization vs. Confidentiality

A core ethical comparison addressing whether participant identifiers are permanently removed from the data versus kept private and protected from unauthorized disclosure.