Entrepreneurial Ability as a Latent Variable
28 November 2010 at 4:58 pm Peter G. Klein 13 comments
| Peter Klein |
It’s the weekend after Thanksgiving, so naturally I’m thinking about residuals — not leftover turkey and cranberry sauce, but entrepreneurial characteristics and behaviors as residuals, as latent variables that leave traces in outcomes that we can’t otherwise explain. I’ve argued before that common measures of entrepreneurship such as startups, self-employment, patents, venture funding, etc., while related to entrepreneurship, are epiphenomena, manifestations of an underlying, unobservable attribute or behavior such as judgment, alertness, innovation, or adaptation. (These are difficult, if not impossible, to measure directly; asking survey respondents, for instance, “How many opportunities did you identify this month?” is not quite the same thing as measuring Kirznerian alertness!) In a recent musing on strategic entrepreneurship I suggested that
many of the entrepreneurial capabilities we’re really interested in are latent, and best captured as residuals — e.g., something heritable and not explainable by other observables. . . . Mike Wright talked [at the CBS strategic entrepreneurship conference] about mobility, both across firms or projects (habitual entrepreneurs, spin-outs) and across countries (immigrant and returnee entrepreneurs, transnational entrepreneurs). From the perspective of research design, some of these movements may be useful for isolating the “entrepreneurial” essence, such as it is.
Seth Carnahan, Rajshree Agarwal, and Ben Campell have an interesting new paper, “The Effect of Firm Compensation Structures on the Mobility and Entrepreneurship of Extreme Performers,” that takes this kind of approach, measuring entrepreneurial ability as the residual in a wage regression. Most of the variation in wages can be explained by age, experience, race, gender, education, and other observables; what remains is partly measurement error, but can also include a latent ability parameter. Seth, Rajshree, and Ben use this parameter, along with the wage structure of an employee’s existing firm, to explain which employees tend to leave to join new firms, particularly startups. Check it out!
Entry filed under: - Klein -, Entrepreneurship, Management Theory, Methods/Methodology/Theory of Science, Strategic Management.
Organizations and Markets 
1.
fabiorojas | 28 November 2010 at 8:57 pm
Exercise #3: Why is it cool to talk about hard to measure dispositions in economic research when it is “po-mo persicope” time when sociologists talk about “habitus?”
Hint: A.A.’s System of the Professions. Details left to the reader!
2.
Peter Klein | 28 November 2010 at 9:54 pm
Oh, we like latent constructs. The sensible and coherent ones.
3.
fabiorojas | 28 November 2010 at 10:42 pm
Peter: It’s this sort of view that strikes me as odd. When a sociologist says something like “some people have hard to measure attitudes and abilities that reflect often unstated moods and dispositions,” economists scream “fuzzy thinking!!!” But when an economist says “some people, like entrepreneurs, have hard to measure attitudes and abilities that reflect often unstated moods and dispositions” then it’s a cool latent variable that totally makes sense. It’s coherent when WE say it, not coherent when people in other departments say it.
4.
Peter Klein | 28 November 2010 at 11:11 pm
OK, I was being flippant. But I really don’t see the problem. Economists deal with latent constructs all the time — preferences or utility being the most obvious. Economists have trouble with concepts like trust, culture — and yes, habitus — not because they’re latent, but because they violate methodological individualism, because they’re used in a sloppy and ad hoc manner, or for some other reason. I get the analogy you’re trying to draw, but I think it’s a false one.
5.
fabiorojas | 28 November 2010 at 11:37 pm
On habitus, I’ll grant you that it is not within the framework of methodologiocal individualism. But culture? Are you on crack? Can’t people learn stuff from other people? Isn’t that culture? Trust? You can’t trust someone all by yourself. Dude, you’re just getting all-econ on me.
6.
Peter Klein | 28 November 2010 at 11:43 pm
Hmmm, the last time an economist screamed “fuzzy thinking!” at the claim that people learn from other people, or that cooperation is possible in the repeated prisoner’s dilemma game, was, when, exactly?
7.
fabiorojas | 29 November 2010 at 12:11 am
You said:
“Economists have trouble with concepts like trust, culture — and yes, habitus — not because they’re latent, but because they violate methodological individualism, because they’re used in a sloppy and ad hoc manner, or for some other reason.”
And then you said that economists don’t have problems with stuff like learning, emotions, and cognition, which is exactly these terms stand for. What else am I supposed to think?
I really feel like I’m playing a shady card game sometimes. It goes like this:
Sociologist: X is important!
Economist: Sloppy fuzzy head head. You are so ad hoc!
Five years later:
Economist: Hey, guess what … X is important!
Sociologist: Wait, um, guys, weren’t we working on X a while ago?
Economist: No you weren’t.
Sociologists: Really?
Economist: You see, if I say that u’=0 then it’s real science. And if it’s an instrumental variable regression. Otherwise it’s junk.
Sociologist: Ok, formalization is good, but don’t we get some credit for talking about X and doing field work and observation on X?
Economist: Nope. Zero. Useless. Unless it’s a heteroskedastic multi-agent signalling Bayesian natural experiment in complete equilibrium that’s published in JPE or AER, you have learned absolutely nothing.
Sociologist: Umm, I guess… how about Y?
And the cycle continues…
8.
Peter Klein | 29 November 2010 at 10:01 am
Fabio, I think you’re manufacturing a disciplinary turf war that doesn’t really exist. My sense is that economists and sociologists focus mostly on different phenomena. Sometimes they study the same things, but from radically different methodological perspectives. So what? Let a thousand flowers bloom. For sure, a lot of modern sociology strikes me as gobbledygook, but a lot of modern economics is mindless formalism or data mining. (You’ll find as much or more criticism of “mainstream economics” on this blog than digs at sociologists.)
9.
Randy | 29 November 2010 at 10:40 am
Peter, I think that Fabio has rightfully and righteously taken you to task over this. If methodological individualism requires that individuals be treated as if they exist with an impenetrable membrane, then it won’t take us very far. Social context exists. Learning, trust, social capital, and attitude formation exist beyond the individual.
I would never say that economists “like” latent constructs. The econ literature abounds with half-assed proxy variables inserted into linear regressions instead of properly modeling latent variables.
And, finally, calling latent variables in sociology sloppy and ad hoc, then extolling economic analyses that artlessly confound latent variables with the error term, is shameful. “I know there is a latent variable in there somewhere” recalls the old joke about the boy shoveling horseshit from the barn because the had faith there was a pony in there somewhere.
10.
Peter Klein | 29 November 2010 at 10:57 am
Wow, I seem to have touched a nerve here. All I said was that a) the entrepreneurial function is usefully treated as a latent construct, b) it may show up in residuals (and, I’ll add now, may be more effectively modeled with fixed effects, SEM in all its full glory, or various other techniques), and c) here’s a paper that looks for entrepreneurial ability in the residuals of a wage regression. Sheesh.
(PS: Randy’s caricature of homo membraneous doesn’t correspond to any version of MI that I subscribe to!)
11.
Randy | 29 November 2010 at 11:29 am
Sorry to have sent such a testy comment earlier. I shouldn’t step between economists and sociologists on a Monday morning. Too many bad vibes in the office.
Sincere apologies.
12.
Peter Klein | 29 November 2010 at 12:12 pm
No worries! It’s all in the name of good, clean fun anyway:
https://organizationsandmarkets.com/2007/04/16/org-bloggers-peace-summit/
13.
David Hoopes | 29 November 2010 at 1:34 pm
Don’t feel bad Randy. If you hadn’t stuck your hand in the dogfight someone else would have. You just saved one of us from getting bitten.
The morning after a wedding party 30 years ago:
Hoopes: You know Spitz, I hate to say it, but I’m kind of glad Dan made a drunken fool of himself last night.
Spitz: So we didn’t have to?
Hoopes: Yep.