Composite Likelihood Research Articles

Simple approaches to nonlinear difference-in-differences with panel data

Summary I derive simple, flexible strategies for difference-in-differences settings where the nature of the response variable may warrant a nonlinear model. I allow for general staggered interventions, with and without covariates. Under an index version of parallel trends, I show that average treatment effects on the treated (ATTs) are identified for each cohort and calendar time period in which a cohort was subjected to the intervention. The pooled quasi-maximum likelihood estimators in the linear exponential family extend pooled ordinary least squares estimation of linear models. By using the conditional mean associated with the canonical link function, imputation and pooling across the entire sample produce identical estimates. Generally, pooled estimation results in very simple computation of the ATTs and their standard errors. The leading cases are a logit functional form for binary and fractional outcomes—combined with the Bernoulli quasi-log likelihood (QLL)—and an exponential mean combined with the Poisson QLL.

Quasi-maximum likelihood-based estimator of the hyperbolic frequency modulated signals

The quasi-maximum likelihood (QML) algorithm has been extended to estimate the phase parameters and the instantaneous frequency (IF) of the hyperbolic frequency modulated (HFM) signals. The Nelder-Mead simplex algorithm (NMSA) is adopted for a fine estimation. The obtained accuracy is excellent with the estimates achieving the Cramer-Rao lower bound (CRLB) above the signal-to-noise (SNR) threshold of 0 dB. The proposed technique is capable of functioning with signals that are sampled below the requirements of the sampling theorem, which is particularly important for HFM signals. Additionally, there are no limitations for signals with monotonic IF and/or group delay (GD) functions.

Generalized Method of Moments Estimation of Realized Stochastic Volatility Model

The purpose of this paper is to study the generalized method of moments (GMM) estimation procedures of the realized stochastic volatility model; we give the moment conditions for this model and then obtain the estimation of parameters. Then, we apply these moment conditions to the realized stochastic volatility model to improve the volatility prediction effect. This paper selects the Shanghai Composite Index (SSE) as the original data of model research and completes the volatility prediction under a realized stochastic volatility model. Markov chain Monte Carlo (MCMC) estimation and quasi-maximum likelihood (QML) estimation are applied to the parameter estimation of the realized stochastic volatility model to compare with the GMM method. And the volatility prediction accuracy of these three different methods is compared. The results of empirical research show that the effect of model prediction using the parameters obtained by the GMM method is close to that of the MCMC method, and the effect is obviously better than that of the quasi-maximum likelihood estimation method.

Phylogenetic tree of Proteus spp. Based on partial rpoB gene sequence analysis

Due to the importance of the proposed rpoB gene as an alternative biomarker for microbial community studies, this study has focused on phylogenetic relationships among local Proteus clinical isolates. Fifty bacterial isolates were collected and identified phenotypically according to the culture, microscopic examination and biochemical tests. VITEK 2 compact system was used to confirm identification. Genotypic identification was performed after DNA extraction for 10 selected isolates and amplification with rpoB gene-specific primer and gel electrophoresis. The products were detected with a ( 1090 bp ) molecular size band, which was sent for Sanger sequencing using an ABI3730XL automated DNA sequencer, and data were analyzed and compared with standard sequences in GenBank.The isolates have been registered in the National Center for Biotechnology Information (NCBI) with accession numbers and named (HIMUS1, HIMUS2, HIMUS3, HIMUS4, HIUS5, HIMUS6, HIMUS7, HIMUS8, HIMUS9 and HIMUS10 ). The phylogenetic tree was constructed using partial (895 bp) rpoB gene sequences for those ten strains. Evolutionary distances were calculated using the method of Maximum Composite Likelihood with 1000 bootstrap replicates using GENEIOUS software. The sequences presented a similarity percentage ranging between (98.76% and 100%) when compared with the sequences of standard strains in NCBI. Keywords: rpoB gene, Proteus spp. Sequencing, Phylogenetic analysis

Estimation of Realized Asymmetric Stochastic Volatility Models Using Kalman Filter

Despite the growing interest in realized stochastic volatility models, their estimation techniques, such as simulated maximum likelihood (SML), are computationally intensive. Based on the realized volatility equation, this study demonstrates that, in a finite sample, the quasi-maximum likelihood estimator based on the Kalman filter is competitive with the two-step SML estimator, which is less efficient than the SML estimator. Regarding empirical results for the S&P 500 index, the quasi-likelihood ratio tests favored the two-factor realized asymmetric stochastic volatility model with the standardized t distribution among alternative specifications, and an analysis on out-of-sample forecasts prefers the realized stochastic volatility models, rejecting the model without the realized volatility measure. Furthermore, the forecasts of alternative RSV models are statistically equivalent for the data covering the global financial crisis.

Forecasting Value-at-Risk using functional volatility incorporating an exogenous effect

This paper proposes a novel extension of log and exponential GARCH models, where time-varying parameters are approximated by orthogonal polynomial systems. These expansions enable us to add and study the effects of market-wide and external international shocks on the volatility forecasts and provide a flexible mechanism to capture various dynamics of the parameters. We examine the performance of the new model in both theoretical and empirical analysis. We investigate the asymptotic properties of the quasi-maximum likelihood estimators under mild conditions. The small-sample behavior of the estimators is studied via Monte Carlo simulation. The performance of the proposed models, in terms of accuracy of both volatility estimation and Value-at-Risk forecasts, is assessed in an empirical study of a set of major stock market indices. The results support the proposed specifications with respect to the corresponding constant-parameters models and to other time-varying parameter models.

The Spatial Autoregressive Panel Data Model with Spatial Moving Average Errors

This paper advocates the wider use of the spatial autoregressive (AR) panel data model with spatial moving average (MA) errors, individual and time effects, and different spatial weight matrices for each spatial lag. We demonstrate the practical relevance of this model, derive and investigate the asymptotic properties of a simple quasi maximum likelihood within estimator when is large and is finite, and provide an empirical example explaining military expenditures in 144 countries over the period 1993–2007.

Inference and forecasting for continuous-time integer-valued trawl processes

This paper develops likelihood-based methods for estimation, inference, model selection, and forecasting of continuous-time integer-valued trawl processes. The full likelihood of integer-valued trawl processes is, in general, highly intractable, motivating the use of composite likelihood methods, where we consider the pairwise likelihood in lieu of the full likelihood. Maximizing the pairwise likelihood of the data yields an estimator of the parameter vector of the model, and we prove consistency and, in the short memory case, asymptotic normality of this estimator. When the underlying trawl process has long memory, the asymptotic behaviour of the estimator is more involved; we present some partial results for this case. The pairwise approach further allows us to develop probabilistic forecasting methods, which can be used to construct the predictive distribution of integer-valued time series. In a simulation study, we document the good finite sample performance of the likelihood-based estimator and the associated model selection procedure. Lastly, the methods are illustrated in an application to modelling and forecasting financial bid–ask spread data, where we find that it is beneficial to carefully model both the marginal distribution and the autocorrelation structure of the data.

Profile Maximum Likelihood Estimation of Single-Index Spatial Dynamic Panel Data Model

In this paper, the spatial dynamic panel data (SDPD) model is extended to the single-index spatial dynamic panel data (Si-SDPD) model by introducing a nonlinear connection function to reflect the interaction between explanatory variables. The Si-SDPD model not only retains the advantages of the parametric SDPD model in dealing with spatial and temporal interaction effects and spatio-temporal dependencies, but also solves the limitations of the parametric SDPD model that may lead to missed bias. It reduces the data dimension of non-parametric models and enhances the practicability and explanatory power of parametric models. Since the parts of the model to be estimated contain unknown functions, we propose a new estimation method, a profile maximum likelihood (PML) method, to solve the problem of incidental parameters in the estimation. Under the assumption that the spatial coefficients are known, we preliminarily estimate the unknown function by carrying out local polynomial estimation, so as to transform the model into the parametric form for solving purposes. We then solve the dynamic panel parametric model via quasi-maximum likelihood (QML) estimation. We derive the asymptotic properties of profile maximum likelihood estimators (PMLEs) and find that, under certain regularity conditions, both parametric and non-parametric estimators are consistent. Monte Carlo results show that PMLEs have good finite sample performance.

Effect of the U.S.–China Trade War on Stock Markets: A Financial Contagion Perspective

In this article, to model risk contagion between the U.S. and China stock markets based on high-frequency financial data, we develop a novel continuous-time jump-diffusion process. For example, we consider three channels for volatility contagion—such as integrated volatility, positive jump variation, and negative jump variation—and each stock market is able to affect the other stock market as an overnight risk factor. We develop a quasi-maximum likelihood estimator for model parameters and establish its asymptotic properties. Furthermore, to identify contagion channels and test the existence of a structural break with a known structural break date, we propose hypothesis test procedures. Using the proposed diffusion model with high-frequency financial data, we investigate the effect of the U.S.–China trade war on stock markets from a financial contagion perspective. From the empirical study, we find evidence of financial contagion from the United States to China and evidence that the risk contagion channel has changed from integrated volatility to negative jump variation.

CherryML: scalable maximum likelihood estimation of phylogenetic models.

Phylogenetic models of molecular evolution are central to numerous biological applications spanning diverse timescales, from hundreds of millions of years involving orthologous proteins to just tens of days relating to single cells within an organism. A fundamental problem in these applications is estimating model parameters, for which maximum likelihood estimation is typically employed. Unfortunately, maximum likelihood estimation is a computationally expensive task, in some cases prohibitively so. To address this challenge, we here introduce CherryML, a broadly applicable method that achieves several orders of magnitude speedup by using a quantized composite likelihood over cherries in the trees. The massive speedup offered by our method should enable researchers to consider more complex and biologically realistic models than previously possible. Here we demonstrate CherryML's utility by applying it to estimate a general 400 × 400 rate matrix for residue-residue coevolution at contact sites in three-dimensional protein structures; we estimate that using current state-of-the-art methods such as the expectation-maximization algorithm for the same task would take >100,000 times longer.

Effect of Long-Term Absenteeism on the Operating Revenues, Productivity, and Employment of Enterprises

(1) Background: Previous studies have shown that absenteeism is negatively associated with employee-level performance, but we do not know how exactly absenteeism affects enterprise-level performance. To bridge this knowledge gap, we investigate how average long-term absenteeism affects Norwegian enterprises’ operating revenues and productivity. Also, we investigate if absenteeism decreases employment and whether operating revenues mediate the association. (2) Methods: We performed an enterprise-level dynamic unconditional quasi-maximum likelihood fixed-effects panel regression. (3) Results: The average share of long-term absenteeism nonlinearly decreases operating revenues and overall productivity at an increasing rate. The nonlinear effect may indicate deteriorating value creation among the share of employees largely not absent, but their productivity actually increases at an increasing rate. Thus, the overall findings indicate that the least productive employees first tend to opt out of the workforce, and as absenteeism increases, those subsequently opting out are otherwise increasingly productive. In parallel, those remaining in the workforce are increasingly productive. Absenteeism, moreover, decreases employment the following year, which is partly explained by revenue losses. However, enterprises cut their workforce due to factors beyond the impact of absenteeism on revenues.

Estimation of spatial autoregressive models for origin–destination flows: A partial likelihood approach

We extend LeSage and Pace (2008)’s spatial autoregressive model for origin–destination flows by accommodating two-way fixed effects. A partial likelihood approach is used for estimation by applying an orthogonal transformation to remove fixed effects in the model. The quasi-maximum likelihood (QML) estimator of the partial log-likelihood function is consistent and asymptotically centered normal. Monte Carlo experiments verify this advantage in finite samples. From the U.S. migration flows, significant spatial influences are captured with smaller magnitudes than those from the model without fixed effects.

Does agricultural cooperative membership impact the poverty level of cocoa farmers in southwestern Nigeria?

ABSTRACT The study examined the impact of agricultural cooperatives on poverty depth of cocoa farmers’ poverty levels in Southwestern Nigeria. A multistage sampling technique was used in selecting 362 cocoa farmers in the study area. The results of a two-step control function quasi-maximum likelihood revealed that age, household size, farm size, and farming experience positively influenced the poverty depth while cooperative membership negatively influenced the depth of poverty among cocoa farmers. This study concludes that cooperative organizations have the potential to reduce poverty effectively, provided their values and principles are respected. Hence, an advocate for continued policy incentives targeted at encouraging farmers to form as well as participate in agricultural cooperatives.

Variable Selection of High-Dimensional Spatial Autoregressive Panel Models with Fixed Effects

This paper studies the variable selection of high-dimensional spatial autoregressive panel models with fixed effects in which a matrix transformation method is applied to eliminate the fixed effects. Then, a penalized quasi-maximum likelihood is developed for variable selection and parameter estimation in the transformed panel model. Under some regular conditions, the consistency and oracle properties of the proposed estimator are established. Some Monte-Carlo experiments and a real data analysis are conducted to examine the finite sample performance of the proposed variable selection procedure, showing that the proposed variable selection method works satisfactorily.

Analysis of East Asia Wind Vectors Using Space–Time Cross-Covariance Models

As the risk posed by climate change becomes increasingly evident, countries across the world are constantly seeking alternative energy sources. Wind energy has substantial potential for future energy portfolios without having negative impacts on the environment. In developing nationwide and worldwide energy plans, understanding the spatio-temporal pattern of wind is crucial. We analyze wind vectors in the region of East Asia from the fifth-generation ECMWF atmospheric reanalysis. To model the wind vectors, we consider Tukey g-and-h transformation-based non-Gaussian processes, along with multivariate covariance functions. The proposed model can address non-Gaussian features and nonstationary dependence structures of wind vectors. In addition, a two-step inference scheme coupled with the composite likelihood method is applied to handle the computational issues posed by a large dataset. In the first step, we fit the temporal dependence structures of data with a location-specific non-Gaussian time series model. This allows us to remove substantial amounts of nonstationary variations in both space and time, and thus, relatively simple covariance models can handle large and complicated data in the second step. We show that the proposed method with a covariance structure reflecting the nonstationarity due to the latitude difference and the land–ocean difference leads to better predictions for wind speed as well as wind potential, which is crucial for planning wind power generation.

A Dynamic Ordered Logit Model with Fixed Effects

Abstract We study a fixed-T panel data logit model for ordered outcomes that accommodates fixed effects and state dependence. We provide identification results for the autoregressive parameter, regression coefficients, and the threshold parameters in this model. Our results require only four observations on the outcome variable. We provide conditions under which a composite conditional maximum likelihood estimator is consistent and asymptotically normal. We use our estimator to explore the determinants of self-reported health in a panel of European countries over the period 2003–2016 and find evidence for state dependence in self-reported health.

Effective estimation of nonlinear errors-in-variables models

Model variables are inevitably affected and interfered by measurement errors in statistical models inference. In this paper, we investigate the effective estimators of unknown operators in the nonlinear errors-in-variables models. By combining the maximum quasi-likelihood approach and the nonparametric local estimation method, a modified approximate maximum quasi-likelihood estimators are applied to evaluate the unknown parameters of the models. Under some mild assumptions, the consistency and asymptotic normality of the corresponding estimators are established. In order to further illustrate the advantages of the modified approach, we utilize simulation examples and actual data of monozygotic twins for analysis. The results visually show the robustness of the modified estimator as well as higher precision and accuracy.

Simultaneous modeling of multivariate heterogeneous responses and heteroskedasticity via a two-stage composite likelihood.

Multivariate heterogeneous responses and heteroskedasticity have attracted increasing attention in recent years. In genome-wide association studies, effective simultaneous modeling of multiple phenotypes would improve statistical power and interpretability. However, a flexible common modeling system for heterogeneous data types can pose computational difficulties. Here we build upon a previous method for multivariate probit estimation using a two-stage composite likelihood that exhibits favorable computational time while retaining attractive parameter estimation properties. We extend this approach to incorporate multivariate responses of heterogeneous data types (binary and continuous), and possible heteroskedasticity. Although the approach has wide applications, it would be particularly useful for genomics, precision medicine, or individual biomedical prediction. Using a genomics example, we explore statistical power and confirm that the approach performs well for hypothesis testing and coverage percentages under a wide variety of settings. The approach has the potential to better leverage genomics data and provide interpretable inference for pleiotropy, in which a locus is associated with multipletraits.

Exponential control of the trajectories of iterated function systems with application to semi-strong GARCH models

AbstractWe establish new results on the strictly stationary solution to an iterated function system. When the driving sequence is stationary and ergodic, though not independent, the strictly stationary solution may admit no moment but we show an exponential control of the trajectories. We exploit these results to prove, under mild conditions, the consistency of the quasi-maximum likelihood estimator of GARCH(p,q) models with non-independent innovations.