Data and (Mis)infomation - concepts lecture 3

Logical fallacy

A faulty reasoning in the construction of an argument. It is just an argument that is somehow wrong.

Formal fallacy

A formal argument is a deductive argument: if you accept the premises, then the conclusion necessarily follows. So in a formal fallacy, the conclusion is supposed to necessarily follow from accepting the premises, yet it doesn’t

Affirming the consequent

A formal fallacy

Taking a true conditional statement under certain assumptions, and invalidly inferring its converse, even though that statement may not be true under the same assumptions

If A is true, then B is true. B is true, therefore A is true.

A premise

A statement or assumption used to support a conclusion

Conclusion

The claim that follows from the premise

Modus Tollens

Falsificationism

Is A is true, then B is true. B is NOT true, therefore A is NOT true

Denying the antecedent

A formal fallacy of inferring the inverse from an original statement.

If A is true, then B is true. A is NOT true, therefore B is NOT true (e.g., if you study hard you will pass this course. You do not study hard. Therefore, you will not pass this course)

Modus Ponens

The valid counterpart of denying the antecedent.

If A is true, then B is true. A is true, therefore B is true (e.g., If you study hard, you will pass this course. You study hard, therefore you will pass the course)

Informal fallacy

A flawed argument caused by its content or use of evidence.

Inductive argument

Even if you accept the premises, then the conclusion still doesn’t necessarily follow; you can still doubt the conclusion.

Deductive argument

If you accept the premises, then the conclusion necessarily follows

Equivocation

A informal fallacy resulting from the use of a particular word/expression in multiple senses within an argument (“calling two things by the same name”)

Proof by assertion

A informal fallacy: a proposition is repeatedly restated regardless of contradiction and refutation. If you repeat something enough, some people will believe you because of familiarity.

Red herring

A informal fallacy: A logical fallacy in which an irrelevant topic is introduced in an argument to divert attention away from the original issue.

False dichotomy

A informal fallacy where only two extreme options are presented as the only possibilities, when in fact more options exist

Slippery Slope

A informal fallacy: a course of action is rejected because the slippery slope advocate believes it will lead to a chain reaction resulting in an undesirable end or ends.
‘Just imagine, what will happen next… and after that…” we end up in a state that no one ever wants

Strawman arguments

A informal fallacy: refuting an argument different from the one actually under discussion, while not recognizing or acknowledging the distinction.

Basically, setting up the other person's argument in a unrealistic way, that nobody would ever entertain.

Ad hominem

A informal fallacy: a rhetorical strategy where the speaker attacks the character, motive, or some other attribute of the person making an argument rather than attacking the substance of the argument itself

Othering

A informal fallacy: The process of perceiving or portraying someone or something as essentially alien or different. Basically: the other person you can never agree with because the other person is so different.

Statistical fallacies

People are notoriously bad with statistics, so it’s easy to deceive (or to be deceived) by them.

We need statistics for evidential reasoning, but statistical arguments are not rarely shady, with data/results being (un)intentionally misused in some shape or form.

Post hoc ergo propter hoc

A statistical fallacy: Assuming X caused Y simply because X happened before Y.
Correlation is not causation!

3 conditions to support causation

Correlation: for an events to cause the other

Temporal precedence: one event needs to come before the other

No confounding: very difficult to establish. No other variables that make it seem there is a relationship between the causal condition

Simpson’s paradox

A statistical fallacy: Counterintuitively, a correlation can even be inverted once you control for third variables!

Base-rate fallacy

A statistical fallacy: people tend to ignore the base rate (e.g., general prevalence) in favor of the individuating information (i.e., information pertaining only to a specific case)

Ecological fallacy

A statistical fallacy: Error of assuming that characteristics observed at the group level are also present at the individual level.

Cherry picking

A statistical fallacy: the act of pointing to individual cases or data that seem to confirm a particular position while ignoring a significant portion of related and similar cases or data that may contradict that position.

Sampling bias

A statistical fallacy: bias in which a sample is collected in such a way that some members of the intended population have a lower or higher sampling probability than others

Non-response bias

A statistical fallacy: Respondents differ systematically from people who do not respond.

Berkson’s paradox

A statistical fallacy: Counterintuitively, a correlation between variables x and y can be falsely inverted when you condition on a colliding variable (‘collider bias’)
Colliding variable = A variable‘caused by’ both x and y

A collider

A variable caused by two other variables

Survivor bias

A statistical fallacy: The logical error of concentrating on entities that passed a selection process while overlooking those that did not. This can lead to incorrect conclusions because of incomplete data (Focusing on successful cases while ignoring cases that failed)

Construct validity & operational definitions

A statistical fallacy: Always ask yourself:

• How is this measured?
• What does the measurement mean?
• How is it interpreted?