In this paper, we propose GMM estimators for short dynamic panel data models with interactive fixed effects. Moment conditions are obtained for the model where the projection method is applied to remove the correlation between regressors and interactive fixed effects. Monte Carlo simulation shows that the proposed GMM estimators perform reasonably well in finite sample.
We propose a family of robust nonparametric estimators for regression function based on the kernel method. We establish the almost complete convergence rate of these estimators under the α-mixing assumption and on the concentration properties on small balls of the probability measure of the functional regressors. Some applications to physics real data have been made. These results are extensions to dependent data of the results given by Azzedine et al. (2008).
In this paper, we consider a parallel profile model for several groups. Given the parallel profile model we construct tests based on the likelihood ratio, without any restrictions on the parameter space, for testing the covariance matrix for random-effects structure or sphericity. Furthermore, given both the parallel profile and random-effects covariance structure the level hypothesis is tested. The attained significance levels and the empirical powers for the given tests in this paper are compared with the tests given by Yokoyama and Fujikoshi (1993) and Yokoyama (1995).
This paper develops an asymptotic expansion of a percentile point of the Gini-based standardized sample mean. Such approximate percentiles can be used for proposing tests of hypotheses or confidence intervals of μ when samples arrive from a normal distribution with unknown mean μ and standard deviation σ. We have asymptotically expressed the percentile point bm,α of the Gini-based pivot (1.5), that is, the Gini-based standardized sample mean. Using large-scale simulations, approximations, and data analyses, we report that the Gini-based test and confidence interval procedures for μ perform better or practically as well as the customarily employed Student's t-based procedures when samples arrive from a normal distribution with suspect outliers. This interesting finding is especially noteworthy when we have a small random sample from a normal population with possible outliers.
The effect of trawling on seabed fauna in the Northern Prawn Fishery experimental region of Australia is investigated through distributional changes in individual weights for each species. A stochastic growth model is employed to overcome a limited number of effective observations. One statistical challenge is to deal with non-identically distributed observations as only total weights and numbers of individuals caught for each species are observed. A modified Cramér-von Mises statistic is introduced and the p-values are evaluated by random number generation. As a result, the gamma distribution, the equilibrium distribution of the stochastic growth model fits well to 57 out of 80 cases before trawling. We conclude that most of the species are unaffected by trawling but several other species are shifted towards lighter weights. The unevenness of the effect over regions suggests that other environmental effects and ecological factors are involved.
This paper considers properties of the fixed-width confidence interval of the difference of two normal means constructed assuming equal variances when the variances are unequal. We explore the coverage probability of the interval and the sample size. Furthermore, we compare the expected total sample size with that of the fixed width confidence interval constructed without such an assumption.