Wage discrimination and the dangers of ‘controlling for’ confounders

24 augusti, 2018 kl. 09:08 | Publicerat i Economics, Statistics & Econometrics | Kommentarer inaktiverade för Wage discrimination and the dangers of ‘controlling for’ confounders

You see it all the time in studies. ”We controlled for…” And then the list starts. The longer the better. Income. Age. Race. Religion. Height. Hair color. Sexual preference. Crossfit attendance. Love of parents. Coke or Pepsi. 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 …

wage-gapThe problem with controls is that it’s often hard to tell the difference between a variable that’s obscuring the thing you’re studying and a variable that is the thing you’re studying.

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. As my colleague Matt Yglesias wrote:

”The commonly cited statistic that American women suffer from a 23 percent wage gap through which they make just 77 cents for every dollar a man earns is much too simplistic. On the other hand, the frequently heard conservative counterargument that we should subject this raw wage gap to a massive list of statistical controls until it nearly vanishes is an enormous oversimplification in the opposite direction. After all, for many purposes gender is itself a standard demographic control to add to studies — and when you control for gender the wage gap disappears entirely! The question to ask about the various statistical controls that can be applied to shrink the gender gap is what are they actually telling us. The answer, I think, is that it’s telling how the wage gap works.”

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

The gender pay gap is a fact that, sad to say, to a non-negligible extent is the result of discrimination. And even though many women are not deliberately discriminated against, but rather self-select into lower-wage jobs, this in no way magically explains away the discrimination gap. As decades of socialization​ research has shown, women may be ‘structural’ victims of impersonal social mechanisms that in different ways aggrieve them. Wage discrimination is unacceptable. Wage discrimination​ is a shame.

The cost of focusing on general equilibrium theory

24 augusti, 2018 kl. 07:34 | Publicerat i Economics | 2 kommentarer

The largest problem with the economics profession’s focus on general equilibrium theory is the opportunity costs of that exploration. Important policy problems are not addressed. Consider Pareto optimality and the welfare theorems, which Fisher sees as the underpinnings of Western capitalism. In a world, such as ours, where property rights cannot be allocated effortlessly and costlessly, economist’s welfare theorems have little policy relevance. Does a policy maker care whether any Pareto efficient allocation can be decentralized as a competitive general equilibrium? The chance of discovering a real-world Pareto optimal policy that can be shown to harm no one in some infinitesimal way is essentially nil.

what ifBy focusing their theoretical policy analysis on Pareto optimal policies, economists avoid coming to grips theoretically with the messy value judgments that must be made in the policy space, which means that their theoretical models provide little guidance on how to deal with the messy problems of actual policy that are designed to achieve both efficiency and fairness. In its almost exclusive focus on efficiency, modern economists have moved away from Classical economist’s utilitarian moral philosophy that underlay Classical economist’s support of markets. Classical economists supported markets because they worked reasonably well in the real world, not because of any deductive proof of the benefits of markets.

Dave Colander

Reformulating the economics curriculum

23 augusti, 2018 kl. 07:49 | Publicerat i Economics | 2 kommentarer

Having gone through a handful of the most frequently used textbooks of economics at the undergraduate level today, I can only conclude that the models that are presented in these modern mainstream textbooks try to describe and analyze complex and heterogeneous real economies with a single rational-expectations-robot-imitation-representative-agent.

madiThat is, with something that has absolutely nothing to do with reality. And — worse still — something that is not even amenable to the kind of general equilibrium analysis that they are thought to give a foundation for, since Hugo Sonnenschein (1972), Rolf Mantel (1976) and Gérard Debreu (1974) unequivocally showed that there did not exist any condition by which assumptions on individuals would guarantee neither stability nor uniqueness of the equilibrium solution.

So what modern economics textbooks present to students are really models built on the assumption that an entire economy can be modelled as a representative actor and that this is a valid procedure. But it is not, as the Sonnenschein-Mantel-Debreu theorem irrevocably has shown.

Of course one could say that it is too difficult on undergraduate levels to show why the procedure is right and to defer it to master and doctoral courses. It could justifiably be reasoned that way — if what you teach your students is true, if The Law of Demand is generalizable to the market level, and the representative actor is a valid modelling abstraction! But in this case, it is demonstrably known to be false, and therefore this is nothing but a case of scandalous intellectual dishonesty. It’s like telling your students that 2 + 2 = 5 and hope that they will never run into Peano’s axioms of arithmetics.

For almost forty years mainstream economics itself has lived with a theorem that shows the impossibility of extending the microanalysis of consumer behaviour to the macro level (unless making patently and admittedly ridiculous assumptions). Still after all these years pretending in their textbooks that this theorem does not exist — none of the textbooks I investigated even mention the existence of the Sonnenschein-Mantel-Debreu theorem — is really outrageous.

Uppdrag granskning och sveket mot våldtäktsoffren

22 augusti, 2018 kl. 19:12 | Publicerat i Politics & Society | 3 kommentarer

grafik3-jpgYours truly såg idag ett intressant avsnitt av SvT:s Uppdrag granskning.

Programmet handlade om att män födda i utlandet är kraftigt överrepresenterade bland de som dömts för att ha begått våldtäkt i Sverige — och, enkannerligen, om varför ledande svenska politiker och brottsforskare inte tyckt att det har varit viktigt eller speciellt intressant att statistiskt belägga våldtäktsmännens etnicitet. Skälet som åberopats av politiker (som t ex Morgan Johansson) och forskare (som t ex Jerzy Sarnecki) är att de TROR att de huvudsakliga orsaksfaktorerna är socio-ekonomiska och att fokus på etnicitet bara skulle spela rasism och utlänningsfientlighet i händerna.

Detta försök till bortförklaring är inget konstigt eller ovanligt — åtminstone om vi talar om politik och medier. Där sysslar man dagligen med den typen av resonemang som bygger på haltande logik och halvsanningar. Mer anmärkningsvärt och mer kritisabelt är det när även forskare hänger sig åt dylikt.

För de flesta sociala fenomen föreligger mekanismer och orsakskedjor som till stor del ytterst går att hänföra till socio-ekonomiska faktorer. Så även med stor sannolikhet när det gäller våldsbrott och mer specifikt våldtäktsbrott. Detta betyder dock ingalunda att man vid exempelvis en statistisk regressionsanalys med ‘konstanthållande’ av socio-ekonomiska variabler helt restlöst skulle i någon kausal mening kunna trolla bort andra viktiga faktorer som etnicitet, kultur, etc.

Och detta är pudelns kärna! Socio-ekonomiska faktorer ÄR viktiga. Men så även andra faktorer. Att dessa i någon mening skulle kunna uppfattas som ‘känsliga’ att kartlägga är inget försvar för att i vetenskapliga sammanhang blunda för dem — något som borde vara självklart även för Brottsförebyggande rådet och Jerzy Sarnecki.

Inte minst Sarnecki har under lång tid och vid upprepade tillfällen tvärsäkert hävdat att våldtäkter bara kan förstås och förklaras som resultat av socio-ekonomiska faktorer. Några entydga evidensbaserade forskningsresultat som skulle kunna utgöra grund för denna tvärsäkerhet föreligger dock inte.

Att hävda att det kan finnas andra faktorer — som t ex etnicitet och kultur — stämplas som ‘farligt’. Detta är långt ifrån första gången i historien som ny kunskap, data och vetenskapliga teorier ifrågasätts utifrån en rädsla för att de kan ha negativa samhälleliga konsekvenser (Galileos och Darwins nya fakta och kunskaper om astronomi och evolution möttes först med invändningar och krav på hemlighållande från dåtidens etablissemang).

‘Fakta sparkar’ som Gunnar Myrdal brukade säga. Att av rädsla för att fakta kan missbrukas välja att mörklägga information om stora och viktiga samhällsproblem som våldtäkter är fullständigt oacceptabelt. Det är ett svek både mot samhället i stort och personer som utsätts för brotten.

Mer — inte mindre — fakta och kunskap, är en förutsättning för att på ett effektivt sätt kunna minska förekomsten av våldtäkter och andra brott i vårt samhälle. Ett samhälle måste ha förtroende för sina medborgares förmåga att hantera information. Avsaknad av det förtroendet är något som vi förknippar med auktoritära samhällen. I en demokrati mörklägger man inte information!

August 21, 1968 — a date which will live in infamy

21 augusti, 2018 kl. 14:33 | Publicerat i Politics & Society | Kommentarer inaktiverade för August 21, 1968 — a date which will live in infamy

 

 
bu

Donald Rubin on randomization and observational studies

21 augusti, 2018 kl. 12:48 | Publicerat i Theory of Science & Methodology | Kommentarer inaktiverade för Donald Rubin on randomization and observational studies

 

Econophysics

20 augusti, 2018 kl. 15:15 | Publicerat i Economics | 1 kommentar

Unfortunately, nothing is more dangerous than dogmas donned with scientific feathers. The current crisis might offer an excellent occasion for a paradigm
change, previously called for by prominent economists like John Maynard Keynes, Alan Kirman and Steve Keen. They have forcefully highlighted the shortcomings
and contradictions of the classical economic theory, but progress has been slow. The task looks so formidable that some economists argue that it is better to stick with the implausible but well-corseted theory of perfectly rational agents than to venture into modelling the infinite number of ways agents can be irrational.

miracle_cartoonPhysicists, however, feel uncomfortable with theories not borne out by (or even blatantly incompatible with) empirical data. But could the methodology of physics really contribute to the much-awaited paradigm shift in economics? …

Econophysics is in fact a misnomer, since most of its scope concerns financial markets. To some economists, finance is a relatively minor subfield and any contribution, even the most significant, can only have a limited impact on economics science at large. I personally strongly disagree with this viewpoint: recent events confirm that hiccups in the financial markets can cripple the entire economy.

From a more conceptual point of view, financial markets are an ideal laboratory for testing several fundamental concepts of economics. Are prices really such that supply matches demand? Are price moves primarily due to news? (The answer to both these questions seem to be clear “no”) … As I will try to illustrate, the very choice of the relevant questions, which ultimately leads to a deeper understanding of the data, is often sheer serendipity: more of an art than a science. That intuition, it seems to me, is well nurtured by an education in the natural sciences, where the emphasis is on mechanisms and analogies, rather than on axioms and theorem proving.

Jean-Philippe Bouchaud

Steven Pinker — a cherry-picking​ Panglossian

20 augusti, 2018 kl. 12:50 | Publicerat i Politics & Society | 5 kommentarer

 

Why most published research findings are false

19 augusti, 2018 kl. 10:45 | Publicerat i Statistics & Econometrics | Kommentarer inaktiverade för Why most published research findings are false

Instead of chasing statistical significance, we should improve our understanding of the range of R values — the pre-study odds — where research efforts operate. Before running an experiment, investigators should consider what they believe the chances are that they are testing a true rather than a non-true relationship. Speculated high R values may sometimes then be ascertained … Large studies with minimal bias should be performed on research findings that are considered relatively established, to see how often they are indeed confirmed. I suspect several established “classics” will fail the test.

homer-stats-quoteNevertheless, most new discoveries will continue to stem from hypothesis-generating​ research with low or very low pre-study odds. We should then acknowledge that statistical significance testing in the report of a single study gives only a partial picture, without knowing how much testing has been done outside the report and in the relevant field at large. Despite a large statistical literature for multiple testing corrections, usually it is impossible to decipher how much data dredging by the reporting authors or other research teams has preceded a reported research finding. Even if determining this were feasible, this would not inform us about the pre-study odds. Thus, it is unavoidable that one should make approximate assumptions on howmany relationships are expected to be true among those probed across the relevant research fields and research designs.​

John P. A. Ioannidis

The rational expectations hoax

18 augusti, 2018 kl. 16:29 | Publicerat i Economics | Kommentarer inaktiverade för The rational expectations hoax

how-many-irrational-assumptions-are-needed-for-economist-to-use-rational-expectationsA lot of mainstream economists still stick with ‘rational expectations’ since they think it has not yet been disconfirmed. They are, of course, entitled to have whatever views they like — after all, it is, to say the least, difficult to empirically disconfirm the non-existence of Gods …

But for the rest of us, let’s see how rational expectations really fare​ as an empirical assumption. Empirical efforts at testing the correctness​​s of the hypothesis have​​ resulted in a series of empirical studies that have more or less concluded that it is not consistent with the facts. In one of the more well-known and highly respected evaluation reviews made, Michael Lovell (1986) concluded:

it seems to me that the weight of empirical evidence is sufficiently strong to compel us to suspend belief in the hypothesis of rational expectations, pending the accumulation of additional empirical evidence.

And this is how Nikolay Gertchev summarizes studies on the empirical correctness of the hypothesis:

More recently, it even has been argued that the very conclusions of dynamic models assuming rational expectations are contrary to reality: ”the dynamic implications of many of the specifications that assume rational expectations and optimizing behavior are often seriously at odds with the data” (Estrella and Fuhrer 2002, p. 1013). It is hence clear that if taken as an empirical behavioral assumption, the RE hypothesis is plainly false; if considered only as a theoretical tool, it is unfounded and self-contradictory​.

For more on the issue, permit me to self-indulgently recommend reading my article Rational expectations — a fallacious foundation for macroeconomics in a non-ergodic world in Real-World Economics Review no. 62.

Inequality perspectives

18 augusti, 2018 kl. 16:03 | Publicerat i Varia | 1 kommentar

sassy

”I never learned maths, so I had to think”

17 augusti, 2018 kl. 20:54 | Publicerat i Economics | 2 kommentarer

Professors may find themselves ill-prepared for the macro classroom. To become academics they had to answer erudite questions posed by more senior members of the discipline. To become good teachers of introductory macro, they have to give clear answers to muddled students. That requires an intuitive feel for the subject. It is not enough to crank through the equations.

rowe Indeed, Mr Rowe attributes part of his success as a teacher to his shortcomings as a mathematician. He quotes Joan Robinson, another clear expositor of macroeconomics: “I never learned maths, so I had to think.” Because the answers did not leap out at him from the equations, he had to dwell on the economic behaviour underneath the algebra.

Macroeconomics is difficult to teach partly because its theorists (classical, Keynesian, monetarist, New Classical and New Keynesian, among others) disagree about so much. It is difficult also because the textbooks disagree about so little.

The Economist

On tour

14 augusti, 2018 kl. 12:35 | Publicerat i Economics, Varia | Kommentarer inaktiverade för On tour

Touring again. Regular blogging to be resumed during the weekend.

Easterlin’s paradox or why economic growth does not make us happier

12 augusti, 2018 kl. 16:02 | Publicerat i Economics | 3 kommentarer

In Easterlin’s (1974) seminal paper, he finds that within any one country, in cross sectional studies, there was a strong correlation between income and happiness. One would easily conclude that money can buy happiness. However, looking at a cross section of countries, one comes to a different conclusion …

For 10 of the 14 countries surveyed, the happiness ranking is about the same, even though the income per capita changes by a factor of 30 from $140 to $2,000 …

easterlinThe finding of strong correlation between income and happiness disappears when comparisons are made across countries. Similarly, there is no correlation between happiness and income in the long run within a single country … Easterlin (2001) cites several studies which show that, despite tremendous increases in GNP per capita, the level of happiness in European and Latin American has remained virtually constant over decades.

The startling implication of these empirical findings is that the stress being placed on economic growth is entirely misplaced. Growth has no clear relation to happiness. The profession of economics, as well as policy makers all over the world are directly threatened by these findings, which suggest radical changes in how to organise economic affairs …

The implicit proposition of utility theory that the sole route to happiness is maximisation of consumption contradicts with the empirical evidence: this proposition is true only in the short run. This short run validity creates a dangerous illusion of long run validity; understanding this has dramatic policy implications. If happiness is determined by relative comparisons, then one can achieve greater happiness by reducing inequalities, and also by reducing the standards of living for everyone. This will lower the benchmark and make it easier for everyone on the planet to be happy in comparison with this benchmark.

Asad Zaman & Mehmet Karacuka

So much for value-free economics

12 augusti, 2018 kl. 15:28 | Publicerat i Economics | 1 kommentar

Back in 1992, New Jersey raised the minimum wage by 18 per cent while its neighbour state, Pennsylvania, left its minimum wage unchanged. Unemployment in New Jersey should — according to mainstream economics textbooks — have increased relative to Pennsylvania. However, when economists David Card and Alan Krueger gathered information on fast food restaurants in the two states, it turned out that unemployment had actually decreased in New Jersey relative to that in Pennsylvania. Counter to mainstream demand theory we had an anomalous case of a backward-sloping supply curve.

And, of course, all those non-ideological and value-free scientific economists out there were überjoyed and prepared to revise their theories …

jp-imgresI’ve subsequently stayed away from the minimum wage literature for a number of reasons. First, it cost me a lot of friends. People that I had known for many years, for instance, some of the ones I met at my first job at the University of Chicago, became very angry or disappointed. They thought that in publishing our work we were being traitors to the cause of economics as a whole.

David Card

Money in perspective

12 augusti, 2018 kl. 13:17 | Publicerat i Economics | 4 kommentarer

keWhen the accumulation of wealth is no longer of high social importance, there will be great changes in the code of morals. We shall be able to rid ourselves of many of the pseudo-moral principles which have hag-ridden us for two hundred years, by which we have exalted some of the most distasteful of human qualities into the position of the highest virtues. We shall be able to afford to dare to assess the money-motive at its true value. The love of money as a possession — as distinguished from the love of money as a means to the enjoyments and realities of life — will be recognized for what it is, a somewhat disgusting morbidity, one of those semi-criminal, semi-pathological propensities which one hands over with a shudder to the specialists in mental disease.

Another cup of coffee

12 augusti, 2018 kl. 11:52 | Publicerat i Varia | 1 kommentar

At last (on Via Garibaldi, Genova) we found a cup big enough for the morning coffee needs of my better half …

20180812_182052952054216.jpg

Being an economist, I, of course, came to think of a famous experiment involving coffee …

Pros. Kahneman, Knetsch & Thaler conducted a study to see how the endowment effect influences our decision making.

The scientists randomly divided participants into buyers and sellers and gave the sellers coffee mugs as a gift. They then asked the sellers for how much they would sell the mug and asked the buyers for how much they would buy it.

EndowmentEffectResults showed that the sellers (who owned the mugs) placed a significantly higher value on the mugs than the buyers did. They were willing to sell a mug for $7.12 while buyers were willing to pay $2.87 (median reservation prices).

People appreciate things that they already own more than those which they might own. The fear of losing the mug (loss aversion) becomes the cause of the contradiction in the evaluation of the cost of the coffee mug.

Mein Herr und mein Gott

11 augusti, 2018 kl. 22:46 | Publicerat i Varia | Kommentarer inaktiverade för Mein Herr und mein Gott

 

Modern macro — a total waste​ of time

11 augusti, 2018 kl. 11:33 | Publicerat i Economics | 2 kommentarer

While one can understand that some of the elements in DSGE models seem to appeal to Keynesians at first sight, after closer examination, these models are in fundamental contradiction to Post-Keynesian and even traditional Keynesian thinking. The DSGE model is a model in which output is determined in the labour market as in New Classical models and in which aggregate demand plays only a very secondary role, even in the short run.

In addition, given the fundamental philosophical problems presented for the use of DSGE models for policy simulation, namely the fact that a number of parameters used have completely implausible magnitudes and that the degree of freedom for different parameters is so large that DSGE models with fundamentally different parametrization (and therefore different policy conclusions) equally well produce time series which fit the real-world data, it is also very hard to understand why DSGE models have reached such a prominence in economic science in general.

Sebastian Dullien

Neither New Classical nor ‘New Keynesian’ microfounded DSGE macro models have helped us foresee, understand or craft solutions to the problems of today’s economies. But still most young academic macroeconomists want to work with DSGE models. UnknownAfter reading Dullien’s article, that certainly should be a very worrying confirmation of economics — at least from the point of view of realism and relevance — becoming more and more a waste of time. Why do these young bright guys waste their time and efforts? I think maybe Frank Hahn gave the truest answer when interviewed on the occasion of his 80th birthday, he confessed that some economic assumptions didn’t really say anything about ‘what happens in the world,’ but still had to be considered very good ‘because it allows us to get on this job.’

The Gray Ghost

10 augusti, 2018 kl. 16:57 | Publicerat i Varia | Kommentarer inaktiverade för The Gray Ghost

 

For Tora and David, with whom, when they were just little kids, I spent hours and hours watching this​ series back at​ the beginning of the 90’s.
They were my heroes then.
They still are.

« Föregående sidaNästa sida »

Blogga med WordPress.com.
Entries och kommentarer feeds.