A Comparative Study of Some Modified Chi-Squared Tests

Voinov, Vassilly; Pya, Natalya; Alloyarova, Roza

doi:10.1080/03610910802501789

Cited by 22 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relative importance of the explanatory variables with significant regression coefficients derived from the multiple linear regression model was determined using random forest regression quantified by the total decrease in node impurity (IncNodePurity) (Grömping, 2009). The correlations among different explanatory and target variables as mentioned above were determined by correlation analysis including Pearson's linear regression (continuous vs. continuous variable), Kruskal–Wallis rank sum test (categorical vs. continuous variable) and Pearson's chi‐squared test (categorical vs. categorical variable) (Liu et al, 2020; Ostertagová et al, 2014; Voinov et al, 2009). The multivariate and correlation analysis was implemented in R statistical computing software using in‐built functions and the “randomForest” package (R Core Team, 2018).…”

Section: Methodsmentioning

confidence: 99%

Global evaluation of inhibitor impacts on ammonia and nitrous oxide emissions from agricultural soils: A meta‐analysis

Fan

Smith

et al. 2022

Global Change Biology

View full text Add to dashboard Cite

Inhibitors are widely considered an efficient tool for reducing nitrogen (N) loss and improving N use efficiency, but their effectiveness is highly variable across agroecosystems. In this study, we synthesized 182 studies (222 sites) worldwide to evaluate the impacts of inhibitors (urease inhibitors [UI], nitrification inhibitors [NI] and combined inhibitors) on crop yields and gaseous N loss (ammonia [NH3] and nitrous oxide [N2O] emissions) and explored their responses to different management and environmental factors including inhibitor application timing, fertilization regime, cropping system, water management, soil properties and climatic conditions using subgroup meta‐analysis, meta‐regression and multivariate analyses. The UI were most effective in enhancing crop yields (by 5%) and reducing NH3 volatilization (by 51%), whereas NI were most effective at reducing N2O emissions (by 49%). The application of UI mitigates NH3 loss and increases crop yields especially in high NH3‐N loss scenarios, whereas NI application would minimize the net N2O emissions and the resultant environmental impacts especially in low NH3‐N loss scenarios. Alternatively, the combined application of UI and NI enables producers to balance crop production and environmental conservation goals without pollution tradeoffs. The inhibitor efficacy for decreasing gaseous N loss was dependent upon soil and climatic conditions and management practices. Notably, both meta‐regression and multivariate analyses suggest that inhibitors provide a greater opportunity for reducing fertilizer N inputs in high‐N‐surplus systems and presumably favor crop yield enhancement under soil N deficiency situations. The pursuit of an improved understanding of the interactions between plant‐soil‐climate‐management systems and different types of inhibitors should continue to optimize the effectiveness of inhibitors for reducing environmental losses while increasing productivity.

show abstract

Section: Methodsmentioning

confidence: 99%

Global evaluation of inhibitor impacts on ammonia and nitrous oxide emissions from agricultural soils: A meta‐analysis

Fan

Smith

et al. 2022

Global Change Biology

View full text Add to dashboard Cite

show abstract

“…Moore (1986, p. 92) commented that “Among the chi-square statistics proposed and studied to date, the Rao–Robson statistic appears to have generally superior power and is therefore the statistic of choice for protection against general alternatives.” Also, the χ N 2 statistic has been found to outperform the Pearson’s χ 2 statistic in power comparisons (e.g., K. C. Rao & Robson, 1974; Voinov et al, 2009) and was more powerful than the Pearson’s χ 2 statistic in our study—therefore, results for the Pearson’s χ 2 statistic are not provided. Also, given the optimality properties of the χ N 2 statistic (e.g., Singh, 1987), the statistic is expected to be more powerful than the T j statistic (Ranger & Kuhn, 2014) which, like χ N 2 , is computed from the differences between observed and expected frequencies but, unlike χ N 2 , does not involve a division by the expected frequencies.…”

Section: Methodsmentioning

confidence: 72%

“…The Nikulin–Rao–Robson (NRR) test (Nikulin, 1973; K. C. Rao & Robson, 1974) statistic has also been found more powerful than tests of normality in detecting departures from normality (e.g., Voinov et al, 2009) and possesses several optimality properties (e.g., Singh, 1987; Voinov et al, 2013, p. 37). In the simulation study later in this article, the SW test, the AD test, and NRR test are used to test for item fit.…”

Section: Reviews Of the Lognormal Model Fit Statistics And Normalitmentioning

confidence: 99%

Assessing Fit of the Lognormal Model for Response Times

Sinharay

Rijn

2020

Journal of Educational and Behavioral Statistics

View full text Add to dashboard Cite

Response time models (RTMs) are of increasing interest in educational and psychological testing. This article focuses on the lognormal model for response times, which is one of the most popular RTMs. Several existing statistics for testing normality and the fit of factor analysis models are repurposed for testing the fit of the lognormal model. A simulation study and two real data examples demonstrate the usefulness of the statistics. The Shapiro–Wilk test of normality and a z-test for factor analysis models were the most powerful in assessing the misfit of the lognormal model.

show abstract

“…, p m } in Equation ( 9) with the traditional chi-squared test, we choose the equiprobable cells for computing the traditional chi-squared test. The chi-square statistic with equiprobable cells was recommended by Voinov et al [16]. For a selected number of representative points m, define the interval endpoints:…”

Section: A Monte Carlo Study and An Illustrative Examplementioning

confidence: 99%

Testing Multivariate Normality Based on Beta-Representative Points

Cao,

Liang,

et al. 2024

Mathematics

View full text Add to dashboard Cite

Testing multivariate normality in high-dimensional data analysis has been a long-lasting topic in the area of goodness of fit. Numerous methods for this purpose can be found in the literature. Reviews on different methods given by influential researchers show that new methods keep emerging in the literature from different perspectives. The theory of statistical representative points provides a new perspective to construct tests for multivariate normality. To avoid the difficulty and huge computational load in finding the statistical representative points from a high-dimensional probability distribution, we develop an approach to constructing a test for high-dimensional normal distribution based on the representative points of the simple univariate beta distribution. The representative-points-based approach is extended to the the case that the sample size may be smaller than the dimension. A Monte Carlo study shows that the new test is able to control type I error rates fairly well for both large and small sample sizes when faced with a high dimension. The power of the new test against some non-normal distributions is generally or substantially improved for a set of selected alternative distributions. A real-data example is given for a simple application illustration.

show abstract

A Comparative Study of Some Modified Chi-Squared Tests

Cited by 22 publications

References 18 publications

Global evaluation of inhibitor impacts on ammonia and nitrous oxide emissions from agricultural soils: A meta‐analysis

Global evaluation of inhibitor impacts on ammonia and nitrous oxide emissions from agricultural soils: A meta‐analysis

Assessing Fit of the Lognormal Model for Response Times

Testing Multivariate Normality Based on Beta-Representative Points

Contact Info

Product

Resources

About