Meta tags:
description= 15 posts published by Lars Syll during November 2023;
Headings (most frequently used words):
the, of, on, recent, comments, lars, syll, way, down, south, london, town, improving, econometric, analysis, dirk, ehnts, über, staatsschulden, mmt, guido, imbens, response, to, late, manipulability, pearl, vs, rubin, wonkish, cancel, culture, angriff, auf, die, pressefreiheit, ignorability, questionable, assumption, dangers, too, much, control, scientific, fraud, busting, natural, rate, unemployment, myth, new, keynesianism, more, useless, than, ever, causal, traps, statistics, here, with, me, bad, faith, economics, winter, tale, posts, policy, reading, list, categories, archives,
Text of the page (most frequently used words):
the (211), and (116), that (100), new (65), are (55), for (49), opens (46), not (45), share (45), window (45), models (34), nov (31), bluesky (30), facebook (30), but (30), 2023 (28), can (27), they (26), data (25), with (24), have (23), may (23), only (22), has (22), this (21), real (20), jan (19), you (19), #comments (18), world (18), from (18), variables (18), economics (17), assumptions (17), mar (16), apr (16), jun (16), posted (16), more (16), und (16), jul (15), aug (15), sep (15), oct (15), dec (15), feb (15), model (15), about (15), than (15), one (15), results (15), 2022 (14), statistics (14), off (14), all (14), causal (14), control (14), 2018 (13), 2019 (13), their (13), really (13), which (13), even (13), statistical (13), 2012 (12), 2013 (12), 2014 (12), 2015 (12), 2016 (12), 2017 (12), 2020 (12), 2021 (12), 2024 (12), 2025 (12), when (12), its (12), your (12), lars (11), other (11), science (11), lönebildning (11), och (11), arbetslöshet (11), say (11), way (11), cannot (11), there (11), die (11), 2011 (10), econometrics (10), being (10), what (10), research (10), analysis (10), because (10), missing (10), those (9), economic (9), important (9), modelling (9), often (9), explanation (9), some (9), keynesian (9), macroeconomics (9), der (9), does (8), who (8), economists (8), yours (8), scientific (8), these (8), never (8), less (8), also (8), was (8), econometric (8), studies (8), unemployment (8), gender (8), will (7), truly (7), much (7), were (7), make (7), questions (7), know (7), test (7), should (7), here (7), knowledge (7), get (7), hold (7), natural (7), rate (7), problems (7), 2026 (6), nothing (6), how (6), want (6), use (6), been (6), question (6), things (6), our (6), then (6), able (6), terms (6), least (6), far (6), standard (6), take (6), causality (6), women (6), always (6), expectations (6), macroeconomic (6), them (6), based (6), problem (6), trying (6), lab (6), controlling (6), using (6), ignorability (6), pearl (6), comment (5), view (5), syll (5), now (5), varia (5), arbetslöshetssiffran (5), som (5), styr (5), like (5), why (5), paradox (5), out (5), many (5), just (5), mainstream (5), prediction (5), anything (5), after (5), think (5), still (5), give (5), hypothesis (5), observations (5), theoretical (5), evidence (5), rather (5), admitted (5), odds (5), well (5), people (5), done (5), rational (5), relations (5), without (5), long (5), inflation (5), thing (5), would (5), researchers (5), hours (5), tractability (5), conditional (5), independence (5), such (5), wokismus (5), eine (5), manipulations (5), mmt (5), theory (4), methodology (4), society (4), fred (4), time (4), policy (4), credibility (4), late (4), theorists (4), building (4), good (4), into (4), value (4), although (4), both (4), very (4), true (4), something (4), truth (4), warrant (4), correct (4), false (4), interesting (4), having (4), come (4), could (4), since (4), any (4), reality (4), unfortunately (4), run (4), says (4), mechanism (4), phenomenon (4), phenomena (4), response (4), back (4), approach (4), men (4), males (4), keynesians (4), microfoundations (4), robust (4), work (4), particular (4), between (4), used (4), worked (4), gap (4), nrh (4), called (4), higher (4), zlokovic (4), culture (4), manipulate (4), potential (4), usually (4), assumption (4), made (4), means (4), missingness (4), ist (4), einen (4), als (4), auf (4), modelers (4), away (4), answers (4), subscribe (3), follow (3), credible (3), built (3), believe (3), understand (3), social (3), years (3), attention (3), modern (3), reasoning (3), little (3), most (3), adequate (3), logically (3), etc (3), demand (3), stronger (3), plausibility (3), ask (3), robustness (3), claims (3), systems (3), suppose (3), original (3), exercise (3), find (3), empirical (3), scientists (3), facing (3), change (3), before (3), faith (3), testing (3), among (3), else (3), possible (3), mechanisms (3), simply (3), simpson (3), regression (3), against (3), apply (3), different (3), where (3), enough (3), structure (3), example (3), reduced (3), keep (3), pig (3), sure (3), price (3), dsge (3), macroeconomists (3), classical (3), economies (3), individuals (3), large (3), parameters (3), almost (3), questionable (3), representative (3), including (3), own (3), generated (3), relevant (3), tool (3), argument (3), around (3), vertical (3), self (3), advocates (3), interest (3), common (3), idea (3), sometimes (3), had (3), drug (3), study (3), experimental (3), confounding (3), understood (3), requires (3), gives (3), variable (3), wage (3), too (3), mathematical (3), inference (3), rubin (3), criterion (3), whether (3), nach (3), viktimisierung (3), fördern (3), dass (3), cancel (3), des (3), ihre (3), non (3), manipulable (3), rcm (3), frameworks (3), significant (3), dirk (3), ehnts (3), staatsschulden (3), don (3), required (2), manage (2), log (2), sign (2), subscribed (2), already (2), wordpress (2), com (2), blog (2), politics (2), reading (2), list (2), arbetslösheten (2), inte (2), wiklund (2), milch (2), recent (2), ones (2), irrelevant (2), remember (2), same (2), revolution (2), precision (2), finding (2), den (2), posts (2), page (2), winter (2), tale (2), robert (2), sugden (2), feeling (2), game (2), seriously (2), expect (2), count (2), part (2), life (2), making (2), ontological (2), become (2), understanding (2), logical (2), deduce (2), hypotheses (2), set (2), construct (2), form (2), dealing (2), conclusions (2), itself (2), asked (2), start (2), critical (2), considered (2), right (2), reason (2), theories (2), possibly (2), relevance (2), course (2), sensitivity (2), tested (2), target (2), per (2), opponent (2), proposed (2), implausible (2), merely (2), show (2), try (2), treat (2), theorist (2), audience (2), within (2), explanatory (2), scope (2), bad (2), suggest (2), interpretation (2), mind (2), present (2), david (2), describe (2), patterns (2), seen (2), observable (2), structures (2), explain (2), applying (2), admission (2), university (2), probabilities (2), females (2), seem (2), discriminated (2), female (2), giving (2), once (2), result (2), turn (2), physics (2), correlations (2), unless (2), factors (2), outcome (2), certainly (2), seems (2), traps (2), paul (2), krugman (2), reduce (2), intertemporal (2), sticky (2), lipstick (2), doesn (2), arguing (2), today (2), main (2), stickiness (2), business (2), developed (2), classicals (2), presuppose (2), emergent (2), simple (2), aren (2), deep (2), microeconomics (2), given (2), effects (2), actors (2), properties (2), characterize (2), level (2), easily (2), simplifications (2), keynes (2), argued (2), future (2), continue (2), conclusion (2), clear (2), forward (2), policies (2), however (2), end (2), provide (2), justification (2), aspirations (2), ultimate (2), see (2), ever (2), line (2), phillips (2), systematically (2), biased (2), plot (2), damage (2), again (2), independent (2), monetary (2), wrote (2), article (2), members (2), whistleblowers (2), experiments (2), examples (2), dossier (2), compound (2), obtained (2), small (2), encouraging (2), need (2), biotech (2), fraud (2), everything (2), risk (2), thereby (2), door (2), produced (2), excluded (2), works (2), included (2), hope (2), inferences (2), worse (2), words (2), sophisticated (2), tend (2), measure (2), dangers (2), precise (2), methodological (2), highly (2), arguments (2), invoked (2), distribution (2), observed (2), whereas (2), needed (2), rarely (2), available (2), purely (2), void (2), answer (2), none (2), defined (2), mantra (2), assume (2), evident (2), yet (2), blinds (2), graphical (2), graph (2), assuming (2), treatment (2), von (2), gerechtigkeit (2), kann (2), seine (2), kollektive (2), gegenüber (2), meinungen (2), gesellschaft (2), wichtig (2), führen (2), individuelle (2), autonomie (2), auch (2), neigt (2), dazu (2), gruppen (2), vielfalt (2), diese (2), bei (2), ihrer (2), wokisten (2), sich (2), individuen (2), angriff (2), pressefreiheit (2), upon (2), manipulation (2), require (2), hypothetical (2), scm (2), positions (2), regarding (2), race (2), looks (2), outcomes (2), represent (2), method (2), randomization (2), achieve (2), design (2), reaching (2), ability (2), guido (2), imbens (2), über (2), rigour (2), advanced (2), forget (2), mean (2), someone (2), improving (2), down (2), south (2), london (2), town (2), website, name, email, write, loading, collapse, bar, subscriptions, site, reader, report, content, privacy, account, join, 606, subscribers, feeds, entries, 112, archives, 707, 542, 998, 390, 301, education, school, 168, categories, fredtorssander, torssander, netiquette, especially, anonymous, pseudo, argumentations, abusive, language, links, please, full, professor, leaves, limited, respond, democracy, outperforms, dictatorship, reification, randomisation, guarantee, nancy, cartwright, contributions, philosophy, sverige, randomness, representativeness, statsskulden, problemet, ett, välförtjänt, bottenrekord, audioholic, summer, stein, lesson, unbiasedness, love, secret, student, stuff, efter, studenten, personal, ekonomiska, politiken, next, absolutely, fabulous, fellow, record, seminars, conferences, admit, playing, intended, feel, sufficiently, combative, spend, listening, expositions, spent, considerable, examining, reasonably, talents, attempt, urging, pay, foundations, sad, paid, increasingly, object, enquire, activities, point, par, export, certificates, presenting, possibilities, analytical, exercises, consciously, explicitly, deductive, nomological, event, occurrence, law, antecedent, initial, conditions, hempel, popper, explicit, sound, explanans, intend, escape, must, premises, deductions, supposed, follows, epistemology, ought, secondary, primary, first, ontology, thinking, necessary, half, century, disciplined, somehow, similar, investigating, though, simplify, serve, pursuit, unrealistic, falsehood, unrealisticness, qualified, resemblance, minimalist, epistemic, appropriate, similarity, ways, exporting, experiment, rejected, surprised, findings, knew, consistent, claimed, expected, deserve, going, created, customarily, presents, sufficient, related, raise, pertinent, temporary, promotes, his, reverting, knowledgeable, audiences, surely, amounts, acting, descriptive, aggressive, might, step, promoting, proof, concept, paradigm, itzhak, gilboa, andrew, postlewaite, larry, samuelson, schmeidler, practice, uncommon, establish, fact, clues, behind, operating, predict, correlate, regress, highlight, deficiency, traditional, toward, 1000, equal, amount, running, logistic, ratios, favourable, position, compared, male, ratio, departments, 800, 680, 200, 100, 900, 210, relate, specific, perspective, importantly, shows, miraculously, constant, influence, probability, studied, paradoxical, concur, mike, woodford, greg, mankiw, sorta, kinda, maximization, modified, prices, putting, rbc, help, importance, counter, helping, euler, equations, optimization, critique, didn, incorporate, cycles, adopted, suggested, added, naturally, infer, solely, extent, summation, micro, moreover, immutable, tastes, technology, bedrock, constancy, pretend, aggregation, presupposes, homothetic, identical, preferences, exists, therefore, capture, underlying, economy, critically, odd, neither, nor, congruent, getting, close, heart, darkness, rigorously, aggregate, reductionist, microfoundational, blind, eye, open, system, interaction, animal, spirits, trust, confidence, institutions, deduced, answerable, individual, analyzed, agree, emphasis, basically, inadmissible, project, history, consequently, identified, dynamic, stochastic, general, equilibrium, drawn, unstable, looking, optimizing, behavioural, stable, changes, couple, dead, realistic, informative, practitioners, investigate, effort, erect, fulfil, tasks, accomplishments, supportive, substantiate, critics, consider, mixture, unhelpful, metaphors, metaphysics, maintaining, remains, sceptic, pretences, yielded, keynesianism, useless, roger, farmer, tendency, points, lie, upward, sloping, closer, horizontal, unlikely, over, decades, conclude, fails, dramatically, simultaneously, decade, averages, reveal, policymakers, decisions, implement, austerity, measures, kill, expansion, unnecessary, costly, inflicted, flawed, illusion, eventuates, kept, accountable, amazes, pretty, cousin, curve, fundamental, block, empirically, falsified, neoclassical, neutrality, money, simplistic, excess, subject, water, describes, actually, existed, controversial, questioned, trade, sixty, ago, milton, friedman, famous, below, rise, busting, myth, speaking, anonymously, four, former, anomalies, found, accident, intimidation, regularly, pushed, others, adjust, two, said, notebooks, completed, ensure, contained, desired, him, instructing, fit, highlights, dozens, papers, supporting, ready, human, contain, seemingly, doctored, misconduct, 113, group, paints, picture, address, unmet, medical, food, administration, fda, gave, fast, track, status, prospect, accelerated, approval, priority, review, trial, few, months, gamble, seemed, warranted, longtime, grantee, prominent, southern, california, usc, neuroscientist, berislav, promising, safety, sponsored, company, founded, national, institutes, health, nih, placed, bet, limit, brain, strokes, kitchen, sink, haven, confounder, solution, collider, create, paths, wasn, begin, christopher, achen, preferable, separate, meaningful, subsets, internally, compatible, regimes, researcher, claiming, big, messy, jury, weak, somebody, convicted, scholars, shouldn, regressions, coefficients, due, specification, precisely, handful, established, spurious, observational, statisticians, econometricians, standardly, add, reliable, showed, 1930s, criticizing, applications, risks, producing, estimates, twice, include, ezra, klein, partly, isolate, fewer, vanishes, yglesias, silly, act, crazy, coincidence, shorter, housekeeping, assigned, bulk, childcare, responsibilities, tries, ends, controlled, starts, controls, specificity, ongoing, discussion, build, maintain, tried, support, conviction, microfounded, care, final, court, appeal, convincing, put, inferential, bridging, modelbuilding, hand, waving, inductive, substantive, posed, formalistic, representations, utilized, analyze, match, facto, misuse, tractable, great, simplifying, agents, linearity, additivity, ergodicity, exchangeability, otherwise, rigorous, predictions, explanations, exempt, justify, choices, choice, realist, case, clarification, goal, whole, endeavour, solve, exemplifies, override, judea, karthika, mohan, convince, staunchest, enthusiast, switch, mantras, quite, define, fundamentally, presumed, governs, independencies, assumed, partially, necessarily, judgmental, testable, implications, claim, concerning, possibility, free, indeed, pose, totally, vocabulary, trivial, estimable, likelihood, function, flat, argue, conceptualized, 1976, notion, reference, causation, continues, chanted, increasing, intensity, faithful, luring, chanters, seeing, improved, emerge, abandoning, prism, altogether, conducting, habitat, unruly, readers, versed, modeling, students, learn, second, class, vowed, avoid, cost, interpreted, verified, background, presented, imagine, turns, frightening, enigma, shun, light, graphs, simplicity, makes, easy, rely, heavily, discomforting, adhering, invariably, invoke, hoc, decorated, ignorable, assignment, let, alone, judge, obwohl, einem, wunsch, sozialer, motiviert, sein, entscheidend, problematischen, implikationen, untersuchen, intoleranz, abweichenden, behindern, fortschritt, einer, inklusiveren, gerechteren, offenen, dialog, nuancierteren, ausgewogeneren, ansatz, für, soziale, fragen, sowohl, echte, suche, schätzt, unterschiede, zwischen, essentialisieren, vereinfachte, stereotypisierte, sicht, schaffen, leugnet, innerhalb, jeder, gruppe, indem, annimmt, alle, mitglieder, gleichen, erfahrungen, perspektiven, teilen, übermäßige, verallgemeinerung, vorurteilen, umgekehrter, diskriminierung, bestimmte, einfach, aufgrund, identität, bevorzugt, werden, zensur, meinungsfreiheit, einzuschränken, übernehmen, oft, mentalität, versuchen, jede, abweichende, stimme, oder, meinung, zum, schweigen, bringen, anstatt, begünstigt, engen, ideologischen, konformismus, dem, nur, legitim, betrachtetes, denken, akzeptiert, wird, ein, besorgniserregender, aspekt, besessenheit, konzentrieren, anstelle, individuums, sie, klassifizieren, zugehörigkeit, identitätsgruppen, weisen, ihnen, opferstatus, gemäß, diesen, kriterien, herangehensweise, reduziert, gruppenidentität, untergräbt, fähigkeit, einzigartige, personen, verwirklichen, naftali, weinberger, admittedly, assert, intervene, specifying, perhaps, lady, nature, herself, coherent, debatable, resolving, debate, careful, purportedly, willingness, interventions, abstracts, concrete, unsurprising, tolerance, talk, themselves, settle, adopt, conflicting, certain, forced, moves, thorny, debates, slightly, contentious, obesity, link, structural, formally, operator, asserts, while, deny, causes, holland, 1986, 2008, arguably, experimentally, manipulated, key, manipulability, wonkish, believing, market, validity, searching, methods, contexts, better, insisting, wrong, accept, limitation, kind, average, instrumental, designs, major, strategies, formulations, order, exact, becomes, clever, place, draw, generalize, larger, populations, type, negative, bias, towards, prioritizing, selection, planning, ultimately, lies, citizens, focusing, narrow, threatens, lead, sceptical, deliver, useful, insistence, schätze, eher, pragmatische, haltung, frage, umgangs, mit, warnt, davor, theorie, art, allheilmittel, betrachten, betont, notwendigkeit, anwendung, prinzipien, spezifischen, gegebenheiten, eines, landes, anzupassen, zudem, weist, darauf, hin, hohe, haushaltsdefizite, nicht, zwangsläufig, vorteilhaft, sind, vernünftige, haushaltsführung, weiterhin, bleibt, andere, wirtschaftliche, herausforderungen, vermeiden, dieses, interview, wirklich, hörenswert, reasons, verisimilitude, encountered, taking, degree, deceptive, appearance, constructed, technically, discussed, swept, under, carpet, coin, flips, imaginary, superpopulation, asking, nowadays, truism, backed, legions, theorems, proved, heaps, fiction, masquerading, frequently, supported, dave, giles, peer, reviewed, best, practices, followed, published, fraction, author, publishing, computer, code, application, produces, hendry, pre, raises, issues, analyse, exactly, obtain, relating, estimator, check, statistically, numerically, economically, yourself, sense, quantity, quality, unforgettable, gretl, downloadable, publications, lps,
Text of the page (random words):
aatsschulden mmt 29 nov 2023 at 18 26 posted in economics comments off on dirk ehnts über staatsschulden mmt dieses interview ist wirklich hörenswert yours truly schätze dirk ehnts eher pragmatische haltung gegenüber mmt und der frage des umgangs mit staatsschulden er warnt davor die mmt theorie als eine art allheilmittel zu betrachten er betont die notwendigkeit die anwendung der mmt prinzipien an die spezifischen gegebenheiten eines landes anzupassen zudem weist er darauf hin dass hohe haushaltsdefizite nicht zwangsläufig vorteilhaft sind und dass eine vernünftige haushaltsführung weiterhin wichtig bleibt um inflation und andere wirtschaftliche herausforderungen zu vermeiden share on facebook opens in new window facebook share on x opens in new window x share on bluesky opens in new window bluesky guido imbens on the response to late 29 nov 2023 at 10 45 posted in statistics econometrics comments off on guido imbens on the response to late many economists yours truly included are highly sceptical of the ability of mainstream economics to deliver useful models some of us even question the modern insistence on modelling if it s not in a model it s not economics even if we accept the limitation of only being able to say something about some kind of average treatment effects when using instrumental variables designs a significant and major problem is that researchers who use these randomization based research strategies often set up problem formulations that are not at all the ones we really want answers to in order to achieve exact and precise results design becomes the main thing and as long as one can get more or less clever experiments in place they believe they can draw far reaching conclusions about both causality and the ability to generalize experimental outcomes to larger populations unfortunately this often means that this type of research has a negative bias away from interesting and important problems towards prioritizing method selection design and research planning are important but the credibility of research ultimately lies in being able to provide answers to relevant questions that both citizens and researchers want answers to focusing on finding narrow late results threatens to lead research away from the really important research questions we as social scientists want to answer believing there is only one really good evidence based method on the market and that randomization is the only way to achieve scientific validity blinds people to searching for and using other methods that in many contexts are better insisting on using only one tool often means using the wrong tool share on facebook opens in new window facebook share on x opens in new window x share on bluesky opens in new window bluesky manipulability pearl vs rubin wonkish 27 nov 2023 at 19 23 posted in statistics econometrics 1 comment pearl asserts while some rcm rubin causal models theorists deny that so called non manipulable variables can be causes pearl 2019 holland 1986 2008 race and gender which arguably cannot be experimentally manipulated are key examples of such variables my response is that although advocates of the frameworks adopt conflicting positions regarding certain variables these positions are not forced upon them by their frameworks when one moves away from thorny variables such as race and gender and looks at debates regarding slightly less contentious variables such as obesity whereas rcm modelers link potential outcomes to particular experimental manipulations scm structural causal models modelers represent manipulations by formally applying the do operator to variables in a graph admittedly pearl does assert that that one can intervene upon gender without specifying a manipulation he would however require do gender to be well defined which requires there be at least hypothetical manipulations on gender perhaps available only to lady nature herself pearl 2018 p 4 whether such a manipulation is coherent is debatable and resolving this debate would require careful attention to the purportedly non manipulable variable given scm modelers willingness to characterize interventions in a way that abstracts away from concrete manipulations it is unsurprising that they would have a higher tolerance than rcm modelers for talk of hypothetical manipulations yet the frameworks themselves do not settle what one should say about particular non manipulable variables naftali weinberger share on facebook opens in new window facebook share on x opens in new window x share on bluesky opens in new window bluesky cancel culture angriff auf die pressefreiheit 26 nov 2023 at 12 08 posted in politics society comments off on cancel culture angriff auf die pressefreiheit ein besorgniserregender aspekt des wokismus ist seine besessenheit von viktimisierung die wokisten konzentrieren sich auf kollektive viktimisierung anstelle des individuums sie klassifizieren individuen nach ihrer zugehörigkeit zu identitätsgruppen und weisen ihnen einen opferstatus gemäß diesen kriterien zu diese herangehensweise reduziert individuen auf ihre gruppenidentität und untergräbt so ihre autonomie und ihre fähigkeit sich als einzigartige personen zu verwirklichen wokismus neigt auch dazu zensur zu fördern und die meinungsfreiheit einzuschränken wokisten übernehmen oft eine mentalität der cancel culture und versuchen jede abweichende stimme oder meinung zum schweigen zu bringen anstatt die vielfalt der meinungen zu fördern begünstigt der wokismus einen engen ideologischen konformismus bei dem nur als legitim betrachtetes denken akzeptiert wird wokismus neigt dazu unterschiede zwischen gruppen zu essentialisieren und so eine vereinfachte und stereotypisierte sicht der gesellschaft zu schaffen er leugnet die individuelle vielfalt innerhalb jeder gruppe indem er annimmt dass alle mitglieder die gleichen erfahrungen und perspektiven teilen diese übermäßige verallgemeinerung kann zu vorurteilen und umgekehrter diskriminierung führen bei der bestimmte gruppen einfach aufgrund ihrer identität bevorzugt werden obwohl der wokismus von einem wunsch nach sozialer gerechtigkeit motiviert sein kann ist es entscheidend seine problematischen implikationen zu untersuchen kollektive viktimisierung und intoleranz gegenüber abweichenden meinungen behindern den fortschritt zu einer inklusiveren und gerechteren gesellschaft es ist wichtig einen offenen dialog zu führen und einen nuancierteren und ausgewogeneren ansatz für soziale fragen zu fördern der sowohl individuelle autonomie als auch eine echte suche nach gerechtigkeit schätzt share on facebook opens in new window facebook share on x opens in new window x share on bluesky opens in new window bluesky ignorability a questionable assumption 25 nov 2023 at 18 59 posted in statistics econometrics 1 comment researchers adhering to missing data analysis invariably invoke an ad hoc assumption called conditional ignorability often decorated as ignorable treatment assignment mechanism which is far from being well understood by those who make it let alone those who need to judge its plausibility for readers versed in graphical modeling conditional ignorability is none other than the back door criterion that students learn in the second class on causal inference and which missing data advocates have vowed to avoid at all cost as we know this criterion can easily be interpreted and verified when background knowledge is presented in graphical form but as you can imagine it turns into a frightening enigma for those who shun the light of graphs still the simplicity of reading this criterion off a graph makes it easy to test whether those who rely heavily on ignorability assumptions know what they are assuming the results of this test are discomforting unfortunately the mantra missing data analysis in causal inference is well understood continues to be chanted at an ever increasing intensity building faith among the faithful and luring chanters to assume ignorability as self evident worse yet the mantra blinds researchers from seeing how an improved level of understanding can emerge by abandoning the missing data prism altogether and conducting causal analysis in its natural habitat using scientific models of reality rather than unruly patterns of missingness in the data we come now to claim 2 concerning the possibility of causality free interpretation of missing data problems it is possible indeed to pose a missing data problem in purely statistical terms totally void of missingness mechanism vocabulary void even of conditional independence assumptions but this is rarely done because the answer is trivial none of the parameters of interest would be estimable without such assumptions i e the likelihood function is flat in theory one can argue that there is really nothing causal about missingness mechanism as conceptualized by rubin 1976 since it is defined in terms of conditional independence relations a purely statistical notion that requires no reference to causation not quite the conditional independence relations that define missingness mechanisms are fundamentally different from those invoked in standard statistical analysis in standard statistics independence assumptions are presumed to hold in the distribution that governs the observed data whereas in missing data problems the needed independencies are assumed to hold in the distribution of variables which are only partially observed in other words the independence assumptions invoked in missing data analysis are necessarily judgmental and only rarely do they have testable implications in the available data we hope these arguments convince even the staunchest missing data enthusiast to switch mantras and treat missing data problems for what they are causal inference problems judea pearl karthika mohan an interesting article on a highly questionable assumption used in potential outcome causal models it also exemplifies how tractability often has come to override reality and truth in science not least in modern mainstream economics a tractable model is of course great since it usually means you can solve it but using simplifying tractability assumptions rational expectations common knowledge representative agents linearity additivity ergodicity exchangeability ignorability etc because otherwise they cannot manipulate their models or come up with rigorous and precise predictions and explanations does not exempt scientists from having to justify their modelling choices being able to manipulate things in models cannot per se be enough to warrant a methodological choice suppose economists do not really think their tractability assumptions make for good and realist models in that case it is certainly a just question to ask for clarification of the ultimate goal of the whole modelling endeavour take for example the ongoing discussion on rational expectations as a modelling assumption in economics those who want to build macroeconomics on microfoundations usually maintain that the only robust policies are those based on rational expectations and representative actors models as yours truly has tried to show in on the use and misuse of theories and models in mainstream economics there is really no support for this conviction at all if microfounded macroeconomics has nothing to say about the real world and the economic problems out there why should we care about it the final court of appeal for macroeconomic models is not if we once we have made our tractability assumptions can manipulate them but the real world and as long as no convincing justification is put forward for how the inferential bridging de facto is made macroeconomic modelbuilding is little more than hand waving that gives us rather a little warrant for making inductive inferences from models to real world target systems if substantive questions about the real world are being posed it is the formalistic mathematical representations utilized to analyze them that have to match reality not the other way around share on facebook opens in new window facebook share on x opens in new window x share on bluesky opens in new window bluesky the dangers of too much control 23 nov 2023 at 15 41 posted in statistics econometrics comments off on the dangers of too much control you see it all the time in studies we controlled for and then the list starts the more things you can control for the stronger your study is or at least the stronger your study seems controls give the feeling of specificity of precision but sometimes you can control for too much sometimes you end up controlling for the thing you re trying to measure an example is research around the gender wage gap which tries to control for so many things that it ends up controlling for the thing it s trying to measure take hours worked which is a standard control in some of the more sophisticated wage gap studies women tend to work fewer hours than men if you control for hours worked then some of the gender wage gap vanishes as yglesias wrote it s silly to act like this is just some crazy coincidence women work shorter hours because as a society we hold women to a higher standard of housekeeping and because they tend to be assigned the bulk of childcare responsibilities controlling for hours worked in other words is at least partly controlling for how gender works in our society it s controlling for the thing that you re trying to isolate ezra klein trying to reduce the risk of having established only spurious relations when dealing with observational data statisticians and econometricians standardly add control variables the hope is that one thereby will be able to make more reliable causal inferences but as keynes showed already back in the 1930s when criticizing statistical econometric applications of regression analysis if you do not manage to get hold of all potential confounding factors the model risks producing estimates of the variable of interest that are even worse than models without any control variables at all conclusion think twice before you simply include control variables in your models when i present this argument one or more scholars say but shouldn t i control for everything i can in my regressions if not aren t my coefficients biased due to excluded variables the excluded variable argument only works if you are sure your specification is precisely correct with all variables included but no one can know that with more than a handful of explanatory variables a preferable approach is to separate the observations into meaningful subsets internally compatible statistical regimes if this can t be done then statistical analysis can t be done a researcher claiming that nothing else but the big messy regression is possible because after all some results have to be produced is like a jury that says well the evidence was weak but somebody had to be convicted christopher h achen kitchen sink econometric models are often the result of researchers trying to control for confounding bu...
|
