nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2005‒02‒13
eight papers chosen by
Philip Yu
Hong Kong University

  1. Bayesian Analysis of Structural Effects in an Ordered Equation System By Li, Mingliang; Tobias, Justin
  2. Estimating the Return to Training and Occupational Experience: The Case of Female Immigrants By Cohen-Goldner, Sarit; Eckstein, Zvi
  3. Money Market Pressure and the Determinants of Banking Crises By Ho, Tai-Kuang; von Hagen, Jürgen
  4. The Politics Of Debt Crises By Van Rijckeghem, Caroline; Weder, Beatrice
  5. Industry/University S&T Transfers: What Can We Learn From Belgian CIS-2 Data? By Capron, Henri; Cincera, Michele
  6. Spousal Influence on Early Retirement Behavior By Zhiyang Jia
  7. Alternative methodologies in studies on business failure: do they produce better results than the classic statistical methods? By Balcaen S.; Ooghe H.
  8. Opportunities for active stock-out management in online stores: The impact of the stock-out policy on online stock-out reactions By Breugelmans E.; Campo K.; Gijsbrechts E.

  1. By: Li, Mingliang; Tobias, Justin
    Abstract: We describe a new simulation-based algorithm for Bayesian estimation of structural effects in models where the outcome of interest and an endogenous treatment variable are ordered. Our algorithm makes use of a reparameterization, suggested by Nandram and Chen (1996) in the context of a single equation ordered-probit model, which significantly improves the mixing of the standard Gibbs sampler. We illustrate the improvements afforded by this new algorithm in a generated data experiment and also make use of our methods in an empirical application. Specifically, we take data from the National Longitudinal Survey of Youth (NLSY) and investigate the impact of maternal alcohol consumption on early infant health. Our results show clear evidence that the health outcomes of infants whose mothers drink while pregnant are worse than the outcomes of infants whose mothers never consumed alcohol while pregnant. In addition, the estimated parameters clearly suggest the need to control for the endogeneity of maternal alcohol consumption.
    Date: 2005–02–08
  2. By: Cohen-Goldner, Sarit; Eckstein, Zvi
    Abstract: Do government provided training programmes benefit the participants and the society? We address this question in the context of female immigrants who first learn the new language and then choose between working or attending government provided training. Although theoretically training may have several outcomes, most evaluations have focused on only one outcome of training: the expected wage. Training might have no direct effect on wage, however, but it affects employment probability in higher paid jobs nevertheless. In order to measure the return to government provided training, and overcome the above reservations, we formulate an estimable stochastic dynamic discrete choice model of training and employment. Given the estimated model, the individual benefit is measured by the change in expected lifetime utility due to the effect of alternative training policy. The social return from training is measured by the expected increase in actual earnings minus the cost, due to a counterfactual policy. Our estimates imply that training has no significant impact on the mean offered wage in blue-collar occupation, but training increases the mean offered wage in white-collar occupation by 19%. Training also substantially increases the job offer rates in both occupations. Furthermore, counterfactual policy simulations show that free access to training programs relative to no training could cause an annual earnings growth of 31.3%. This large social gain (ignoring the cost of the programme) comes mainly from the impact of training on the job offer probabilities and, consequently, on unemployment, and not, as conventionally thought, from the impact of training on potential earnings. Moreover, the average ex-ante expected present value of utility for a female immigrant at arrival (individual benefit) increases by 50% using a counterfactual policy of fully available training relative to the estimated restricted level of training opportunity.
    Keywords: immigration; occupation; training; transitions; unemployment; welfare
    JEL: J31 J68
    Date: 2004–09
  3. By: Ho, Tai-Kuang; von Hagen, Jürgen
    Abstract: Identifying banking crises is the first step in the research on determinants of banking crises. The prevailing practice is to employ market events to identify a banking crisis. Researchers justify the usage of this method on the grounds that either direct and reliable indicators of banks’ assets quality are not available, or that withdrawals of bank deposits are no longer a part of financial crises in a modern financial system with deposits insurance. Meanwhile, most researchers also admit that there are inherent inconsistency and arbitrariness associated with the events method. This paper develops an index of money market pressure to identify banking crises. We define banking crises as periods in which there is excessive demand for liquidity in the money market. We begin with the theoretical foundation of this new method and show that it is desirable, and also possible, to depend on a more objective index of money market pressure rather than market events to identify banking crises. This approach allows one to employ high frequency data in regression, and avoid the ambiguity problem in interpreting the direction of causality that most banking literature suffers. Comparing the crises dates with existing research indicates that the new method is able to identify banking crises more accurately than the events method. The two components of the index, changes in central bank funds to bank deposits ratio and changes in short-term real interest rate, are equally important in the identification of banking crises. Bank deposits, combined with central bank funds, provide valuable information on banking distress. With the newly defined crisis episodes, we examine the determinants of banking crises using data complied from 47 countries. We estimate conditional logit models that include macroeconomic, financial, and institutional variables in the explanatory variables. The results display similarities to and differences with existing research. We find that slowdown of real GDP, lower real interest rates, extremely high inflation, large fiscal deficits, and over-valued exchange rates tend to precede banking crises. The effects of monetary base growth on the probability of banking crises are negligible.
    Keywords: conditional logit model; events method; identification of banking crises; index of money market pressure
    JEL: C43 E44 G21
    Date: 2004–10
  4. By: Van Rijckeghem, Caroline; Weder, Beatrice
    Abstract: This paper shows that politics matter in explaining defaults on external and domestic debt obligations. We explore a large number of political and macroeconomic variables using a nonparametric technique to predict safety from default. The advantage of this technique is that it is able to identify complementarities that are not captured in standard probit analysis. We find that political factors matter, and do so in different ways for democratic and non-democratic regimes, and for domestic and external debt. Moreover we find that there is an important complementarity between political and economic conditions, which is essential in explaining the incidence of default.
    Keywords: early warning systems; political institutions; sovereign debt crises
    JEL: F30 F34
    Date: 2004–10
  5. By: Capron, Henri; Cincera, Michele
    Abstract: The second European Innovation Survey (CIS-2) provides information about different modes of interactions between innovative firms and other research institutions, in particular universities. These data are exploited to estimate an ordered probit model with sample selection of the role played by universities and other partners as a main source of new ideas for firms innovation activities as well as a GHK triprobit model to explore the role of firm and industry characteristics on formal and informal collaborative agreements between firms, universities and other research partners. The results suggest that the factors explaining the use of a particular source of information are not the same according to the type of sources. In a same vein, the determinants of industry collaborations with universities have a different impact when other partners are considered.
    Keywords: Belgian CIS-2; industry-university collaborations; innovation
    JEL: O32
    Date: 2004–11
  6. By: Zhiyang Jia (Statistics Norway)
    Abstract: In this paper, we use a binary choice panel data model to analyze married individuals.retirement behavior in Norway when a new option, AFP early retirement becomes available. We focus our study on the influence of the spouse.s characteristics on early retirement behavior. We find the directions of spousal e¤ects are quite symmetric but women seem to have a much stronger response to their spouses' characteristics than men. The comparison of di¤erent specifications indicates that correct modeling of the error term covariance structure in a panel data binary choice model is quite important.
    Keywords: Retirement; Spousal Influence; Panel Data; Random Effects.
    JEL: H55 J26
    Date: 2005–02
  7. By: Balcaen S.; Ooghe H.
    Abstract: Over the last 35 years, the topic of company failure prediction has developed to a major research domain in corporate finance. Academic researchers from all over the world have been developing a gigantic number of corporate failure prediction models, based on various types of modelling techniques. Besides the classic cross-sectional statistical methods, which have produced numerous failure prediction models, researchers have also been using several alternative methods for analysing and predicting business failure. To date, a clear overview and discussion of the application of alternative methods in corporate failure prediction is still lacking. Moreover, frequently, different designations or names are used for one method. Therefore, this study aims to provide a clear overview of the alternative research methods, attributing each of them a fixed designation. More in particular, this paper extensively elaborates on the most popular methods of survival analysis, machine learning decision trees and neural networks. Furthermore, it discusses several other alternative methods, which can be considered to have a certain value added in the empirical literature on business failure: the fuzzy rules-based classification model, the multi-logit model, the CUSUM model, dynamic event history analysis, the catastrophe theory and chaos theory model, multidimensional scaling, linear goal programming, the multi-criteria decision aid approach, rough set analysis, expert systems and self-organizing maps. This paper discusses the main features of these methods and their specific assumptions, advantages and disadvantages and it gives an overview of a number of academically developed corporate failure prediction models. Several issues viewed in isolation by earlier studies are here considered together, which is of major importance for gaining a clear insight into the possible alternative methods of corporate failure modelling and their corresponding features. A second aim of this paper is to find an answer to the question whether the more sophisticated, alternative modelling methods produce better performing failure prediction models than the rather simple classic statistical methods. The analysis of the conclusions of a large number of empirical studies comparing the classification results and/or the prediction abilities of failure prediction models based on different techniques seems to indicate that we may question the benefits to be gained from using the more sophisticated alternative methods.
    Date: 2004–08–21
  8. By: Breugelmans E.; Campo K.; Gijsbrechts E.
    Abstract: This paper investigates the impact of an online retailer’s stock-out policy on purchase incidence and choice. We make a distinction between three policies: (1) stock-outs are immediately visible and there are no suggestions, (2) stock-outs are only visible after clicking and (3) a replacement item is suggested for each stock-out product. Results from an extensive and realistic online grocery shopping experiment reveal that the adopted stock-out policy has a significant impact on both decisions. First, making stock-outs not immediately visible creates confusion and intensifies the consumer’s loss experience, thereby reducing the tendency to buy in the category. Second, while suggesting a replacement item normally leads to a substantial increase in the item’s choice probability, this effect is canceled out when higher-priced – suspicious – items are suggested. Overall, these results indicate that retailers have an interest in pursuing open and convenience-oriented stock-out policies.
    Date: 2005–02

This nep-dcm issue is ©2005 by Philip Yu. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.