Likelihood-based cross-validation score for selecting the smoothing parameter in maximum penalized likelihood estimation

Maximum penalized likelihood estimation is applied in non(semi)-para-metric regression problems, and enables us exploratory identification and diagnostics of nonlinear regression relationships. The smoothing parameter A controls trade-off between the smoothness and the goodness-of-fit of a function. The method of cross-validation is used for selecting A, but the generalized cross-validation, which is based on the squared error criterion, shows bad be¬havior in non-normal distribution and can not often select reasonable A. The purpose of this study is to propose a method which gives more suitable A and to evaluate the performance of it.

A method of simple calculation for the delete-one estimates in the likeli¬hood-based cross-validation (LCV) score is described. A score of similar form to the Akaike information criterion (AIC) is also derived. The proposed scores are compared with the ones of standard procedures by using data sets in liter¬atures. Simulations are performed to compare the patterns of selecting A and overall goodness-of-fit and to evaluate the effects of some factors. The LCV-scores by the simple calculation provide good approximation to the exact one if λ is not extremeiy smaii Furthermore the LCV scores by the simple size it possible to select X adaptively They have the effect, of reducing the bias of estimates and provide better performance in the sense of overall goodness-of fit. These scores are useful especially in the case of small sample size and in the case of binary logistic regression.     

Testing Equality of Mean Vectors in Two Sample Problem with Missing Data

Finding the influence of traffic accident on the road is helpful to analyze the characteristics of traffic flow, and take reasonable and effective control measures. Here, the detrended fluctuation analysis method is applied to investigate the complexity of time series in mixed traffic flow with a blockage induced by an accident. As a parameter to depict the long-term evolutionary behavior of the time series in traffic flow, the scaling exponent is analyzed. According to the scaling exponent, it is shown that the traffic flow time series can display long-range correlation characteristics, short-range correlation characteristics, and non-power-law relation in the long-range correlation characteristics, which is strongly dependent on the entering probability of vehicle, the ratio of slow vehicle and the blockage duration time.     

Statistical Analysis of Marginal Count Failure Data

Manufacturers want to assess the quality andreliability of their products. Specifically, they want to knowthe exact number of failures from the sales transacted duringa particular month. Information available today is sometimesincomplete as many companies analyze their failure data simplycomparing sales for a total month from a particular departmentwith the total number of claims registered for that given month.This information—called marginal count data—is, thus,incomplete as it does not give the exact number of failures ofthe specific products that were sold in a particular month. Inthis paper we discuss nonparametric estimation of the mean numbersof failures for repairable products and the failure probabilitiesfor nonrepairable products. We present a nonhomogeneous Poissonprocess model for repairable products and a multinomial modeland its Poisson approximation for nonrepairable products. A numericalexample is given and a simulation is carried out to evaluatethe proposed methods of estimating failure probabilities undera number of possible situations.     

An extended formulation of Arrow's theorem for k-social welfare functions

Past studies in social choice theory are generally based on the assumption that any two alternatives must be incompatible. We are concerned with the concept, k-social choice based on the assumption that just k alternatives out of p (1kp–1) are compatible. The purpose of this paper is to show an extended formulation of Arrow's theorem for k-social welfare functions.     

What motivates single women to save? the case of Japan

Using Japanese panel data, we analyze precautionary savings due to staying single in the presence of income uncertainty. Our panel analysis finds that compared with young women who are likely to get married within 3 years, those who are not plan to have 44 percent more savings for precautionary purposes, and 108 percent more for retirement. These results suggest that in facing higher risk of income fluctuation due to choosing to marry late or remain unmarried, young women intend to have more wealth to mitigate the income risk inherent in single life.     

Bias‐reduced marginal Akaike information criteria based on a Monte Carlo method for linear mixed‐effects models

In linear mixed‐effects (LME) models, if a fitted model has more random‐effect terms than the true model, a regularity condition required in the asymptotic theory may not hold. In such cases, the marginal Akaike information criterion (AIC) is positively biased for (?2) times the expected log‐likelihood. The asymptotic bias of the maximum log‐likelihood as an estimator of the expected log‐likelihood is evaluated for LME models with balanced design in the context of parameter‐constrained models. Moreover, bias‐reduced marginal AICs for LME models based on a Monte Carlo method are proposed. The performance of the proposed criteria is compared with existing criteria by using example data and by a simulation study. It was found that the bias of the proposed criteria was smaller than that of the existing marginal AIC when a larger model was fitted and that the probability of choosing a smaller model incorrectly was decreased.     

Enhanced Experience of Emotional Arousal in Response to Dynamic Facial Expressions

In this study, we investigated the emotional effect of dynamic presentation of facial expressions. Dynamic and static facial expressions of negative and positive emotions were presented using computer-morphing (Experiment 1) and videos of natural changes (Experiment 2), as well as other dynamic and static mosaic images. Participants rated the valence and arousal of their emotional response to the stimuli. The participants consistently reported higher arousal responses to dynamic than to static presentation of facial expressions and mosaic images for both valences. Dynamic presentation had no effect on the valence ratings. These results suggest that dynamic presentation of emotional facial expressions enhances the overall emotional experience without a corresponding qualitative change in the experience, although this effect is not specific to facial images.

A Study on Technical and Cultural Differences in Survey Methodology Between Japan and the United States

Abstract: At present, Japanese researchers conducting social surveys encounter several difficulties such as restricted access to official registers and a decrease in current response rates. These researchers may expect these difficulties to be solved by the survey techniques or methods developed outside Japan, such as computer-assisted interviews (CAI) and Internet surveys. It is unclear whether the numerous technical differences between survey methodologies developed in Japan and elsewhere imply the backward-ness of Japan or cultural differences. This paper discusses the potential of various recent survey methods, focusing on the culture and paradigms in Japan and the UnitedStates. First, this paper presents an overview of survey techniques, such as computer-assisted personal interviewing, Internet surveys, and mixed modes. Second, it points out the fact that the existence of the registers and different survey concepts might have created the different survey paradigms. In addition, reference is made to the linguisticdifferences between the US and Japan. The results indicate that survey research is more dispersed in Japan than in the US and that survey research adapted to the uniqueness of Japanese culture is not accumulated sufficiently, although such an accumulation is required. Finally, it is stated that not only surveys, but also the concept of methodology, is not very popular in Japan. Furthermore, the development of survey research in the US is likely to be related to pragmatism.     

Son preference in Japan

We examine the sex preference in Japan, using Japanese microdata, and find that parents in the 1920–1939 cohort have a lexicographic son preference. Further, the lexicographic son preference disappears in subsequent cohorts and a mixed preference is observed in parents with two children. These results are supported when the parents’ socioeconomic background is considered. Cohort effects such as weakening son preference and emerging mixed preference are observed. Moreover, when husbands are the eldest sons, a lexicographic son preference is observed only in the 1920–1939 cohort, although it persists in the subsequent cohorts when husbands are farmers/self-employed workers.     

Influences of the edge radius of curvature of tactile dots and bars on their Discriminability

Tactile dots and bars serve as tactile landmarks so that people with visual impairment can use same consumer products as those used by sighted people. However, reliable age-related data on the appropriate sizes and the shapes was not necessarily available. The purpose of this study is to evaluate influences of edge radius of curvature of tactile dots and bars on their discriminability in younger and older people to determine the appropriate size of tactile bars (as distinguished from tactile dots). Sighted younger and older participants tactually discriminated the tactile dots and bars presented individually, in random order, by a two-alternative forced-choice task. The results showed that both participants discriminated tactile bars from tactile dots faster and more accurately as the dimensional difference between bar length and width increased, regardless of conditions of edge radius of curvature. Therefore, longer dimensional difference between width and length of tactile bars is an important factor to discriminate tactile bars correctly. On the other hand, tactile dots with a larger edge radius of curvature have higher discriminability than tactile dots with a smaller edge radius of curvature in the case of dots of identical height.