A synthetic control chart for the coefficient of variation

The coefficient of variation (CV) control chart has recently been introduced in the literature. Here, the salient features of this chart and the conforming run length chart are integrated to produce a synthetic coefficient of variation (SynCV) chart. The run length profile of the SynCV chart is numerically compared with the originally proposed chart and the upward EWMA-γ² chart. The SynCV chart outperforms the original CV chart, while the EWMA-γ² outperforms the SynCV chart for small increases in the CV. However, for large increases in the CV, the SynCV chart outperforms the EWMA-γ² chart.     

Estimation of Mode Using Auxiliary Information

In this article, we propose naïve estimator, ratio estimator, and difference estimator of the mode of a study variable by using the known mode of an auxiliary variable. The asymptotic properties of the proposed estimators are studied analytically as well as empirically for different situations. The proper use of auxiliary information is found to result in efficient ratio and difference estimators than the naïve estimator.     

Use of weighted least squares regression jn simulation studies

When a simulation or Monte Carlo analysis uses the same set of N samples as input for the comparison of the power of tests, the resulting estimates of power are highly correlated. As a result, the statistical analysis of these results should use weighted least squares or other equivalent procedures. A reanalysis of one simulation study (Thode et al., 1983) found that the weighted least squares estimates had much smaller standard errors than the ordinary least squares estimates. The reduction in the standard errors of the parameters was a factor between 4 and 9 for the tests found to be more powerful. The necessary calculations are described.     

Univariate Bayesian nonparametric mixture modeling with unimodal kernels

Within the context of mixture modeling, the normal distribution is typically used as the components distribution. However, if a cluster is skewed or heavy tailed, then the normal distribution will be inefficient and many may be needed to model a single cluster. In this paper, we present an attempt to solve this problem. We define a cluster, in the absence of further information, to be a group of data which can be modeled by a unimodal density function. Hence, our intention is to use a family of univariate distribution functions, to replace the normal, for which the only constraint is unimodality. With this aim, we devise a new family of nonparametric unimodal distributions, which has large support over the space of univariate unimodal distributions. The difficult aspect of the Bayesian model is to construct a suitable MCMC algorithm to sample from the correct posterior distribution. The key will be the introduction of strategic latent variables and the use of the Product Space view of Reversible Jump methodology.     

Using large data sets to forecast sectoral employment

We use several models using classical and Bayesian methods to forecast employment for eight sectors of the US economy. In addition to using standard vector-autoregressive and Bayesian vector autoregressive models, we also augment these models to include the information content of 143 additional monthly series in some models. Several approaches exist for incorporating information from a large number of series. We consider two multivariate approaches—extracting common factors (principal components) and Bayesian shrinkage. After extracting the common factors, we use Bayesian factor-augmented vector autoregressive and vector error-correction models, as well as Bayesian shrinkage in a large-scale Bayesian vector autoregressive models. For an in-sample period of January 1972 to December 1989 and an out-of-sample period of January 1990 to March 2010, we compare the forecast performance of the alternative models. More specifically, we perform ex-post and ex-ante out-of-sample forecasts from January 1990 through March 2009 and from April 2009 through March 2010, respectively. We find that factor augmented models, especially error-correction versions, generally prove the best in out-of-sample forecast performance, implying that in addition to macroeconomic variables, incorporating long-run relationships along with short-run dynamics play an important role in forecasting employment. Forecast combination models, however, based on the simple average forecasts of the various models used, outperform the best performing individual models for six of the eight sectoral employment series.     

Putting the parity into service‐user participation: An integrated model of social justice

Models of service‐user participation have derived from citizenship or consumerist agendas, neither of which has achieved the structural reforms important for the most marginalised social work clients. This article proposes Fraser's model of ‘parity of participation’ as an appropriately multifaceted frame for capturing the social justice aspirations of service‐user participation. A qualitative case study compared the experiences and expectations of people who had used Australian mental health services with a sample who had used Australian homelessness services to examine their expectations of participation at individual and representative levels. The findings reinforce concerns from Fraser's research about the tendency for identity‐based consumerist notions of participation to reify group identity. This leads to tokenistic service‐user involvement strategies that have little impact on participation at a structural level. Fraser's parity of participation is shown to have untested potential to reshape service‐user participation to meet the social justice aspirations of social work clients. Key Practitioner Message: ● Innovative, service‐user driven strategies for collaboration will be those which challenge existing power structures; ● Service users want their contributions to decision making to generate identifiable change in the system of social services; ● The success of service‐user participation strategies might be the extent to which political, economic and cultural opportunities are enhanced.     

Using Critical Realism to Explain Indeterminacy in Role Behaviour Systematically

We demonstrate in this article how critical realism can be used to explain indeterminacy in role behaviour systematically. In so doing, we both rebut various criticisms of critical realism made recently by Kemp and Holmwood and attempt to illustrate the weaknesses and absences of approaches that concentrate unduly on the collection of expectations of (different groups of) actors concerning roles and the behaviour of incumbents. Within a framework that recognises that structure and agency are ontologically distinct but necessarily empirically related entities, we argue that structures should be seen as sources of indeterminacy within role behaviour for at least four reasons: the co‐determination of roles through the intersection of structures; conflicting role expectations caused by contradictions inhering within structures; asymmetries of power within social relations; and asymmetric repetition within structural reproduction/transformation. In light of this discussion of structural sources of indeterminacy, we then go on to demonstrate how critical realism is also able to analyse systematically the agential sources of indeterminacy within role behaviour and expectations through theories of psychobiography and reflexivity. We thus conclude that critical realism contains the conceptual tools required to illuminate the point(s) of intersection between structure, culture and agency which is central to understanding both role behaviour and the plurality of expectations concerning such behaviour.     

A Note on Whittle's Likelihood

The approximate likelihood function introduced by Whittle has been used to estimate the spectral density and certain parameters of a variety of time series models. In this note we attempt to empirically quantify the loss of efficiency of Whittle's method in nonstandard settings. A recently developed representation of some first-order non-Gaussian stationary autoregressive process allows a direct comparison of the true likelihood function with that of Whittle. The conclusion is that Whittle's likelihood can produce unreliable estimates in the non-Gaussian case, even for moderate sample sizes. Moreover, for small samples, and if the autocorrelation of the process is high, Whittle's approximation is not efficient even in the Gaussian case. While these facts are known to some extent, the present study sheds more light on the degree of efficiency loss incurred by using Whittle's likelihood, in both Gaussian and non-Gaussian cases.     

Posterior Sampling When the Normalizing Constant is Unknown

This article describes a means by which to undertake Bayesian posterior inference via sampling techniques when the normalizing constant is not computable and hence unavailable. The strategy relies on the introduction of latent variables which removes any integrals associated with the inaccessibility of the normalizing constant.