This paper summarizes the technical activities of the Task Force on Power System Dynamic State and Parameter Estimation. This Task Force was established by the IEEE Working Group on State Estimation ...Algorithms to investigate the added benefits of dynamic state and parameter estimation for the enhancement of the reliability, security, and resilience of electric power systems. The motivations and engineering values of dynamic state estimation (DSE) are discussed in detail. Then, a set of potential applications that will rely on DSE is presented and discussed. Furthermore, a unified framework is proposed to clarify the important concepts related to DSE, forecasting-aided state estimation, tracking state estimation, and static state estimation. An overview of the current progress in DSE and dynamic parameter estimation is provided. The paper also provides future research needs and directions for the power engineering community.
We propose a new statistical instrument-free method to tackle the endogeneity problem. The proposed method models the joint distribution of the endogenous regressor and the error term in the ...structural equation of interest (the structural error) using a copula method, and it makes inferences on the model parameters by maximizing the likelihood derived from the joint distribution. Similar to the "exclusion restriction" in instrumental variable methods, extant instrument-free methods require the assumption that the unobserved instruments are exogenous, a requirement that is difficult to meet. The proposed method does not require such an assumption. Other benefits of the proposed method are that it allows the modeling of discrete endogenous regressors and offers a new solution to the slope endogeneity problem. In addition to linear models, the method is applicable to the popular random coefficient logit model with either aggregate-level or individual-level data. We demonstrate the performance of the proposed method via a series of simulation studies and an empirical example.
Comment Belloni, Alexandre; Chernozhukov, Victor
Journal of the American Statistical Association,
12/2015, Letnik:
110, Številka:
512
Journal Article
Recenzirano
Corresponding inference procedures are much less well developed, and one of the interesting contributions of this article is the observation that the limiting distribution (here and throughout, the ...same notation as in the article is used) of ... is discontinuous at ... Such nonregular limiting distributions are well known to cause difficulties for the bootstrap (e.g., Beran 1997; Samworth 2003). Although in some settings, these issues are an artefact of the pointwise asymptotics of consistency usually invoked to justify the bootstrap (Samworth 2005), there are other settings where some modification of standard bootstrap procedures is required. Two such examples include bootstrapping Lasso estimators (Chatterjee and Lahiri 2011) and certain classification problems (Laber and Murphy 2011), where thresholded versions of the obvious estimators are bootstrapped, in an analogous fashion to the approach in this article. (ProQuest: ... denotes formulae/symbols omitted.)
Comment Zhang, Yichi; Laber, Eric B
Journal of the American Statistical Association,
12/2015, Letnik:
110, Številka:
512
Journal Article
Recenzirano
The following comments relate to material in McKeague and Qian (2015) (henceforth referred to as MQ). We have found this material to be very worthwhile reading and we thank the organizers for the ...opportunity to provide these comments. MQ study a maximum statistic, ..., that can be used to test for the null hypothesis of no effect of covariates in a linear-model analysis. Their major focus is on the development of a bootstrap style procedure that serves the dual purpose of estimating the distribution of ... and then using this estimate as the basis for a test of the null hypothesis. Our perspective is that their procedure is composed of two almost separate components -- a simulation of the distribution under the null and a bootstrap estimate that is valid away from the null. Our comments focus on the testing component of their procedure, and on alternate tests for this hypothesis. (ProQuest: ... denotes formulae/symbols omitted.)
Comment Leeb, Hannes
Journal of the American Statistical Association,
12/2015, Letnik:
110, Številka:
512
Journal Article
Recenzirano
When testing a simple null hypothesis, like ... as in the present case with ART, the nonuniformity problem outlined in the preceding section is not an issue, however. Here, the quantity of interest ...is the distribution of the (scaled) estimation error under the null, and this distribution can often be estimated, either directly or (as in the present article) by estimating or approximating the large-sample limit distribution under the null. (ProQuest: ... denotes formulae/symbols omitted.)