Inferential Fallacies & Research Biases

← Back to Domain-Specific Families

Abstractions that name flawed patterns of inference or measurement in research and public reasoning — hasty generalization, argument from anecdote, the Table 2 fallacy, and randomized response — alongside related judgment biases such as normalcy bias, outcome bias, and zero-risk bias.

18 abstractions in this family — domain-specific abstractions that sit near one another in structural-signature space (k-means over structural-signature embeddings). Each is shown with its short description.

• Access journalism — Access journalism, or access reporting, refers to journalism (often in interview form) which prioritizes access—meaning media time with important, rich, famous, powerful, or otherwise influential people in politics, culture, sports, business, technology, and other areas—over journalistic objectivity and/or integrity.
• Argument from anecdote — Misuse of anecdotal evidence in the form of argument from anecdote is an informal fallacy and is sometimes referred to as the "person who" or anecdotal fallacy, with statements like "I know a person who..." or "I know of a case where...".
• Attack rate — In epidemiology, the attack rate is the proportion of an at-risk population that contracts the disease during a specified time interval.
• Ballot-Order Effect — The ballot order effect refers to the effect of voting behavior based on the placement of candidates' names on an election ballot.
• Cognitive bias mitigation — Cognitive bias mitigation is the prevention and reduction of the negative effects of cognitive biases – unconscious, automatic influences on human judgment and decision making that reliably produce reasoning errors.
• Covariate — Depending on the context, an independent variable is sometimes called a "predictor variable", "regressor", "covariate", "manipulated variable", "explanatory variable", "exposure variable" (see reliability theory), "risk factor" (see medical statistics), "feature" (in machine learning and pattern recognition) or "input variable".
• Gambling — Gambling (also known as betting or gaming) is the wagering of something of value ("the stakes") on a random event with the intent of winning something else of value, where instances of strategy are discounted.
• Hasty generalization — Hasty generalization is the fallacy of examining just one or very few examples or studying a single case and generalizing that to be representative of the whole class of objects or phenomena.
• Imperfect induction — The imperfect induction is the process of inferring from a sample of a group to what is characteristic of the whole group.
• Inflicted insight — Inflicted insight is a possible consequence for subjects participating in certain kinds of research.
• Legal liability — In law, liable means "responsible or answerable in law; legally obligated".
• Normalcy bias — Normalcy bias, or normality bias, is a cognitive bias which leads people to disbelieve or minimize threat warnings.
• Outcome bias — The outcome bias is an error made in evaluating the quality of a decision when the outcome of that decision is already known.
• Punishment (psychology) — Punishment is any change in a human or animal's surroundings which, occurring after a given behavior or response, reduces the likelihood of that behavior occurring again in the future.
• Randomized response — Randomised response is a research method used in structured survey interview.
• Table 2 fallacy — The Table 2 Fallacy is a term coined by Daniel Westreich and Sander Greenland in 2013.
• Twyman's law — Twyman's law states that "Any figure that looks interesting or different is usually wrong", following the principle that "the more unusual or interesting the data, the more likely they are to have been the result of an error of one kind or another".
• Zero-risk bias — Zero-risk bias is a tendency to prefer the complete elimination of risk in a sub-part over alternatives with greater overall risk reduction.