New version page

Business School

Upgrade to remove ads

This preview shows page 1-2-3 out of 10 pages.

Save
View Full Document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience

Upgrade to remove ads
Unformatted text preview:

Economics of Education Review 21 (2002) 471–480www.elsevier.com/locate/econedurevA nested logit model of the choice of a graduate businessschoolMark Montgomery*Department of Economics, Grinnell College, Grinnell, IA 50112, USAReceived 10 December 1998; accepted 27 June 2000AbstractLess than a handful of papers have used data on individuals to examine people’s decisions about which school toattend. This paper develops a nested logit model of the determinants of choice of a graduate business school. Data aredrawn from a new longitudinal survey of registrants for the Graduate Management Admission Test. One finding is thatelasticity of school choice with respect to tuition is fairly low, about 0.08. Another is that, even after controlling forthe effects of Affirmative Action in admissions, blacks and Hispanics are substantially more attracted to top-tier insti-tutions, while women are less attracted to them.  2002 Elsevier Science Ltd. All rights reserved.JEL classification: I21; J24Keywords: School choice; Demand for schooling1. IntroductionThe economic literature contains many articles onpeople’s decisions whether to go to college, but only afew on their decisions about which college to go to. Thispaper extends the literature on school choice in severalways. First, unlike previous studies, all of which focusedon undergraduate education, this study examines thechoice of a graduate management program. Second, itmodels the decisions whether to attend school simul-taneously with the decision which school to attend, usinga nested logit. Finally, this study has a richer source ofdata on both applicants and schools than was availableto previous work. It employs a recent survey of regis-trants for the Graduate Management Admission Test(GMAT), sponsored by the Graduate ManagementAdmissions Council. The GMAT survey is sup-plemented by published data on business schools.* Tel.: +1-641-269-3146; fax: +1-641-269-4985.E-mail address: [email protected] (M.Montgomery).0272-7757/02/$ - see front matter  2002 Elsevier Science Ltd. All rights reserved.PII: S0272-7757(01)00032-2Our analysis yields several interesting results. Forexample, elasticity of business school choice withrespect to tuition is surprisingly low, about 0.08. Also,even after controlling for the effect of race on admis-sions, blacks and Hispanics appear substantially morelikely to choose a top-tier institution than whites. Womenappear less likely to choose one than men.2. The literature on school choiceMost studies of school choice have relied upon insti-tutional-level data rather than data on individual choices.A recent paper by Bezmen and Depken (1998), forexample, examined how application rates at 772 US col-leges responded to school characteristics like cost, size,and state unemployment rates. Several other studies havelooked at enrollment or application rates for a singleinstitution: Wetzel, O’Toole and Peterson (1998), Erhen-berg and Sherman (1984), Moore, Studenmund andSlobko (1991).In comparison, less than a handful of studies haveused data on individuals to model how one school is472 M. Montgomery / Economics of Education Review 21 (2002) 471–480chosen from among a discrete set of alternative insti-tutions. Kohn, Manski and Mundel (1976) (KMM) werethe first to apply the methodology of discrete choice tothis question. KMM used the SCOPE1survey to developa conditional logit model of the choice of a college. Theyfound that tuition, room and board costs, and distancefrom home all negatively influenced the likelihood ofchoosing a particular school. The quality of the schoolincreased the likelihood it would be chosen. Manski andWise (1983) extended the KMM analysis to a multi-nomial logit model of choice among a set of school andnon-school alternatives. They found tuition and scholar-ship aid to be significant determinants of whether toattend school and which one to choose. The Manski andWise model, however, had a very restricted choice set.No information was included about schools to which thesample member had not applied or not been admitted.Oosterbeek, Groot and Hartog (1992) were able todevelop a multinomial logit model using a full choiceset of schools; they used data on economists in theNetherlands, which happens to have only five economicsdepartments. Unfortunately, the only school character-istic they could include was predicted earnings for gradu-ates at each school.This paper extends the literature on school choice bydeveloping a nested logit model of the selection of agraduate business school. In this model the school-choicedecision is one “nest” in a joint decision about whether(and how) to attend school (part-time or full-time), andwhich school to attend. The parameters of the separatedecision functions are estimated jointly by full-infor-mation maximum likelihood (FIML).3. The modelOur econometric approach assumes that a prospectiveMBA student chooses a graduate business program witha two-stage process. First she decides whether to go full-time, to go part-time, or not to go at all. If she decidesto go full-time she chooses among one set of availableinstitutions, if part-time she chooses from a (potentially)different set. A simple schematic is presented in Fig. 1.We treat part-time and full-time attendance as separateregimes because for graduate business students they arequite distinct. Part-time MBA students usually attend atnight while working at a day job. Clearly the schoolchoices of part-timers with well-established jobs aremore constrained by geography than those of full-timers.Moreover, many MBA programs only offer nightcourses. Thus we assume an individual’s choice set for1School to College: Opportunities for Post-Secondary Edu-cation, The Center for Research and Development in HigherEducation, University of California, Berkeley (1966).Fig. 1. Structure of the decision model.a part-time program differs from that for a full-timer pro-gram.In a nested logit framework the two school-choicemodels (part-time and full-time) form one nest, theattendance model the other. Though estimated simul-taneously, the structures of the nests are quite differentand are therefore discussed separately.3.1. The school choice modelThe school choice is represented by a random utilitymodel (RUM) estimated by the conditional logit tech-nique introduced by McFadden (1973). The RUMapproach assumes that a person selects one option (inthis case a business school) from among all of theoptions in a so-called


Download Business School
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Business School and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Business School 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?