Suchergebnisse

ABSTRACTArtificial neural networks are new methods for classification. We investigate two important issues in building neural network models; network architecture and size of training samples. Experiments were designed and carried out on two‐group classification problems to find answers to these model building questions. The first experiment deals with selection of architecture and sample size for different classification problems. Results show that choice of architecture and choice of sample size depend on the objective: to maximize the classification rate of training samples, or to maximize the generalizability of neural networks. The second experiment compares neural network models with classical models such as linear discriminant analysis and quadratic discriminant analysis, and nonparametric methods such as k‐nearest‐neighbor and linear programming. Results show that neural networks are comparable to, if not better than, these other methods in terms of classification rates in the training samples but not in the test samples.

PurposeThe paper examines the cultural differences in consumers' evaluations of vertical brand extensions.Design/methodology/approachA 2 (extension types: upward, downward) × 2 (nationality: USA, China) × 2 (ownership: owner, non-owner) between-subjects design with thinking styles as a covariate was employed to test consumers' evaluations of vertical brand extensions. A total of 228 subjects from the US and 194 from China participated in the two experimental studies.FindingsThe paper finds that consumers prefer downward extensions to upward extensions. Furthermore, Chinese consumers have even more favorable evaluations of downward extension products than do American consumers. In addition, analytic thinkers exhibit a stronger ownership effect than holistic thinkers.Originality/valueThe research contributes to the understanding of culture differences in vertical brand extension evaluations.

The effectiveness of the joint estimation (JE) outlier detection method as a process control technique for short autocorrelated time series is investigated and compared with exponentially weighted moving average (EWMA). The research goal is to determine the effectiveness of the method for detecting out‐of‐control observations when they are the last observation in a short autocorrelated time series. This is an important problem because detecting an outlier in the period when it occurs, rather than several periods after it occurs, will preclude the production of more defective units. Two cases are investigated: short simulated time series when normality is assumed, and short real time series when the assumption is violated. The results show that JE is effective for short time series, particularly for autoregressive series when normality is violated. Joint estimation is also effective for moving average series under the normality assumption and less effective when the assumption is violated. In all cases, JE is found to be more effective than EWMA.

Examines the success factors critical to the adoption and implementation of advanced manufacturing technology. Empirically tests the hypothesis that the management variables most associated with the human factor in automation projects alone can differentiate firms who are successful in adopting the technologies from those who are not so successful. Analyzes the differences between the two groups of firms across 27 management variables and six demographic variables.

The identification and location of materials losses in nuclear facilities is an important issue. Many complexities arise in monitoring such losses. These complexities include the dependency among materials balance observations and the influence of errors (outliers) on parameter estimates of various monitoring methods. The proposed Joint Estimation procedure is superior to standard methods (control chart and CUSUM) and to methods that build in correlation (ARMA control chart, ARMA CUSUM, and the Generalized M procedure) in the detection of nuclear materials losses. The Joint Estimation procedure is robust to the influence of outliers, is flexible in accommodating a range of dependencies among observations, and provides information on the type of loss. Further, the procedure is reliable in that it yields a probability of false alarms and a probability of detecting losses closer to specifications.

ABSTRACTEconometric methods used in foreign exchange rate forecasting have produced inferior out‐of‐sample results compared to a random walk model. Applications of neural networks have shown mixed findings. In this paper, we investigate the potentials of neural network models by employing two cross‐validation schemes. The effects of different in‐sample time periods and sample sizes are examined. Out‐of‐sample performance evaluated with four criteria across three forecasting horizons shows that neural networks are a more robust forecasting method than the random walk model. Moreover, neural network predictions are quite accurate even when the sample size is relatively small.