Optimum Quantization for Local Decision Based on Independent Samples

The problem of designing quantizers for use in decision-making systems is considered. Applying the theory of local tests, general criteria are derived for the optimal selection of quantizer parameters for the large-sample-size case. These criteria agree with previously established results based on optimization in terms of distance measures and are shown also to lead to that quantizer-decision system which is most efficient asymptotically. To illustrate the design procedure, several applications to signal detection are discussed.     

Travel Cost Analysis of a Cultural Heritage Site: The Case of Historic St. Mary's City of Maryland

Historic St. Mary's City located in rural southern Maryland, marks the 17th century British Colonial capital of the State of Maryland. As with most cultural heritage sites, Historic St. Mary's City can be classified as possessing public goods-type characteristics, and as such, welfare benefit estimates must utilize non-market valuation techniques. To date, the primary valuation methodology used for cultural heritage sites research involves stated preference methods. This study is one of the first to employ a revealed preference methodology, the zonal travel cost model, to estimate the consumer surplus welfare measures of a cultural heritage site. We analyze three years of visitor sample data to compare three functional forms of visitor demand. The average of the annual individual consumer surplus measures ranged from approximately $8.00 to $19.26, depending on the functional forms used. When aggregated to the total number of individual paid visitors, the average annual benefit estimates range from approximately $75,492 to $176,550.     

A Relative Efficiency study of Some Popular Detectors

The relative efficiency between two detectors is a measure of the amount of data one detector requires, relative to the other detector, to attain a prescribed level of performance. In this paper the behavior of the relative efficiencies of two pairs of popular detection systems is investigated, and it is shown that the commonly employed asymptotic value of the relative efficiency can sometimes be a poor indicator of finite-sample-size detection performance even for some very large sample sizes.     

On robust detection of discrete-time stochastic signals

The problem of designing robust systems for the detection of stochastic signals in noise is considered for the large-sample-size, small-signal case. By applying two previously-established models for the detection of stochastic signals, known results for the robust detection of deterministic signals are extended on a limited basis to the stochastic- signal case. The proposed detectors are seen to be robust over a class of possible noise statistics, based on a Huber-Tukey mixture model, which contains noises characterized by heavy-tailed probability density functions. In addition, numerical results are presented which verify the robustness property of the proposed detectors over wider classes of noise mixtures.     

A Cross-National Study of Computer News Sites: Global News,Local Sites

The Internet is not only an object of and a tool for study; it is also both simultaneously global and local. In order to address how global and how local it is, this study compares the news content of 1 week from four different computer news web sites in four different countries (using four different languages). These sites use the same code base and all strive to be the same in terms of computer culture. They are global in their reach and in the news they cover, yet they are all local in terms of language and geography. They are ideal locales to study how forces of the global and the local play out on the highly connected Internet, using Google language tools for translation. Findings were surprising in that they showed very little in terms of a pattern of any sort. This is similar to a 1953 UNESCO study of newspapers, but strange in that given the passing of 50 years and the connectedness of the Internet, greater overlap was expected. Link destinations for stories that were on more than one site were also examined, and the Japanese site had more in common with the American site while the two European sites were more alike in this lens. This is also surprising, given that an East/West split was expected. Little work in this specific area was found, and this study highlights some of the questions and methodological difficulties that need to be addressed.