Semiparametric binary regression models under shape constraints with an application to Indian schooling data

We consider estimation of the regression function in a semiparametric binary regression model defined through an appropriate link function (with emphasis on the logistic link) using likelihood-ratio based inversion. The dichotomous response variable Δ$\Delta$ is influenced by a set of covariates that can be partitioned as (X,Z)$(X,Z)$ where Z$Z$ (real valued) is the covariate of primary interest and X$X$ (vector valued) denotes a set of control variables. For any fixed X$X$, the conditional probability of the event of interest (Δ=1$\Delta =1$) is assumed to be a non-decreasing function of Z$Z$. The effect of the control variables is captured by a regression parameter β$\beta$. We show that the baseline conditional probability function (corresponding to X=0$X=0$) can be estimated by isotonic regression procedures and develop a likelihood ratio based method for constructing asymptotic confidence intervals for the conditional probability function (the regression function) that avoids the need to estimate nuisance parameters. Interestingly enough, the calibration of the likelihood ratio based confidence sets for the regression function no longer involves the usual χ²${\chi }^2$ quantiles, but those of the distribution of a new random variable that can be characterized as a functional of convex minorants of Brownian motion with quadratic drift. Confidence sets for the regression parameter β$\beta$ can however be constructed using asymptotically χ²${\chi }^2$ likelihood ratio statistics. The finite sample performance of the methods are assessed via a simulation study. The techniques of the paper are applied to data sets on primary school attendance among children belonging to different socio-economic groups in rural India.     

Deep networks for predicting direction of change in foreign exchange rates

Trillions of dollars are traded daily on the foreign exchange (forex) market, making it the largest financial market in the world. Accurate forecasting of forex rates is a necessary element in any effective hedging or speculation strategy in the forex market. Time series models and shallow neural networks provide acceptable point estimates for future rates but are poor at predicting the direction of change and, hence, are not very useful for supporting profitable trading strategies. Machine learning classifiers trained on input features crafted based on domain knowledge produce marginally better results. The recent success of deep networks is partially attributable to their ability to learn abstract features from raw data. This motivates us to investigate the ability of deep convolution neural networks to predict the direction of change in forex rates. Exchange rates for the currency pairs EUR/USD, GBP/USD and JPY/USD are used in experiments. Results demonstrate that trained deep networks achieve satisfactory out‐of‐sample prediction accuracy.     

Medical Insurance Coverage and Health Production Efficiency

Conventional economic theory predicts that medical insurance coverage causes an inefficient production of health because of  ex ante  and  ex post  moral hazard effects. However, no research has empirically examined the magnitude of the inefficiency. This study empirically examines the impact of medical insurance on the technical efficiency of health production at the metropolitan level. The underlying health production function allows for preventive care, curative care, and behavioral factors. Data envelopment analysis determines relative technical efficiency. The multiple regression results indicate that insurance coverage generates inefficiency but the efficiency loss appears to be relatively small on the extensive margin.     

Patent Protection and R&D with Endogenous Market Structure

In a model with endogenous number of innovating firms, we show that whether patent protection increases R&D investment is ambiguous, and depends on the market demand function and the cost of R&D. If the market size increases with number of firms, patent protection reduces R&D investment if the cost of R&D is sufficiently high, and higher product differentiation increases the possibility of lower R&D investment under patent protection. If the market size does not increase with number of firms, patent protection never reduces R&D investment. We find that welfare is lower under patent protection than under no patent protection.     

On General and Specific Transfers for Child Support in Divorce

In a post-divorce equilibrium under joint legal custody of a child the paper compares the effect of two different transfer schemes, a general purpose transfer scheme and a specific purpose transfer scheme, from non-custodial parent to the custodial parent of the child on his/her welfare. Surprisingly, it finds that the marginal effects are neutral. The result contributes to the policy framework by suggesting that the lawyers/courts can choose the two alternatives equivalently in settling the child custody cases in a post-divorce situation. The paper also characterizes such transfer schemes and proves that the schemes can never restore the child’s welfare at the ‘happy marriage’ equilibrium level.

     

Modelling risk factors for fatal pedestrian crashes in Kolkata,India

Abstract

In developing countries, pedestrian safety is an issue of major concern. Although an extensive body of literature is available on the identification of elements related to the pedestrian’s risk; the studies are primarily conducted in urban areas of developed countries. The findings from these studies may only be partially relevant to the cities of an emerging country such as India. The present study analyzes historical crash records obtained from the “Kolkata Police” and identifies the risk factors at the road network level for the hazardous corridors posing a high risk to the pedestrians. The study findings reveal that pedestrians’ fatalities at intersections are associated with a high vehicular volume, higher pedestrian-vehicular interaction, high approach speed, overtaking tendency of vehicles, certain land-use type, encroachment of footpath, inadequate sight distance, inaccessible pedestrian crosswalk, wider minor carriageway, the absence of a pedestrian signal head, and lack of enforcement. On the other hand, the models outcomes reveal that pedestrians’ fatalities at midblock road segments are associated with low pedestrian volume, high approach speed, overtaking tendency of the vehicle, encroachment of footpath, on-street parking, wider road width, certain land-use type, inadequate sight distance, insufficient lighting, and inadequate pavement markings.     

Foreign Capital,Spillovers and Export Performance in Emerging Economies: Evidence from Indian IT Firms

The role of foreign capital inflow, foreign direct investment (FDI) and foreign portfolio investment (FPI), on export behavior of both recipients and non‐recipient competing firms in the same sector often guides economic development policy. By using panel data of Indian IT firms over 2000–2006, we show that FDI reduces the sunk costs of entering foreign markets and therefore positively effects both the decision to export and the export propensity of recipient firms. Foreign portfolio investment has no effect on the decision to export, but it does marginally increase the volume of exports. Further, these positive FDI and FPI recipient effects do not spill‐over to non‐recipients.     

Patent Protection,Innovation and Technology Licensing

We show that the common wisdom suggesting higher investment in innovation under a stronger patent protection may not be true if the innovator can license its technology ex‐post innovation. If the initial cost of production is high and the slope of the marginal cost of undertaking innovation is moderate, investment in innovation is maximised at a patent protection that is weaker than the strongest patent protection. Otherwise, strongest patent protection maximises investment in innovation. We also show that welfare is maximised neither at the strongest patent protection nor at the weakest patent protection but at an intermediate patent protection. Our results are important for patent policies.