|
on Discrete Choice Models |
| By: | Richard Williams (Notre Dame Sociology) |
| Abstract: | The assumptions of the ordered logit/probit models estimated by ologit and oprobit are often violated. When an ordinal regression model incorrectly assumes that error variances are the same for all cases, the standard errors are wrong and (unlike OLS regression) the parameter estimates are biased. Heterogeneous choice/ location-scale models, which can be estimated with the user-written program oglm, explicitly specify the determinants of heteroskedasticity in an attempt to correct for it. Further, these models can be used when the variance/variability of underlying attitudes is itself of substantive interest. In other instances, the parallel lines assumption of the ordered logit/probit model is violated; in such cases, a generalized ordered logit/probit model (estimated via gologit2) may be called for. This paper talks about how to interpret and use the models that are estimated by oglm and gologit2. We talk about key assumptions behind the models, when each type of model may be appropriate, when the models may be problematic, and how to interpret the results and make them easier to understand. |
| Date: | 2006–07–23 |
| URL: | http://d.repec.org/n?u=RePEc:boc:asug06:9&r=dcm |
| By: | Juan Mora (Universidad de Alicante); Ana I. Moro (Universidad de Granada) |
| Abstract: | We discuss how to test consistently the specification of an ordereddiscrete choice model. Two approaches are considered: tests based onconditional moment restrictions and tests based on comparisons betweenparametric and nonparametric estimations. Following these approaches,various statistics are proposed and their asymptotic properties are discussed.The performance of the statistics is compared by means of simulations. Avariant of the standard conditional moment statistic and a generalization ofHorowitz-Spokoiny’s statistic perform best. |
| Keywords: | Specification Tests, Ordered Discrete Choice Models; Statistical Simulation |
| JEL: | C25 C52 C15 |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:ivi:wpasad:2006-17&r=dcm |
| By: | Rinaldo Brau (University of Cagliari); Matteo Lippi Bruni (University of Bologna) |
| Abstract: | We evaluate the demand for long term care (LTC) insurance prospects in a stated preference context, by means of the results of a choice experiment carried out on a representative sample of the Emilia-Romagna population. Choice modelling techniques have not been used yet for studying the demand for LTC services. In this paper these methods are first of all used in order to assess the relative importance of the characteristics which define some hypothetical insurance programmes and to elicit the willingness to pay for some LTC coverage prospects. Moreover, thanks to the application of a nested logit specification with ‘partial degeneracy’, we are able to model the determinants of the preference for status quo situations where no systematic cover for LTC exists. On the basis of this empirical model, we test for the effects of a series of socio-demographic variables as well as personal and household health state indicators. |
| Keywords: | Health Insurance, Long Term Care, Choice Experiments, Nested Logit Models |
| JEL: | I11 I18 H40 C25 |
| Date: | 2006–05 |
| URL: | http://d.repec.org/n?u=RePEc:fem:femwpa:2006.71&r=dcm |
| By: | Jung, Robert; Kukuk, Martin; Liesenfeld, Roman |
| Abstract: | This paper compares various models for time series of counts which can account for discreetness, overdispersion and serial correlation. Besides observation- and parameter-driven models based upon corresponding conditional Poisson distributions, we also consider a dynamic ordered probit model as a flexible specification to capture the salient features of time series of counts. For all models, we present appropriate efficient estimation procedures. For parameter-driven specifications this requires Monte Carlo procedures like simulated Maximum likelihood or Markov Chain Monte-Carlo. The methods including corresponding diagnostic tests are illustrated with data on daily admissions for asthma to a single hospital. |
| Keywords: | Efficient Importance Sampling, GLARMA, Markov Chain Monte-Carlo, Observation-driven model, Parameter-driven model, Ordered Probit |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:cauewp:3194&r=dcm |
| By: | Roger Wilkins (Melbourne Institute of Applied Economic and Social Research, The University of Melbourne and IZA Bonn) |
| Abstract: | Using information collected by the 2001 Household Income and Labour Dynamics in Australia (HILDA) survey, I investigate the factors associated with underemployment, defined as a situation where a part-time employed person would like to work more hours in order to increase income. Multinomial logit models are estimated of labour force status in which underemployment is distinguished from other part-time employment. Effects of a wide range of personal and neighbourhood characteristics are examined, including family background, employment history and local labour market conditions. Underemployment is found to have many predictors in common with unemployment, but also a number of differences. Additional models are estimated on employed persons only that investigate the job characteristics associated with underemployment. Relatively few job characteristics predict underemployment as distinct from other part-time employment. |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:iae:iaewps:wp2006n16&r=dcm |
| By: | Sandra Sookram (Sir Arthur Lewis Institute of Social & Economic Studies, University of the West Indies, St. Augustine, Trinidad & Tobago); Friedrich G. Schneider (Department of Economics, Johannes Kepler University Linz, Austria); Patrick Kent Watson (Sir Arthur Lewis Institute of Social & Economic Studies, University of the West Indies, St. Augustine, Trinidad & Tobago) |
| Abstract: | Using the case study of Trinidad and Tobago we investigate for an emerging economy the socioeconomic, demographic, and attitudinal characteristics that influence the propensity of individuals in the household sector to participate in the hidden economy and their perception of the risk of detection by tax authorities in doing so. To this end we analyze data gathered from a unique cross-sectional field survey covering 570 households. Our econometric results using multinomial logit and ordered probit models suggest that individual household members are motivated to undertake hidden economic activity because they believe taxes are too high, their incomes are too low, they have dependents to support, and they believe that the resulting tax evasion will go undetected. |
| Keywords: | hidden economy; multinomial logit and ordered probit models; emerging economies |
| JEL: | C25 C51 E26 |
| Date: | 2006–05 |
| URL: | http://d.repec.org/n?u=RePEc:jku:econwp:2006_05&r=dcm |
| By: | Koetter, Michael; Bos, Jaap W. B.; Heid, Frank; Kool, Clemens J. M.; Kolari, James W.; Porath, Daniel |
| Abstract: | The inability of most bank merger studies to control for hidden bailouts may lead to biased results. In this study, we employ a unique data set of approximately 1,000 mergers to analyze the determinants of bank mergers. We use data on the regulatory intervention history to distinguish between distressed and non-distressed mergers. We find that, among merging banks, distressed banks had the worst profiles and acquirers perform somewhat better than targets. However, both distressed and non-distressed mergers have worse CAMEL profiles than our control group. In fact, non-distressed mergers may be motivated by the desire to forestall serious future financial distress and prevent regulatory intervention. |
| Keywords: | Mergers, bailout, X-efficiency, multinomial logit |
| JEL: | G14 G21 G34 |
| Date: | 2005 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp2:4264&r=dcm |