Asymptotic Power Advantages of Long-Horizon Regression Tests

Author(s):  
Nelson C. Mark ◽  
Donggyu Sul
2021 ◽  
pp. 135481662110224
Author(s):  
Liang-Ju Wang ◽  
Ming-Hsiang Chen ◽  
Zhandong Yang ◽  
Ching-Hui (Joan) Su

This study proposes and tests two hypotheses concerning the effects of hotel industry operations on air quality based on data of 26 major tourist cities in China from 2002 to 2017. The empirical analyses take two steps. In the first step, panel regression test results reveal that hotel industry operations (measured by hotel sales revenue) significantly raise the value of particulate matter (PM)2.5 (the key indicator of air quality), supporting the first hypothesis that hotel industry operations deteriorate air quality and providing empirical evidence of the adverse impact of the hotel industry on air quality. In the second step, subsample analyses support the second hypothesis that the impact of hotel sales revenue on air quality diminishes over time. The results from the rolling regression tests validate the existence of a diminishing effect of hotel industry operations on air quality.


2014 ◽  
Vol 31 (3) ◽  
pp. 539-559 ◽  
Author(s):  
I. Gaia Becheri ◽  
Feike C. Drost ◽  
Ramon van den Akker

In a Gaussian, heterogeneous, cross-sectionally independent panel with incidental intercepts, Moon, Perron, and Phillips (2007, Journal of Econometrics 141, 416–459) present an asymptotic power envelope yielding an upper bound to the local asymptotic power of unit root tests. In case of homogeneous alternatives this envelope is known to be sharp, but this paper shows that it is not attainable for heterogeneous alternatives. Using limit experiment theory we derive a sharp power envelope. We also demonstrate that, among others, one of the likelihood ratio based tests in Moon et al. (2007, Journal of Econometrics 141, 416–459), a pooled generalized least squares (GLS) based test using the Breitung and Meyer (1994, Applied Economics 25, 353–361) device, and a new test based on the asymptotic structure of the model are all asymptotically UMP (Uniformly Most Powerful). Thus, perhaps somewhat surprisingly, pooled regression-based tests may yield optimal tests in case of heterogeneous alternatives. Although finite-sample powers are comparable, the new test is easy to implement and has superior size properties.


2021 ◽  
Author(s):  
Yan Yu ◽  
Jiasu Liu

Objectives: This meta-analysis aimed to identify the therapeutic effect of 0.01% atropine with on ocular axial elongation for myopia children. Methods: We searched PubMed, Cochrane Library, and CBM databases from inception to July 2021. Meta-analysis was conducted using STATA version 14.0 and Review Manager version 5.3 softwares. We calculated the weighted mean differences(WMD) to analyze the change of ocular axial length (AL) between orthokeratology combined with 0.01% atropine (OKA) and orthokeratology (OA) alone. The Cochran's Q-statistic and I2 test were used to evaluate potential heterogeneity between studies. To evaluate the influence of single studies on the overall estimate, a sensitivity analysis was performed. We also performed sub group and meta-regression analyses to investigate potential sources of heterogeneity. We conducted Begger's funnel plots and Egger's linear regression tests to investigate publication bias. Results: Nine studies that met all inclusion criteria were included in this meta-analysis. A total of 191 children in OKA group and 196 children in OK group were assessed. The pooled summary WMD of AL change was -0.90(95%CI=-1.25~-0.55) with statistical significance(t=-5.03, p<0.01), which indicated there was obvious difference between OKA and OK in myopic children. Subgroup analysis also showed that OKA treatment resulted in significantly less axial elongation compared to OK treatment alone according to SER. We found no evidence for publication bias. Conclusions:  Our meta-analysis indicates 0.01% atropine atropine is effective in slowing axial elongation in myopia children with orthokeratology.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Vinh Huy Nguyen ◽  
Carolina Gomez ◽  
Suchi Mishra ◽  
Ali M. Parhizgari

PurposeWe examine how the net share purchases of top executives of acquiring firms, specifically the Chief Executive Officer (CEO) and the Chief Operating Officer (COO), can impact shareholder perceptions of a merger and acquisition (M&A) around the announcement time.Design/methodology/approachRegression tests using the post-announcement cumulative returns as the dependent variables, and CEO and COO net purchases as independent test controlling for the net purchases of all other insiders, COO and CEO ownership, exercised options, unexercised exercisable options, merger type, pre-announcement firm size, past performance, industry growth, industry instability, year and industry fixed effects. The regression tests are used for various sub-samples (i.e. non-contemporaneous events, duality, operational complexity, economic conditions).FindingsWe find that overall shareholders value the COO's net purchases before the announcement but not those of the CEOs. If the COO is also the CEO, then executive buy-ins appear to have a negative reaction from the shareholders. When the firm has many business segments or when the announcement is made in an economic recession, the COO's net purchases do not have a positive influence on the shareholders.Originality/valueWe are the first to provide evidence that investors pay attention to the COO around M&A announcements. In the age of celebrity CEOs, who can instantaneously change the stock price with one press release, having another executive that can shape the opinion of investors can diversify the agency risk.


2017 ◽  
Vol 9 (1) ◽  
pp. 234
Author(s):  
Asiyeh Foshat ◽  
Reza Zarei

This study aims to analyze the relationship between organizational culture and silence with organizational health. The methodology of the study is correlation, and its statistical population is 642 that are all employers in Maskan Bank in Fars province. Sampling was executed through one-phase clustering sampling in which 130 persons were selected as statistical sample. Three questionnaires of organizational health (Hawaii et al., 1987), organizational culture (Hofstede, 1980), and organizational silence (Vacola & Bouradas, 2005) were used for collecting data. Data was analyzed step to step using Pearson correlation coefficient and multiple regression tests. Results indicated that there is a significant inverse relationship between organizational culture and silence with organizational health (less than 0.01). Higher level managers’ view of silence (among elements of organizational silence) and patriarchy (among elements of organizational culture) are capable of predicting organizational health in inverse. Other elements are not significantly capable in predicting organizational health.


Sign in / Sign up

Export Citation Format

Share Document