PHIL2420 Lecture Notes - Lecture 9: Abraham Wald, Deductive Reasoning, Survivorship Bias
PHIL2420(
20(
9.(Lecture(Notes(
(
− Abraham(Wald(
o Lowering(risk(of(being(shot(down(
o Limitations(of(armor(
o Data(on(plane(damage(
− Survivorship(bias:(concentrating(on(people(or(things(that(made(it(past(some(selection(process(and(
overlooking(those(that(did(not(
− Analysing(scientific(results(
1. Hypothesis(of(interest(
2. Null(hypothesis(
3. Population(of(interest(
4. Sample(((
5. Design(
6. Results(
7. Evaluation(
− Reasoning(is(providing(reasons(for(your(statements(
− Providing(reasons(justifies(statements(
− Reasoning(can(expose(mistakes(
− Reasoning(facilitates(critique(
− Providing(reasons(can(move(the(discussion(forward(
− Reasoning(is(a(recursive(process(
− Formally,(reasoning(proceeds(through(the(construction(of(arguments(
− Persuasion(is(an(attempt(to(convince(others(that(what(you(say(is(true(
− Constructing(arguments(at(the(most(basic(level,(providing(reasons(for(the(statements(you(make,(is(a(
good(strategy(for(persuasion(
− Arguments(can(attack(or(defend(opinions(
− Arguments(are(for(justifying(judgment(
− An(argument(infers(a(conclusion(from(a(set(of(premises(
− An(argument(is(either(inductive(or(deductive(on(the(basis(of(form(alone(
− Deductive(reasoning:(All(A’s(are(B.(X(is(an(A.(Therefore(X(is(B.(
− An(inductive(argument(allows(us(to(generalize(on(the(basis(of(empirical(data(
− A(deductive(argument(enables(us(to(derive(true(conclusions(from(true(premises(
− An(inductive(argument(is(one(in(which(the(truth(of(its(premises(support(the(truth(of(its(conclusion(
− Inductive(arguments:(sampling,(analogy,(causal,(inference(to(best(explanation(
− A(deductive(argument(is(one(in(which(the(truth(of(its(premises(guarantees(the(truth(of(its(conclusion((
− You(can(justify(an(assumption(by(providing(a(valid(argument(for(it(
− A(deductively(valid(argument:(if(all(its(premises(are(true(then(its(conclusion(must(be(true(
− An(argument(is(deductively(valid(if(and(only(if(the(truth(of(its(premises(guarantee(the(truth(of(its(
conclusion(
− A(deductive(argument(is(sound(if(and(only(if(its(is(valid(and(has(true(premises(
− A(conditional(is(false(when(its(antecedent(is(true(and(the(consequence(is(false(
− Random(sampling(
o Clear(hypothesis(
o Sample(must(not(be(biased(
o Larger(the(sample(the(better(the(data(
o Good(method( (