Search results

The purpose of this paper is to investigate the design method of partial observer canonical form (POCF), which is one of the important research tools for industrial plants.

Motivated by the two-steps method proposed in Xu et al. (2020), this paper extends this method to the case of Multi-Input Multi-Output (MIMO) nonlinear system. It decomposes the original system into two subsystems by observable decomposition theorem first and then transforms the observable subsystem into OCF. Furthermore, the necessary and sufficient conditions for the existing of POCF are proved.

The proposed method has a wide range of applications including completely observable nonlinear system, noncompletely observable nonlinear system, autonomous nonlinear system and forced nonlinear system. Besides, comparing to the existing results (Saadi et al., 2016), the method requires less verified conditions.

The new method concerning design POCF has better plants compatibility and less validation conditions.

The objective of this paper is to evaluate the learning gap between private and public school children in primary school, and ascertain the part of the private–public school learning gap that is due to differences in observables and the part that can be attributed to private school effect.

The paper utilized a household survey data from Ghana that assessed children on numeracy and literacy in both English and local languages. The primary methodology for this study is non-linear Oaxaca decomposition. The study also utilized Welch's t-statistics to test if there are any differences in the private–public school learning gaps across several sub-groups.

Findings from this study show a substantial gain for private school attendance on both numeracy and literacy. The results show that a little over 60% of the total learning gap in numeracy and literacy in English is explained by observable characteristics. However, observable characteristics almost explain all the learning gaps in the reading and writing of local languages. Evidence from the study suggests that the private school effect is homogeneous across several sub-groups. The results reveal years of education, expenditure on extra classes, religion and urbanicity as the most important variables explaining the gap that is caused by differences in observables.

Despite the belief that private school children in Ghana have better learning outcomes, there has not been any study to quantify this learning gap in the country and this study fills this gap. While there is literature on the differences in the learning outcomes between public and private schools, those studies have focused on the differences that are attributable to the private school effect. This article does not only present the differences in the learning outcomes but also shows the proportion that is due to observable characteristics and the part that can be attributed to the private school effect.

We compare methods to measure comovement in business cycle data using multi-level dynamic factor models. To do so, we employ a Monte Carlo procedure to evaluate model performance for different specifications of factor models across three different estimation procedures. We consider three general factor model specifications used in applied work. The first is a single-factor model, the second a two-level factor model, and the third a three-level factor model. Our estimation procedures are the Bayesian approach of Otrok and Whiteman (1998), the Bayesian state-space approach of Kim and Nelson (1998) and a frequentist principal components approach. The latter serves as a benchmark to measure any potential gains from the more computationally intensive Bayesian procedures. We then apply the three methods to a novel new dataset on house prices in advanced and emerging markets from Cesa-Bianchi, Cespedes, and Rebucci (2015) and interpret the empirical results in light of the Monte Carlo results.

This survey focuses on two families of nonlinear vector time series models, the family of vector threshold regression (VTR) models and that of vector smooth transition regression (VSTR) models. These two model classes contain incomplete models in the sense that strongly exogeneous variables are allowed in the equations. The emphasis is on stationary models, but the considerations also include nonstationary VTR and VSTR models with cointegrated variables. Model specification, estimation and evaluation is considered, and the use of the models illustrated by macroeconomic examples from the literature.

The role of trend inflation shocks for the U.S. macroeconomic dynamics is investigated by estimating two DSGE models of the business cycle. Policymakers are assumed to be concerned with a time-varying inflation target, which is modeled as a persistent and stochastic process. The identification of trend inflation shocks (as opposed to a number of alternative innovations) is achieved by exploiting the measure of trend inflation recently proposed by Aruoba and Schorfheide (2011). Our main findings point to a substantial contribution of trend inflation shocks for the volatility of inflation and the policy rate. Such contribution is found to be time dependent and highest during the mid-1970s to mid-1980s.

The purpose of this paper is to present the methodology that was used to perform system identification of a dynamically unstable tilt-rotor from flight test data. The method incorporated wavelet transform into the maximum likelihood principle formulation, emphasizing both time and frequency responses. Using wavelets allowed to additionally filter noise in the data, and this increased the estimation quality. This approach did not require measurement and process noise modeling in contrast to the Kalman filter usage for parameter estimation.

In the study, lateral-directional stability and control derivatives of an unstable tiltrotor in hover were estimated. This was performed by applying the maximum likelihood output error method. The estimated model response was decomposed using the Mallat pyramid and matched to wavelet coefficients obtained directly from measurements. In addition, a coherence-based weighting function was used to put more emphasis on the most reliable data. For comparison, the same set of data was used to identify a model with the same structure using the maximum likelihood principle with an incorporated Kalman filter.

It was found that maximum likelihood principle and wavelet transform allowed for estimating aerodynamic coefficients of a dynamically unstable aircraft. The estimation was performed with high accuracy.

The designed method can be used for system identification of unstable aircraft and when additional noise is present (e.g. when noise due to turbulence was observable during the flight test or higher noise levels were present in the sensors data).

The paper presents verification of a wavelet-based maximum likelihood principle output error method using flight test data.

I survey applications of Markov switching models to the asset pricing and portfolio choice literatures. In particular, I discuss the potential that Markov switching models have to fit financial time series and at the same time provide powerful tools to test hypotheses formulated in the light of financial theories, and to generate positive economic value, as measured by risk-adjusted performances, in dynamic asset allocation applications. The chapter also reviews the role of Markov switching dynamics in modern asset pricing models in which the no-arbitrage principle is used to characterize the properties of the fundamental pricing measure in the presence of regimes.

Using matched data from the 1996 to 2004 Current Population Survey (CPS), we examine racial patterns in annual transitions into and out of health insurance coverage. We first decompose racial differences in static health insurance coverage rates into group differences in transition rates into and out of health insurance coverage. The low rate of health insurance coverage among African-Americans is due almost entirely to higher annual rates of losing health insurance than whites. Among the uninsured, African-Americans have similar rates of gaining health insurance in the following year as whites. Estimates from the matched CPS also indicate that the lower rate of health insurance coverage among Asians is almost entirely accounted for by a relatively high rate of losing health insurance. In contrast to these findings, differences in health insurance coverage between Latinos and whites are due to group differences in both the rate of health insurance loss and gain. Using logit regression estimates, we also calculate nonlinear decompositions for the racial gaps in health insurance loss and gain. We find that two main factors are responsible for differences in health insurance loss between working-age whites and minorities: job loss and education level. Higher rates of job loss account for 30 percent of the health insurance gap for African-Americans and Asians, and 16 percent of the health insurance gap for Latinos. Lower levels of education explain roughly 15 percent of the gap for African-Americans and Latinos (Asians' higher levels of education serve to close the gap). Higher rates of welfare and SSI participation among African-Americans also serve to widen the gap in health insurance loss by 8 percent.