On the asymptotic optimality of the LIML estimator with possibly many instruments

We consider the estimation of the coefficients of a linear structural equation in a simultaneous equation system when there are many instrumental variables. We derive some asymptotic properties of the limited information maximum likelihood (LIML) estimator when the number of instruments is large; some of these results are new as well as old, and we relate them to results in some recent studies. We have found that the variance of the limiting distribution of the LIML estimator and its modifications often attain the asymptotic lower bound when the number of instruments is large and the disturbance terms are not necessarily normally distributed, that is, for the micro-econometric models of some cases recently called many instruments and many weak instruments.     

Promoting green buildings: Do Chinese consumers care about green building enhancements?

This paper explores sustainability‐related choices about buildings by analysing how consumers rated the relative importance of various attributes of conventional and green buildings. It also analyses how consumers judge environmental and health‐oriented improvements in green buildings. Unlike previous studies, this research applied conjoint analysis to explore the green building market at the consumer's level by regarding green buildings as nondurable green products and services. We used a survey to gather consumer preferences about several green building hotel models which partly applied green energy, modern wood structures and improved indoor environmental quality (IEQ). In total, 341 consumers participated the survey in two of China's largest cities: Beijing and Shanghai. The results revealed that green energy was the most preferred attribute of green buildings, exerting an even stronger overall effect on consumer choice than price. Afterwards, we identified distinct consumer segments and determined the background characteristics of each segment based on the similarities in the preferences for each attribute. The largest consumer segment, consisting of younger consumers, ranked green energy as the most important criterion. However, an improved indoor environmental quality was generally not highly ranked, and individuals in the consumer segment, which included more older and female consumers, were more likely to reject modern wood structures. The results also revealed that higher‐income individuals were most concerned with price, and consumers with higher levels of education were willing to pay more to support green buildings.     

On finite sample properties of alternative estimators of coefficients in a structural equation with many instruments

We compare four different estimation methods for the coefficients of a linear structural equation with instrumental variables. As the classical methods we consider the limited information maximum likelihood (LIML) estimator and the two-stage least squares (TSLS) estimator, and as the semi-parametric estimation methods we consider the maximum empirical likelihood (MEL) estimator and the generalized method of moments (GMM) (or the estimating equation) estimator. Tables and figures of the distribution functions of four estimators are given for enough values of the parameters to cover most linear models of interest and we include some heteroscedastic cases and nonlinear cases. We have found that the LIML estimator has good performance in terms of the bounded loss functions and probabilities when the number of instruments is large, that is, the micro-econometric models with “many instruments” in the terminology of recent econometric literature.     

Systematic review and analysis of efficacy of recombinant factor IX products for prophylactic treatment of hemophilia B in comparison with rIX-FP

Abstract

Aims: Prophylaxis with standard-acting recombinant factor IX (rFIX) in hemophilia B patients requires frequent injections. Extended half-life (EHL) products allow for prolonged dosing intervals, and so reduce this treatment burden. Three technologies are employed to extend the half-life of FIX; glycopegylation, Fc-fusion, and albumin fusion. rIX-FP is a novel albumin fusion protein, which allows for a prolonged dosing interval of up to 14?days. A systematic review and indirect statistical comparison was performed to evaluate the efficacy of both EHL and standard-acting rFIX products compared with rIX-FP in Phase III trials for prophylaxis in adult hemophilia B patients.

Materials and methods: A systematic search was conducted in both EMBASE and PubMed to identify Phase III trials of prophylactic rFIX treatment in previously treated hemophilia B patients aged ≥12?years (FIX ≤2%). Annualized bleeding rate (ABR), spontaneous ABR (AsBR), and joint ABR (AjBR) data were extracted from each study. A z-test was performed using the mean of each parameter, and the mean difference in outcome between studies was calculated.

Results: Seven articles investigating six rFIX products were identified. Median ABR, AsBR, and AjBR ranged from 0–3.0, 0–1.0, and 0–1.1 (means = 0.8–4.26, 0.13–2.6, and 0.34–2.85), respectively. rIX-FP achieved the lowest median and mean values in all three parameters. Z-tests showed that mean ABR was significantly lower for rIX-FP 7-day prophylaxis compared with the majority of standard-acting and other EHL rFIX products.

Limitations: The low number of appropriate trials available for comparison limits the quantity of data available for comparison, and restricts the use of methods of adjustment for variance in study design or patient characteristics. However, these limitations are shared with similar analyses published in this field.

Conclusion: This indirect comparison of Phase III trials indicates that rIX-FP efficacy compares favorably vs other rFIX products for prophylaxis in hemophilia B.     

Likelihood Inference on Semiparametric Models: Average Derivative and Treatment Effect

Over the past few decades, much progress has been made in semiparametric modelling and estimation methods for econometric analysis. This paper is concerned with inference (i.e. confidence intervals and hypothesis testing) in semiparametric models. In contrast to the conventional approach based on t‐ratios, we advocate likelihood‐based inference. In particular, we study two widely applied semiparametric problems, weighted average derivatives and treatment effects, and propose semiparametric empirical likelihood and jackknife empirical likelihood methods. We derive the limiting behaviour of these empirical likelihood statistics and investigate their finite sample performance through Monte Carlo simulation. Furthermore, we extend the (delete‐1) jackknife empirical likelihood toward the delete‐d version with growing d and establish general asymptotic theory. This extension is crucial to deal with non‐smooth objects, such as quantiles and quantile average derivatives or treatment effects, due to the well‐known inconsistency phenomena of the jackknife under non‐smoothness.     

Technological Progress and the Wage Growth of Older Japanese Workers

Declining birth and mortality rates are leading to population aging throughout the OECD countries. This paper examines one possible consequence for national productivity – we ask: Are older workers able to take advantage of new technologies as effectively as their younger counterparts? Using Japanese data for 1973-2000, we find that if we ignore job tenure, workers beyond the age of 50 do not seem as able to benefit from total factor productivity growth as their younger colleagues. However, Japanese workers past age 50 move to lesser paying positions more frequently than is common elsewhere, and we believe that the complete answer to our question depends upon whether an inability to keep up with new technologies induces late-in-career job changes or whether the changes follow, in practice, from other factors.     

Moment Estimation of the Probit Model with an Endogenous Continuous Regressor

We propose a generalized method of moments (GMM) estimator with optimal instruments for a probit model that includes a continuous endogenous regressor. This GMM estimator incorporates the probit error and the heteroscedasticity of the error term in the first‐stage equation in order to construct the optimal instruments. The estimator estimates the structural equation and the first‐stage equation jointly and, based on this joint moment condition, is efficient within the class of GMM estimators. To estimate the heteroscedasticity of the error term of the first‐stage equation, we use the k‐nearest neighbour (k‐nn) non‐parametric estimation procedure. Our Monte Carlo simulation shows that in the presence of heteroscedasticity and endogeneity, our GMM estimator outperforms the two‐stage conditional maximum likelihood estimator. Our results suggest that in the presence of heteroscedasticity in the first‐stage equation, the proposed GMM estimator with optimal instruments is a useful option for researchers.