Parameter estimate for three-parameter kappa distribution using LHmoments approach

The method of higher-order L-moments (LH-moment) was proposed as a more robust alternative compared to classical L-moments to characterize extreme events. The new derivation will be done for Mielke-Johnson’s Kappa and Three-Parameters Kappa Type-II (K3D-II) distributions based on the LH-moments approach. The data of maximum monthly rainfall for Embong station in Terengganu were used as a case study. The analyses were conducted using the classical L-moments method with η=0 and LH-moments methods with η=1, η=2, η=3 and η=4 for a complete data series and upper parts of the distributions. The most suitable distributions were determined based on the Mean Absolute Deviation Index (MADI), Mean Square Deviation Index (MSDI), and Correlation (r). Also, L-moment and LH-moment ratio diagrams were used to represent visual proofs of the results. The analysis showed that LH-moments methods at a higher order of K3D-II distribution best fit the data of maximum monthly rainfalls for the Embong station for the upper parts of the distribution compared to L-moments. The results also proved that whenever η increases, LH-moments reflect more and more characteristics of the upper part of the distribution. This seems to suggest that LH-moments estimates for the upper part of the distribution events are superior to L-moments in fitting the data of maximum monthly rainfalls.

LH-Moments of the Wakeby Distribution applied to Extreme Rainfall in Thailand

This article applies the Wakeby distribution (WAD) with high-order L-moments estimates (LH-ME) to annual extreme rainfall data obtained from 99 gauge stations in Thailand. The objectives of this study investigate to obtain appropriate quantile estimates and return levels for several return periods, 2, 5, 10, 25 and 50 years. The 95% confidence intervals for the quantiles determined from the WAD are derived using the bootstrap technique. Isopluvial maps of estimated design values that correspond to selected return periods are presented. The LH-ME results are better than estimates from the more primitive L-moments method for a large majority of the stations considered.

VC: a method for estimating time-varying coefficients in linear models

This paper describes a moments estimator for a standard state-space model with coefficients generated by a random walk. The method calculates the conditional expectations of the coefficients, given the observations. A penalized least squares estimation is linked to the GLS (Aitken) estimates of the corresponding linear model with time-invariant parameters. The estimates are moments estimates. They do not require the disturbances to be Gaussian, but if they are, the estimates are asymptotically equivalent to maximum likelihood estimates. In contrast to Kalman filtering, no specification of an initial state or an initial covariance matrix is required. While the Kalman filter is one sided, the filter proposed here is two sided and therefore uses more of the available information for estimating intermediate states. Further, the proposed filter has a clear descriptive interpretation.

Volatility filtering in estimation of kurtosis (and variance)

The kurtosis of the distribution of financial returns characterized by high volatility persistence and thick tails is notoriously difficult to estimate precisely. We propose a simple but effective procedure of estimating the kurtosis coefficient (and variance) based on volatility filtering that uses a simple GARCH model. In addition to an estimate, the proposed algorithm issues a signal of whether the kurtosis (or variance) is finite or infinite. We also show how to construct confidence intervals around the proposed estimates. Simulations indicate that the proposed estimates are much less median biased than the usual method-of-moments estimates, their confidence intervals having much more precise coverage probabilities. The procedure alsoworks well when the underlying volatility process is not the one the filtering technique is based on. We illustrate how the algorithm works using several actual series of returns.

Impact of extended alliance portfolio configuration on firm innovation

In the past, alliance portfolio configuration (APC) studies concentrated mostly on the direct alliances or partners of a focal firm. However, a focal firm is also influenced by indirect alliances or partners. This study endeavors to focus on this aspect of APC. It contributes to APC research by extending the scope to three degrees from a focal firm. To assess the effects of extended APCs, 186 3-year window snapshots were created of the extended APCs of 31 Korean bio-pharmaceutical firms. These snapshots range from 2007 to 2014. The effects of structure (density), size (number of alliances and partners), and relationships to firm innovation were measured using the two-step generalized method of moments estimates. The results show that structural sparseness and larger-sized extended APCs are more favorable conditions for innovation, and that structural sparseness and size have a positive relationship to innovation performance.

Production Function Estimation in Stata Using the Ackerberg–Caves–Frazer Method

We present a new e-class command, acfest, that implements the method of Ackerberg, Caves, and Frazer (2015, Econometrica 83: 2411–2451) to estimate production functions. This method deals with the functional dependence problems that may arise in the methods proposed by Olley and Pakes (1996, Econometrica 64: 1263–1297) and, particularly, Levinsohn and Petrin (2003, Review of Economic Studies 70: 317–341) (implemented in Stata by Yasar, Raciborski, and Poi [2008, Stata Journal 8: 221–231] and Petrin, Poi, and Levinsohn [2004, Stata Journal 4: 113–123], respectively). In particular, the acfest command yields (nonlinear, robust) generalized method of moments estimates using a Mata function and two specification tests (Wald and Sargan–Hansen). After estimation, predict provides the estimated productivity of the firms in the sample.