Image reconstruction by adaptive bayesian classification with a locally proportional prior

This paper concerns the problem of reconstructing images from noisy data by means of Bayesian classification methods. In Klein and Press, 1992, the authors presented a method for reconstructing images called Adaptive Bayesian Classification (ABC). The ABC procedure was shown to preform very well in simulation experiments. The ABC procedure was multistaged; moreover, it involved selecting a prior at Stage n that was the posterior at Stage n - 1. In this paper the authors show that we can improve upon ABC for some problems by modifying the way we take the prior at each stage. The new proposal is to take the prior for the pixel label at each stage as proportional to the number of pixels with that label in a small neighborhood of the pixel. The ABC procedure with a locally proportional prior (ABC/LPP) tends to improve upon the ABC procedure for some problems because the prior in the iterative portion of ABC/LPP is contextual, while that in ABC in non- contextual.     

On the explosion rate of maximum-bias functions

The maxbias function B_T() contains much information about the robustness properties of the estimate T. This function satisfies B_T(0)=0 and B_T()<for all 0<<whereis the breakdown point of T. Hampel (1974)pioneered the study of the limiting behaviour of B_T(?) where ? → 0. He computed and optimized the rate γ at which B_T(?) approaches 0 when ? → 0. This rate is now called the contamination sensitivity of T, and constitutes one of the cornerstones of the theory of robustness. We show that much can also be learned from the study of the limiting behaviour of B_T(?) when ? → ?*. A new robustness measure, called the relative explosion rate, can be obtained by studying the limiting relative maxbias behaviour of two extimates when approaches their common breakdown point ?*. Like the contamination sensitivity, the relative explosion rate can be readily derived from the estimate's score function. General formulae are given for M-estimates of scale and S-, MM- and τ-estimates of regression. We also show that the maxbias behaviour for large ? is largely determined by the curvature of the estimate's score function near zero. This motivates our definition and study of the local order of a score function.     

Community College Programs for the Human Services

A national survey of 2-year human services programs in community colleges revealed the current status of these programs and identified significant trends in areas such as program number, curriculum design, standard-setting mechanisms, student composition and career paths, and faculty affiliation. Of particular interest was the relationship of these programs and their graduates to social work education and the social services job market. Among the principal findings were (a) these programs are in a period of renewed growth and (b) a need and an opportunity exist for the social work profession, particularly social work education, to be constructively involved in this level of education.     

Demographic Transitions and Changes in the Living Arrangements of Children: The Netherlands 1850–2010

The transformation of Europe’s demographic regime over the past two centuries has led to considerable changes in the living arrangements of children. We study long-term changes, making use of three datasets covering the living arrangements of children born between 1850 and 1993 in the Netherlands: a historical national sample of children born between 1850 and 1922, a retrospective survey covering children born between 1923 and 1985, and data from the national population registry relating to children born between 1986 and 1993. We describe the changes in terms of whether fathers, mothers, and stepparents lived with these children at birth and at age 15. We observe a massive increase in the percentage of children growing up in a complete family between the 1850–1879 cohort and the mid-twentieth century cohorts and a return to nineteenth-century conditions in the most recent birth cohort. Time spent in a complete family increased continuously from the mid-nineteenth century on, to decrease again from the 1960s on.     

Some statistical issues in weather experimentation

A number of topics of statistical methodology in weather modification are discussed. The time sequence of unit definition, classification and randomization is shown to affect the types of units that can be used validly, and this casts doubt on the value of blocking. Re-randomization (permutation) tests are recommended as the only reliable method of confirmatory inference for weather experiments. Some aspects of such tests are examined, including a procedure for multiple comparisons. The plague of multiplicity of tests is discussed and warned against. Doubts about cumulative evaluations of "all" experiment's are expressed. A case is argued for examination of some non-randomized seeding operations. Consid¬ering the dearth of randomized data, it is argued that careful evaluation of seeding operations should be undertaken.     

Lot Splitting in Unbalanced Production Systems*

This research investigates the impact of lot splitting in unbalanced production systems, under a variety of experimental conditions. Scheduling policies specifically designed for use in the presence of a long-term bottleneck, a condition frequently encountered in practice, are developed and tested. Results indicate that when steps are taken at nonbottleneck work centers to capitalize on capacity imbalances through increasing the number of setups and, hence, the variety of products produced, shop effectiveness is improved. The results also indicate that scheduling policies that tend to increase the size of the average process batch retard the overlapping of operations, which is critical to the success of the lot-splitting methodology in reducing flow time. Finally, it is shown that increasing capacity at nonbottleneck work centers along with implementation of effectiveness-oriented scheduling polices leads to improved shop performance.     

An Evaluation of Flexible Workday Policies in Job Shops*

Job shops have long faced pressures for improvement in a challenging and volatile environment. Today's trends of global competition and shortening of product life cycles suggest that both the challenges and the intensity of market volatility will only increase. Consequently, the study of tactics for maximizing the flexibility and responsiveness of a job shop is important. Indeed, there is a significant body of literature that has produced guidelines on when and how to deploy tactics such as alternate routings for jobs and transfers of cross‐trained workers between machines. In this paper we consider a different tactic by adjusting the length of workdays. Hours in excess of a 40‐hour week are exchanged for compensatory time off at time and a half, and the total amount of accrued compensatory time is limited to no more than 160 hours in accordance with pending legislation. We propose several simple flexible workday policies that are based on an input/output control approach and investigate their performance in a simulated job shop. We find significant gains in performance over a fixed schedule of eight hours per day. Our results also provide insights into the selection of policy parameters.