RENNA JIANG <!– /* Style Definitions */ p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-parent:””; margin:0in; margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:12.0pt; font-family:”Times New Roman”; mso-fareast-font-family:”Times New Roman”;} p.Default, li.Default, div.Default {mso-style-name:Default; mso-style-parent:””; margin:0in; margin-bottom:.0001pt; mso-pagination:widow-orphan; mso-layout-grid-align:none; text-autospace:none; font-size:12.0pt; font-family:”Times New Roman”; mso-fareast-font-family:”Times New Roman”; color:black;} @page Section1 {size:8.5in 11.0in; margin:1.0in 1.25in 1.0in 1.25in; mso-header-margin:.5in; mso-footer-margin:.5in; mso-paper-source:0;} div.Section1 {page:Section1;} –>

RENNA JIANG

June 2008

Address: 1369 E Hyde Park Blvd. Apt 202

Chicago, IL 60615, USA

Phone: 847-204-8512

E-mail: rjiang1@ChicagoGSB.edu

Web: http://home.uchicago.edu/~rjiang1

EDUCATION

Ph.D. in Marketing, 2009 (expected)

University of Chicago, Graduate School of Business, Chicago, IL, USA

– Support Area: Economics

– Coordinated Sequence: Econometrics and Statistics

– Dissertation (Job Market Paper): “Structural Estimation of a Moral Hazard Model: An Application

to Business Selling”

– Dissertation Committee: Pradeep Chintagunta (Co-Chair), Peter Rossi (Co-Chair), Jean-Pierre Dubé,

Milton Harris

Bachelor in Economics, 2001

Tsinghua University, Beijing, China

RESEARCH INTERESTS

– Moral Hazard in Sales Force

– Learning in Pharmaceutical Industry

– Bayesian Methods and Structural Modeling

HONORS, AWARDS AND SCHOLARSHIPS

Winner of ISBM (Institute for the Study of Business Markets) Business Marketing Doctoral Support Award Competition, 2007

Performance Bonus for Excellence in Teaching Assistance (Executive MBA – London and Singapore), Graduate School of Business, University of Chicago, 2006, 2007

Kilts Center Fellow, Graduate School of Business, University of Chicago, 2008

Haring Symposium Fellow, 2007

INFORMS Society of Marketing Science Doctoral Consortium Fellow, 2005, 2006

Summer Research Grant, Graduate School of Business, University of Chicago, 2004

Doctoral Fellowship, Graduate School of Business, University of Chicago, 2003-2007

Page 1 of 5

DISSERTATION

“Structural Estimation of a Moral Hazard Model: An Application to Business Selling”

(Contact me for the latest version of the paper)

Extended Abstract: The optimal contracting issue is relevant for many economic situations where a “principal” hires an “agent” to undertake certain actions for the former. Moral hazard can arise in these situations when the agent’s objective is not entirely aligned with that of the principal, and the principal is unable to observe how much effort the agent puts into the job. One marketing context in which the moral hazard issue is particularly relevant is sales force compensation. While theoretical marketing researchers have mostly focused on the design of an optimal contract, much of the empirical work has been conducted to test various comparative statics predictions from the theoretical models.

This research differs markedly from most previous empirical work in that we do not impose optimality on the principal. Rather, we estimate a structural model which in turn allows us to make statements about what the optimal behavior should be. We are able to do this with a unique data set that contains information on effort (measured as monetary cost) in the context of business selling. The data are obtained via surveys. In our sample, manufacturers (the “principal”) of industrial components hire outside selling agencies (the “agent”) as representatives (hence the term “rep firms”) to sell products to business customers. In return, the rep firms receive commissions on realized sales.

The data also contain information on sales and commission rates. Together with the effort data, we build a structural model consisting of two equations: a sales production function whereby effort produces sales, and an effort equation characterizing the selling agents’ optimizing behavior. Specifically, agents choose effort levels based on the productivity of effort and the commission rate. The second equation is at the heart of the moral hazard problem. The manufacturer cannot directly impose his desired level of effort on the agents because actual effort is unobservable. The agents are free to choose effort levels in their best interests. In order to motivate the agents to take the “correct” actions, the manufacturer needs to know how the agents’ effort reacts to the promised commission rates.

The model also allows the agent to have better information than the manufacturer about the opportunities in the field. Specifically, effort’s effectiveness on sales (i.e., productivity) is determined by two components: i) a deterministic component that may depend on characteristics of the customer, of the field salesperson, and of the selling firm; ii) a random shock that is customer specific. The salesperson knows both components before making the effort decision, while the manufacturer does not observe the random component. In addition, we extend the model to allow for unobserved factors (to the researcher) that could potentially influence both the productivity of effort and the commission rate. This can be motivated by situations in which the manufacturer has some knowledge about the effort productivity (e.g., the selling difficulty of his products), and uses that information in choosing commission rates. Model parameters are estimated using a maximum likelihood procedure.

We then use the parameter estimates to compute optimal commission rates and to further quantify the economic consequences of the manufacturer’s seemingly sub-optimizing behavior. Our empirical results support the existence of common unobserved components which affect the effort’s productivity and commission rates in the opposite direction. The negative correlation is consistent with the notion that the manufacturers pay higher commission rates to more difficult to sell products. We find that the predicted

Page 2 of 5

optimal commission rates are higher than what are observed in the data, and that the manufacturers could achieve higher sales and value (after paying commissions) by adopting the proposed optimal rates.

OTHER RESEARCH

“Bayesian Analysis of Random Coefficient Logit Models Using Aggregate Data,” with Puneet Manchanda and Peter E. Rossi (R&R for the Journal of Econometrics)

Abstract: We present a Bayesian approach for analyzing aggregate level sales data in a market with differentiated products. We consider the aggregate share model proposed by Berry, Levinsohn and Pakes (1995) which introduces a common demand shock into an aggregated random coefficient logit model. A full likelihood approach is possible with a specification of the distribution of the common demand shock, although we demonstrate that our Bayes estimator works well even in the presence of a mis-specified shock distribution. We introduce a re-parameterization of the covariance matrix to improve the performance of the random walk Metropolis for covariance parameters. We illustrate the usefulness of our approach with both actual and simulated data. Sampling experiments show that our approach performs well relative to the GMM estimator.

“Information, Learning and Drug Diffusion: The Case of Cox-2 Inhibitors,” with Pradeep K. Chintagunta and Ginger Z. Jin (under review at Quantitative Marketing and Economics)

Abstract: The recent withdrawal of Cox-2 Inhibitors has generated debate on the role of information in drug diffusion: can the market learn the efficacy of new drugs, or does it depend solely on manufacturer advertising and FDA updates? In this study, we use a novel data set to study the diffusion of three Cox-2 Inhibitors–Celebrex, Vioxx and Bextra–before the Vioxx withdrawal. Our study has two unique features: first, we observe each patient’s reported satisfaction after consuming a drug. This patient level data set, together with market level data on FDA updates, media coverage, academic articles, and pharmaceutical advertising, allows us to model individual prescription decisions. Second, we distinguish across-patient learning of a drug’s general efficacy from the within-patient learning of the match between a drug and a patient. Our results suggest that prescription choice is sensitive to many sources of information. At the beginning of 2001 and upon Bextra entry in January 2002, doctors held a strong prior belief about the efficacy of the three drugs. As a result, the learning from patient satisfaction is gradual and more concentrated on drug-patient match than on across-patient spillovers. Newspaper articles are weakly beneficial for Cox-2 drug sales, but academic articles appear to be detrimental. The FDA updates appear to follow academic articles and deliver little new information to doctors. Manufacturer advertising also influences the choice of a patient’s medication. A number of counterfactual experiments are carried out to quantify the influence of information on market shares.

Page 3 of 5

INVITED TALK

“Information, Learning and Drug Diffusion: The Case of Cox-2 Inhibitors,” Marketing Department Seminar Series, Stern School of Business, New York University, March 2008

CONFERENCE PRESENTATIONS

“Bayesian Analysis of Random Coefficient Logit Models Using Aggregate Data”

– Seminar on Bayesian Inference in Econometrics and Statistics (SBIES), Graduate School of

Business, University of Chicago, May 2008

– INFORMS Marketing Science Conference, Katz Graduate School of Business, University of

Pittsburgh, June 2006

SELECTED PH.D. LEVEL COURSEWORK Area	Course		Instructor
Marketing	Pro-seminar Advanced Marketing Theory: Behavior Perspective Advanced Marketing Theory: Quant Perspective Bayesian Statistics and Marketing Marketing Literature Seminar		All Marketing Faculty Chris Hsee Pradeep Chintagunta Peter Rossi Aparna Labroo / Günter Hitsch
Information Economics	Price Theory III Economics of Information Auctions		Pierre-André Chiappori Milton Harris Ali Hortacsu
Industrial Organization	Advanced Industrial Organization I Advanced Industrial Organization III		Dennis Carlton Amil Petrin
	Industrial Organization and Prices I Topics in Industrial Organization (Dynamics) (Economics Department, Northwestern University)	Aviv Nevo / Michael Whinston Aviv Nevo / Igal Hendel
Other Economics	Price Theory I (Microeconomic Theory) Price Theory II (General Equilibrium / Game Theory) Numerical Methods in Economics		Garry Becker / Kevin M. Murphy Hugo Sonnenschein / Philip Reny Kenneth Judd
	Microeconomics III (Game Theory) (Economics Department, Northwestern University)	Michael Whinston
Econometrics	Empirical Analysis II Empirical Analysis III Applied Econometrics		Lars Peter Hansen Han Hong Amil Petrin
Statistics	Probability and Statistics Statistical Inference Applied Linear Statistical Methods Intro to Probability Models		Nicholas Polson Nicholas Polson Wei-Biao Wu Yali Amit