Pre-checking for non-monotonicity of the Wald statistic

The non-monotonic behaviour of the Wald test in some finite-sample applications leads to low power when the null hypothesis needs rejection most. This article proposes a simple check for discerning if the Wald statistic for testing significance of regression coefficients is non-monotonic in the neighbourhood of the parameter space from which the sample data are drawn. Monte Carlo simulations show that this method works rather well for detecting situations where the Wald test can be safely applied. An example is provided to illustrate the use of this check.     

Computation of the estimated parameters and wald statistic for the generalized growth curve model

Multivariate analysis is difficult when there are missing observations in the response vectors. Kleinbaum (1973) proposed a Wald statistic useful in the analysis of incomplete multivariate data. SUBROUTINE C0EF calculates the estimated parameter matrix g in the generalization of the Potthoff-Roy (1964) growth curve model proposed by Kleinbaum (1973). SUBROUTINE WALD calculates the Wald statistic for hypotheses of the form Hn: H 5 D = 0 as proposed by Kleinbaum (1973).     

Computing Wald criteria for nested hypotheses

We present a numerically convenient procedure for computing Wald criteria for nested hypotheses. Similar to Szroeter’s (1983) generalized Wald test, the suggested procedure does not require explicit derivation of the restrictions implied by the null hypothesis and hence its use might eliminate an intricate step in testing linear and nonlinear hypotheses. We show that the traditional Wald test, Szroeter’s (1983) generalized Wald test and our procedure are asymptotically equivalent under H₀. A class of nonlinear transformations of the restrictions for which the Wald statistic is asymptotically invariant is discussed. Finally, we illustrate the use of our procedure for testing the common factor restrictions in a dynamic regression model.     

Moments of the quartic assignment statistic with an application to multiple regression

We present the first three exact moments of the symmetric quartic assignment statistic. Efficient computational formulas have been derived to overcome severe difficulties in third moment calculations. Two examples illustrate applications of the quartic assignment statistic: evaluation of significant “clustering” or “mixing”; and distribution-free tests for equality of several planar regression models. This article extends previous results on the cubic assignment statistic in Iyer and Vecchia (1989).     

Modified Wald statistics for generalized linear models

Summary: Wald statistics in generalized linear models are asymptotically ² distributed. The asymptotic chi–squared law of the corresponding quadratic form shows disadvantages with respect to the approximation of the finite–sample distribution. It is shown by means of a comprehensive simulation study that improvements can be achieved by applying simple finite–sample size approximations to the distribution of the quadratic form in generalized linear models. These approximations are based on a ² distribution with an estimated degree of freedom that generalizes an approach by Patnaik and Pearson. Simulation studies confirm that nominal level is maintained with higher accuracy compared to the Wald statistics.     

Sensitivity of Rao's score test,the Wald test and the likelihood ratio test to nuisance parameters

The purpose of this paper is to compare the sensitivity of the likelihood ratio test, Rao's score test, and the Wald test to the change of the nuisance parameters. The main result is that, with an error of magnitude O(n⁻¹), the null distributions and the local alternative distributions of these tests are equally sensitive to nuisance parameter. We will also give accurate factorizations of these test statistics as quadratic forms, which are themselves useful for asymptotic analyses.     

Small-Sample Properties of GMM-Based Wald Tests

This article assesses the small-sample properties of generalized-method-of-moments-based Wald statistics by using (a) a vector white-noise process and (b) an equilibrium business-cycle model as the data-generating mechanisms. In many cases, the small-sample size of the Wald tests exceeds its asymptotic size and increases sharply with the number of hypotheses being jointly tested. We argue that this is mostly due to difficulty in estimating the spectral-density matrix of the residuals. Estimators of this matrix that impose restrictions implied by the model or the null hypothesis substantially improve the properties of the Wald statistics.     

On the usability of the fluctuation test statistic to identify multiple cointegration break points

The fluctuation test suggested by Hansen and Johansen [Some tests for parameter constancy in cointegrated VAR models, Econometrics J. 2 (1999), pp. 306–333] intends to distinguish between the presence of zero and one break in cointegration relations. In this article, we provide evidence by Monte Carlo simulations that it also serves as a graphical device to detect even multiple break locations. It suffices to consider a simplified and easy-to-implement version of the original fluctuation test. Its break detection performance depends on the sign of change in cointegration parameters and the break height. The sign issue can be approached successfully by a backward application of the test statistic. If breaks are observable, the break locations are detected at the true location on average. We apply the graphical procedure to assess the cointegration of bond yields of Spain, Italy and Portugal with German yields for the period 1995–2013 which is surprisingly supported by the trace test. However, the recursive cointegration approach shows that a stable relationship with German yields is only present for sub-periods between the introduction of the Euro and the global financial crisis which is in line with expectations. The statistical robustness of these results is supported by a forward and backward application of the cointegration breakdown test by Andrews and Kim [Tests for cointegration breakdown over a short time period, J. Bus. Econom. Stat. 24 (2006), pp. 379–394].     

Designing a control chart of extended EWMA statistic based on multiple dependent state sampling

In this paper, we presented a memory type control chart (CC) based on multiple dependent state (MDS) sampling to pinpoint the slight variation in the process mean for the quality trait of normal distribution (ND). Two pairs of control limits denominated as internal and external control limits are derived using under control mean and variance. The essential steps are taken to get the value of average run length (ARL) for stable and disturb process. Various tables of ARLs are erected using different smoothing constants, shifts and MDS parameter. Comparisons are established to assess the effectiveness of initiated CC with the various existing CC in term of ARL. It has been ascertained that offered CC manifest the best performance in searching out the diminutive changes in the process mean. Two examples, one is based on simulation study and other is related to real-life data, have been discussed for its practical purpose.KEYWORDS: Multiple dependent state, normal distribution, smoothing constants, control chart     

Partitioning Anderson's statistic for tied data

Anderson (Biometrics 15 (1959) 582) proposed a χ²-type statistic for the nonparametric analysis of a randomized blocks design with no ties in the data. In this paper, we propose an Anderson statistic that allows for ties in the data. We show that the asymptotic distribution of the statistic under the null hypothesis of no treatment effect is a χ² distribution. Under weak assumptions on the tie structure it is shown that the degrees of freedom for the asymptotic distribution is unchanged compared to the untied case. An extended analysis based on a partition of the statistic into independent components is suggested. The first component is shown to equal the Friedman rank statistic corrected for ties. The subsequent components allow for the detection of dispersion effects, higher order effects and differences in distribution. A simulation study is given and the new analysis is applied to a sensory evaluation data set.     

Pena's statistic for the Liu regression

In fitting regression model, one or more observations may have substantial effects on estimators. These unusual observations are precisely detected by a new diagnostic measure, Pena's statistic. In this article, we introduce a type of Pena's statistic for each point in Liu regression. Using the forecast change property, we simplify the Pena's statistic in a numerical sense. It is found that the simplified Pena's statistic behaves quite well as far as detection of influential observations is concerned. We express Pena's statistic in terms of the Liu leverages and residuals. The normality of this statistic is also discussed and it is demonstrated that it can identify a subset of high Liu leverage outliers. For numerical evaluation, simulated studies are given and a real data set has been analysed for illustration.     

A test statistic for weighted runs

A new test statistic based on runs of weighted deviations is introduced. Its use for observations sampled from independent normal distributions is worked out in detail. It supplements the classic χ² test which ignores the ordering of observations and provides additional sensitivity to local deviations from expectations. The exact distribution of the statistic in the non-parametric case is derived and an algorithm to compute p-values is presented. The computational complexity of the algorithm is derived employing a novel identity for integer partitions.     

Optimization of design parameters for control charts with multiple assignable causes

Duncan's economic model of Shewhart's original x¯ chart has established its optimal and economic application for processes with the Markovian failure characteristic. As the sample statistics show some indications of process variations, the variable-sampling-interval (VSI) control charts perform more effectively than the fixed sampling interval (FSI) ones due to a higher frequency in the sampling rate. Regarding the economic design of control charts, most studies have been dedicated to the FSI scheme. In 1998, Bai & Lee considered the production process with a single assignable cause and proposed an economic VSI design for a general x¯ control chart. However, in real cases, there are multiple assignable causes in the production process. Therefore, concerning the operation characteristics of the real industry, this research develops an economic model for the VSI control chart with multiple assignable causes based on stochastic and statistics theory and determines the optimal design parameters of the chart. A numerical example is also provided to demonstrate the effectiveness of the proposed model and the result indicates that VSI performs more effectively than a FSI control chart.     

A modification of watson's statistic for goodness-of-fit

A modification of Watson's statistic is suggested for dealing with stochastically ordered alternatives in the goodness-of-fit setting.     

A modified Kolmogorov-Smirnov test for a rectangular distribution with unknown parameters: Computation of the distribution of the test statistic

A recursive scheme for the calculation of the distribution of the test statistic of a modified Kolmogorov-Smirnov-test for a rectangular distribution with unknown parameters is given.