MODELING OF CONFIGURAL JUDGMENT PROCESSES AS A SERIES OF SUBSPACE HYPERPLANES

Past research in modeling human judgments has been accompanied by continuing debate as to the necessity and effectiveness of using “configural” models, vis-a-vis“first-order” models, to represent complex decision processes. The resounding power of first-order models adequately to represent apparently configural processes repeatedly has been demonstrated to the frustration of those researchers who intuitively feel that man decides in a complex and configural manner. This paper presents the theory that the apparent weakness of configural models may be attributed to the assumption that interaction effects are “continuous” phenomena when in fact they are “discrete” or local interactions. The definition of subspaces of the predictor set, over which “local” first-order hyperplanes may be used, is investigated as a viable means of representing “discrete” interactions while preserving some of the parsimony of the “continuous” formulations. The application of the Automatic Interaction Detection technique to define subspaces and local models is attempted with positive results for an installment loan officer. Then a comparison with the results from a recent study which used various “continuous” formulations shows a definite superiority of the “local” modeling approach.     

USING AN UNCERTAINTY MODEL TO ASSESS SALES RESPONSE TO ADVERTISING*

Implications of a probabilistic “random walk” model of incremental sales response to advertising are developed for various timing patterns of advertising expenditures. Maximum likelihood procedures for assessing advertising effectiveness and for estimating a decay (forgetting) rate are developed and applied to artificial data of known configuration and are used to assess the impact over time of a brochure program on mail-order sales. Results are also compared to those from alternative models involving various lag patterns in advertising effects.     

WHY MERGERS REDUCE PROFITS AND RAISE SHARE PRICES–A THEORY OF PREEMPTIVE MERGERS

We provide a possible explanation for the empirical puzzle that mergers often reduce profits, but raise share prices. If being an “insider” is better than being an “outsider”, firms may merge to preempt their partner merging with a rival. The insiders' stock market value is increased, since the risk of becoming an outsider is eliminated. These results are derived in an endogenous‐merger model, predicting the conditions under which mergers occur, when they occur, and how the surplus is shared. (JEL: L13, L41, G34, C78)     

DISCRETE CHOICE WITH SOCIAL INTERACTIONS AND ENDOGENOUS MEMBERSHIPS

This paper is about selection of neighbors in models of social interactions. I study a general equilibrium model of behavior subject to endogenous social influences when heterogeneous individuals can choose whom to associate with, buying associations on a “memberships market”. Social effects in behavior turn out to be a stratifying force: The desire for valuable interactions induces inefficient sorting and may lead to the endogenous emergence of “social traps”. The theory is then used to suggest identification strategies that may solve, in a micro‐founded way, identification and selection problems that typically affect empirical work on social interactions. Such strategies offer a viable alternative when valid instrumental variables or randomized experiments are not available. (JEL: C26, D85, Z13, Z19)     

THE IMPACT OF ENTERPRISE INFORMATION TECHNOLOGY ADOPTION ON OPERATIONAL PERFORMANCE: AN EMPIRICAL INVESTIGATION

This paper presents the results of a natural experiment conducted at a U.S. high‐tech manufacturer. The experiment had as its treatment the adoption, at a single point in time, of a comprehensive enterprise information system throughout the functional groups charged with customer order fulfillment. This information technology (it) adoption was not accompanied by substantial contemporaneous business process changes. Immediately after adoption, lead time and on‐time delivery performance suffered, causing a “performance dip” similar to those observed after the introduction of capital equipment onto shop floors. Lead times and on‐time delivery percentages then improved along a learning curve. After several months, performance in these areas improved significantly relative to preadoption levels. These observed performance patterns could not be well explained by rival causal factors such as order, production, and inventory volumes; head count; and new product introductions. Thus, this longitudinal research presents initial evidence of a causal link between IT adoption and subsequent improvement in operational performance measures, as well as evidence of the timescale over which these benefits appear.     

Average and Quantile Effects in Nonseparable Panel Models

Nonseparable panel models are important in a variety of economic settings, including discrete choice. This paper gives identification and estimation results for nonseparable models under time‐homogeneity conditions that are like “time is randomly assigned” or “time is an instrument.” Partial‐identification results for average and quantile effects are given for discrete regressors, under static or dynamic conditions, in fully nonparametric and in semiparametric models, with time effects. It is shown that the usual, linear, fixed‐effects estimator is not a consistent estimator of the identified average effect, and a consistent estimator is given. A simple estimator of identified quantile treatment effects is given, providing a solution to the important problem of estimating quantile treatment effects from panel data. Bounds for overall effects in static and dynamic models are given. The dynamic bounds provide a partial‐identification solution to the important problem of estimating the effect of state dependence in the presence of unobserved heterogeneity. The impact of T, the number of time periods, is shown by deriving shrinkage rates for the identified set as T grows. We also consider semiparametric, discrete‐choice models and find that semiparametric panel bounds can be much tighter than nonparametric bounds. Computationally convenient methods for semiparametric models are presented. We propose a novel inference method that applies in panel data and other settings and show that it produces uniformly valid confidence regions in large samples. We give empirical illustrations.     

A Novel Approach to Chemical Mixture Risk Assessment—Linking Data from Population‐Based Epidemiology and Experimental Animal Tests

Humans are continuously exposed to chemicals with suspected or proven endocrine disrupting chemicals (EDCs). Risk management of EDCs presents a major unmet challenge because the available data for adverse health effects are generated by examining one compound at a time, whereas real‐life exposures are to mixtures of chemicals. In this work, we integrate epidemiological and experimental evidence toward a whole mixture strategy for risk assessment. To illustrate, we conduct the following four steps in a case study: (1) identification of single EDCs (“bad actors”)—measured in prenatal blood/urine in the SELMA study—that are associated with a shorter anogenital distance (AGD) in baby boys; (2) definition and construction of a “typical” mixture consisting of the “bad actors” identified in Step 1; (3) experimentally testing this mixture in an in vivo animal model to estimate a dose–response relationship and determine a point of departure (i.e., reference dose [RfD]) associated with an adverse health outcome; and (4) use a statistical measure of “sufficient similarity” to compare the experimental RfD (from Step 3) to the exposure measured in the human population and generate a “similar mixture risk indicator” (SMRI). The objective of this exercise is to generate a proof of concept for the systematic integration of epidemiological and experimental evidence with mixture risk assessment strategies. Using a whole mixture approach, we could find a higher rate of pregnant women under risk (13%) when comparing with the data from more traditional models of additivity (3%), or a compound‐by‐compound strategy (1.6%).     

THE ESCALATION OF COMMITMENT IN SEQUENTIAL DECISION MAKING: SITUATIONAL AND PERSONAL MODERATORS AND LIMITING CONDITIONS*

Two laboratory studies manipulated variables in order to observe their effect on the escalation of individuals' commitment to earlier investment decisions. The experimental results indicated that escalation of commitment to a failing course of action is not a general phenomenon. Information pertinent to the future prospects of reinvestment and to decision alternatives provided main effects. Neither study showed a main effect for initial success vs. failure. Decision-maker gender consistently influenced decisions in both studies through interactions with success/failure feedback and through the communicated attributions of “powerful others” regarding the causes of previous decision outcomes. Implications for theory and research are discussed.     

Perfectionism and Choice

Empirical evidence suggests that perfectionism can affect choice behavior. When striving for perfection, a person can desire to keep normatively appealing options feasible even if she persistently fails to use these options later. For instance, she can “pay not to go to the gym,” as in DellaVigna and Malmendier (2006). By contrast, some perfectionists may avoid normatively important tasks for fear of negative self‐evaluation of their performance. This paper models perfectionist behaviors in Gul and Pesendorfer's (2001) menu framework where agents may be tempted to deviate from their long‐term normative objectives. In addition to self‐control costs, I identify a utility component that reflects emotional costs and benefits of perfectionism. My model is derived from axioms imposed on preferences over menus in an essentially unique way.     

A SIMULATION MODEL OF THE HIGHER EDUCATION SYSTEM OF A STATE1

This paper describes a simulation model to estimate the enrollments and expenditures associated with various policy alternatives for the post-secondary education system of a state, with Indiana as an example. Enrollments, operating expenditures, and construction costs are predicted for every public and private school for each year until 1985. The basic model-building technique employed is regression analysis on historical data, but it is supplemented by other quantitative techniques and by experts' predictions. The model may be used to predict “most likely” future enrollments and costs, to perform sensitivity analyses to better understand the impact of various exogenous variables upon the system, and to evaluate possible policy alternatives. Including all of the schools in a state makes possible the evaluation of policy alternatives such as possible configurations of new two-year public schools, the effect of tuition changes, and the effect of enrollment ceilings for larger state universities.     

THE RISE OF THE EAST AND THE FAR EAST: GERMAN LABOR MARKETS AND TRADE INTEGRATION

We analyze the effects of the unprecedented rise in trade between Germany and “the East” (China and Eastern Europe) in the period 1988–2008 on German local labor markets. Using detailed administrative data, we exploit the cross‐regional variation in initial industry structures and use trade flows of other high‐income countries as instruments for regional import and export exposure. We find that the rise of the East in the world economy caused substantial job losses in German regions specialized in import‐competing industries, both in manufacturing and beyond. Regions specialized in export‐oriented industries, however, experienced even stronger employment gains and lower unemployment. In the aggregate, we estimate that this trade integration has caused some 442,000 additional jobs in the economy and contributed to retaining the manufacturing sector in Germany. This is almost exclusively driven by the rise of Eastern Europe, not by China. We also conduct an analysis at the individual worker level, and find that trade had a stabilizing overall effect on employment relationships.     

ON THE EQUIVALENCE OF TWO VERSIONS OF THE PRESENT VALUE PROCEDURE

The central issue in equipment investment analysis is the selection of the best of two or more alternatives. A common procedure is to first assume that for each alternative there is an infinite stream of identical pieces of equipment. The present value of the associated infinite stream of revenues and costs is calculated. Then the alternative having the highest present value (where revenues are positive and costs are negative) is selected. The assumption of the infinite stream, though computationally desirable, is not very palatable to the decision maker. In this paper we show that the above procedure is equivalent to using a criterion which is definitely more appealing. The author has found this “equivalence” result to be helpful in teaching the basic concepts of the present value procedure. Also the result should be of interest to practitioners involved in equipment investment decision making.     

LEGAL STANDARDS,ENFORCEMENT, AND CORRUPTION

Stricter laws require more incisive and costlier enforcement. Because enforcement activity depends both on available tax revenue and the honesty of officials, the optimal legal standard of a benevolent government is increasing in per capita income and decreasing in officials' corruption. In contrast to the “tollbooth view” of regulation, the standard chosen by a self‐interested government is a non‐monotonic function of officials' corruption, and can be either lower or higher than that chosen by a benevolent regulator. International evidence on environmental regulation shows that standards correlate positively with per‐capita income, and negatively with corruption, consistent with the model's predictions for benevolent governments. (JEL: D73, K42, L51)     

The Value of Environmental Information without Control of Subsequent Decisions

The standard value of information approach of decision analysis assumes that the individual or agency that collects the information is also in control of the subsequent decisions based on the information. We refer to this situation as the “value of information with control (VOI‐C).” This paradigm leads to powerful results, for example, that the value of information cannot be negative and that it is zero, when the information cannot change subsequent decisions. In many real world situations, however, the agency collecting the information is different from the one that makes the decision on the basis of that information. For example, an environmental research group may contemplate to fund a study that can affect an environmental policy decision that is made by a regulatory organization. In this two‐agency formulation, the information‐acquiring agency has to decide, whether an investment in research is worthwhile, while not being in control of the subsequent decision. We refer to this situation as “value of information without control (VOI‐NC).” In this article, we present a framework for the VOI‐NC and illustrate it with an example of a specific problem of determining the value of a research program on the health effects of power‐frequency electromagnetic fields. We first compare the VOI‐C approach with the VOI‐NC approach. We show that the VOI‐NC can be negative, but that with high‐quality research (low probabilities of errors of type I and II) it is positive. We also demonstrate, both in the example and in more general mathematical terms, that the VOI‐NC for environmental studies breaks down into a sum of the VOI‐NC due to the possible reduction of environmental impacts and the VOI‐NC due to the reduction of policy costs, with each component being positive for low environmental impacts and high‐quality research. Interesting results include that the environmental and cost components of the VOI‐NC move in opposite directions as a function of the probability of environmental impacts and that VOI‐NC can be positive, even though the probability of environmental impacts is zero or one.     

Consistency of Higher Order Risk Preferences

Risk aversion (a second‐order risk preference) is a time‐proven concept in economic models of choice under risk. More recently, the higher order risk preferences of prudence (third‐order) and temperance (fourth‐order) also have been shown to be quite important. While a majority of the population seems to exhibit both risk aversion and these higher order risk preferences, a significant minority does not. We show how both risk‐averse and risk‐loving behaviors might be generated by a simple type of basic lottery preference for either (1) combining “good” outcomes with “bad” ones, or (2) combining “good with good” and “bad with bad,” respectively. We further show that this dichotomy is fairly robust at explaining higher order risk attitudes in the laboratory. In addition to our own experimental evidence, we take a second look at the extant laboratory experiments that measure higher order risk preferences and we find a fair amount of support for this dichotomy. Our own experiment also is the first to look beyond fourth‐order risk preferences, and we examine risk attitudes at even higher orders.     

PROPERTY RIGHTS AND THE EFFICIENCY OF BARGAINING

We show that efficient bargaining is impossible for a wide class of economic settings and property rights. These settings are characterized by (i) the existence of “adverse efficient opt‐out types”, whose participation does not change the efficient allocation and who, when they opt out, are the worst type other agents can face, and (ii) non‐existence of the “marginal core”, and its multivaluedness with a positive probability. We also examine the optimal allocation of property rights within a given class that satisfies (i), such as simple property rights, liability rules, and dual‐chooser rules. We characterize property rights that minimize the expected subsidy required to implement efficiency. With two agents, simple property rights that are optimal in this way maximize the expected surplus at the status quo allocation, but this no longer holds with more agents. We also study “second‐best” budget‐balanced bargaining under a liability rule. The optimal “second‐best” liability rule may differ from, but is often close to, the expectation of the victim's harm, which would be optimal if there were no bargaining. However, liability rules that are close to a simple property right result in a lower expected surplus than the simple property right they are near.     

EFFECTS OF RANDOM SHIFTS OF TESTING EQUIPMENT ON PROCESS CONTROL SYSTEM DESIGN AND SELECTION OF PROCESS CONTROL POLICIES*

This paper studies issues associated with designing process control systems when the testing equipment is subjected to random shifts. We consider a production process with two states: in control and out of control. The process may shift randomly to the out‐of‐control state over time. The process is monitored by periodically sampling finished items from the process. The equipment used to test sampled items also is assumed to have two states and may shift randomly during the testing process. We formulate a cost model for finding the optimal process control policy that minimizes the expected unit time cost. Numerical results show that shifts of the testing equipment may significantly affect the performance of a process control policy. We also studied the effects of the testing equipment's shifts on the selection of process control policies.     

DISTANCE AND FOREIGN DIRECT INVESTMENT WHEN CONTRACTS ARE INCOMPLETE

We introduce incomplete contracts in a model where multinational firms from a certain country (“North”) can decide to serve a foreign market (“South”) through exports or through horizontal foreign direct investment (FDI). FDI relies on the supply of specialized intermediate inputs that could be supplied either by northern suppliers or by suppliers located in South. Intermediate sourcing contracts are complete in North but not in South. Were southern contracts also complete, FDI would arise only when trade barriers are high enough. Incomplete contracts in South generate, instead, a non‐linear relation between trade barriers and FDI as foreign investment emerges also when trade barriers are low enough. The reason is the positive effect that low trade barriers have on the bargaining power of final producers with respect to their southern suppliers. (JEL: F23, F12)     

Regression Versus Causation,Revisited

I recently discussed pitfalls in attempted causal inference based on reduced‐form regression models. I used as motivation a real‐world example from a paper by Dr. Sneeringer, which interpreted a reduced‐form regression analysis as implying the startling causal conclusion that “doubling of [livestock] production leads to a 7.4% increase in infant mortality.” This conclusion is based on: (A) fitting a reduced‐form regression model to aggregate (e.g., county‐level) data; and (B) (mis)interpreting a regression coefficient in this model as a causal coefficient, without performing any formal statistical tests for potential causation (such as conditional independence, Granger‐Sims, or path analysis tests). Dr. Sneeringer now adds comments that confirm and augment these deficiencies, while advocating methodological errors that, I believe, risk analysts should avoid if they want to reach logically sound, empirically valid, conclusions about cause and effect. She explains that, in addition to (A) and (B) above, she also performed other steps such as (C) manually selecting specific models and variables and (D) assuming (again, without testing) that hand‐picked surrogate variables are valid (e.g., that log‐transformed income is an adequate surrogate for poverty). In her view, these added steps imply that “critiques of A and B are not applicable” to her analysis and that therefore “a causal argument can be made” for “such a strong, robust correlation” as she believes her regression coefficient indicates. However, multiple wrongs do not create a right. Steps (C) and (D) exacerbate the problem of unjustified causal interpretation of regression coefficients, without rendering irrelevant the fact that (A) and (B) do not provide evidence of causality. This reply focuses on whether any statistical techniques can produce the silk purse of a valid causal inference from the sow's ear of a reduced‐form regression analysis of ecological data. We conclude that Dr. Sneeringer's analysis provides no valid indication that air pollution from livestock operations causes any increase in infant mortality rates. More generally, reduced‐form regression modeling of aggregate population data—no matter how it is augmented by fitting multiple models and hand‐selecting variables and transformations—is not adequate for valid causal inference about health effects caused by specific, but unmeasured, exposures.