Fully nonmetric estimation of a continuous nonlinear conjoint utility function

The special conjoint-analysis problem of estimating the parameters of a continuous nonlinear utility function from ordinal rank order data is investigated. A special purpose estimation method, called NONCON, is proposed that offers two advantages: First, it is capable of directly maximizing Kendall's rank order correlation coefficient T as the appropriate measure of goodness of fit. Second, it requires less computational effort than competing procedures using general purpose conjointanalysis programs. The superiority of NONCON is demonstrated for the estimation of a continuous nonlinear two-parameter utility function the parameters of which serve as input for the optimization of sales force compensation schemes.     

THE EFFECT OF ESTIMATION IN HIGH‐DIMENSIONAL PORTFOLIOS

We study the effect of estimated model parameters in investment strategies on expected log‐utility of terminal wealth. The market consists of a riskless bond and a potentially vast number of risky stocks modeled as geometric Brownian motions. The well‐known optimal Merton strategy depends on unknown parameters and thus cannot be used in practice. We consider the expected utility of several estimated strategies when the number of risky assets gets large. We suggest strategies which are less affected by estimation errors and demonstrate their performance in a real data example. Strategies in which the investment proportions satisfy an L₁ ‐constraint are less affected by estimation effects.     

Sequential choice designs to estimate the heterogeneity distribution of willingness-to-pay

Two prominent approaches exist nowadays for estimating the distribution of willingness-to-pay (WTP) based on choice experiments. One is to work in the usual preference space in which the random utility model is expressed in terms of partworths. These partworths or utility coefficients are estimated together with their distribution. The WTP and the corresponding heterogeneity distribution of WTP is derived from these results. The other approach reformulates the utility in terms of WTP (called WTP-space) and estimates the WTP and the heterogeneity distribution of WTP directly. Though often used, working in preference space has severe drawbacks as it often leads to WTP-distributions with long flat tails, infinite moments and therefore many extreme values. By moving to WTP-space, authors have tried to improve the estimation of WTP and its distribution from a modeling perspective. In this paper we will further improve the estimation of individual level WTP and corresponding heterogeneity distribution by designing the choice sets more efficiently. We will generate individual sequential choice designs in WTP space. The use of this sequential approach is motivated by findings of Yu et al. (2011) who show that this approach allows for superior estimation of the utility coefficients and their distribution. The key feature of this approach is that it uses Bayesian methods to generate individually optimized choice sets sequentially based on prior information of each individual which is further updated after each choice made. Based on a simulation study in which we compare the efficiency of this sequential design procedure with several non-sequential choice designs, we can conclude that the sequential approach improves the estimation results substantially.     

中国入境旅游的文化差异效应测度研究——基于引力模型的分析

一般而言,不同国家或地区的旅游资源带有明显的文化特征,将文化距离指数这一变量纳入到引力模型中,能够估计文化差异对中国入境旅游影响的综合效应和影响程度。基于16个国家和地区连续8年的面板数据的估计结果表明:文化差异的确对中国的入境旅游有较大的影响,其综合效果是消极的,各国的自发旅游消费也存在较大的差异;此外,绝对地理距离、人均收入水平和中国的经济发展能力对入境旅游也有不同程度的影响。因此,中国在发展入境旅游业的过程中,应当综合考虑文化因素与经济因素的相互关系,合理运用文化要素,对入境旅游的开发和营销等工作进行有效规划。     

Modelling pedestrian go-home decisions: A comparison of linear and nonlinear compensatory,and conjunctive non-compensatory specifications

This paper presents the main findings of an application of several models to predict the go-home decision of pedestrians in shopping streets. Two compensatory multinomial logit models, one with a linear utility function of time and the other with a nonlinear utility function of time, and a non-compensatory conjunctive model are specified. Data about pedestrian behaviour in a major shopping street in Beijing served as input for model estimation. The conjunctive model performs best, suggesting that pedestrians use simplifying heuristics to decide when to end the shopping trip and go home. In addition, the nonlinear multinomial logit model outperforms the linear model, indicating that marginal utility of time decreases with increasing time.     

Advances in random utility models report of the workshop on advances in random utility models duke invitational symposium on choice modeling behavior

In recent years, major advances have taken place in three areas of random utility modeling: (1) semiparametric estimation, (2) computational methods for multinomial probit models, and (3) computational methods for Bayesian estimation. This paper summarizes these developments and discusses their implications for practice.     

信道特性对OFDM信道估计中导频模式选择的影响

分别介绍了基于梳状导频和块状导频的OFDM信道估计的原理,重点研究了上述两种导频在不同的信道环境中的信道估计性能.仿真分析展示了两种导频模式对传输信道的不同参数的敏感程度,由此给出了在不同的传输信道条件下导频模式的选择依据.     

Characterisation and comparison of gender-specific utility functions of shopping duration episodes

This paper reports the results of an analysis of gender differences in the parameters of utility functions derived from activity duration data. The estimated utility functions allow a comparison of the marginal utility, inflection point and the (a)symmetry of the utility of activity duration. Some significant differences between men and women are found. The results of the analyses indicate that the utility that men and women derive from basic in-home leisure activities is more or less the same. Gender differences were found for out-of-home activities, including grocery and non-grocery shopping activities.     

Is self-knowledge the ultimate prize? A quantitative analysis of participation choice in online ideation crowdsourcing contests

Online crowdsourcing contests are a nascent but rapidly growing method among marketers and retailers to generate and solicit creative ideas. In two studies – a dynamic model with scraped data from a well-known crowdsourcing platform using Python (study 1) and a survey among real participants in online contests with conjoint analysis (study 2) – we explore how multiple design parameters influence participation in online contests. Our empirical results support the notion that both extrinsically (i.e., prize money) and intrinsically (i.e., feedback) motivating parameters can generate value for participants (i.e., expected utility). Comparatively, however, we find evidence that intrinsically motivating design parameters that provide self-relevant feedback (i.e., feedback from organizer) can be more impactful than extrinsically motivating design parameters (i.e., award size). We also show novel time-dependent effects: as a contest nears its end, important design parameters shift in their effects on participation rates— their role over time is non-monotonic. In particular, the effect of award size becomes non-significant, but feedback remains impactful. Our findings contribute to the crowdsourcing literature, especially regarding how self-knowledge (e.g., self-efficacy) affects utility and consumer co-creation through contest participation over time; the findings also can help retail managers and marketers enhance participation in idea contests.     

公允价值的内涵、本质、计量追求与运用关键

本文在探讨公允价值的产生背景的基础上,比较了不同时期各国或组织的公允价值定义,并重点对FAS157的最新定义进行了分析。本文认为广义的公允价值包括过去、现在和未来三个时间界区的计量属性,狭义的公允价值即未来现金流量现值。公允价值的计量追求是对经济收益的计量。根据效用价值理论公允价值的本质是一种效用价值,根据马克思主义劳动价值理论公允价值的本质是交换价值,两者都是一种价格的估计。会计信息相关性与可靠性的权衡是公允价值的运用关键。     

一种新的最小均方误差线性合并算法

针对未编码的多输入多输出系统,将基于训练序列的最小均方误差(MMSE)信道估计算法与最优线性无偏估计结构(BLUE)相结合对已估计的信道参数进行估计.仿真结果表明,使用线性合并的MMSE算法比传统的MMSE算法具有较小的参数估计误差,比使用线性合并的LS算法性能更好.     

采用数据辅助的大规模MIMO信道半盲迭代估计

由于大规模多输入多输出(Multiple-Input Multiple-Output,MIMO)信道衰落参数的维度较高,导致最优估计算法计算量大且需要的导频数较多而影响到频谱效率。为降低计算复杂度并减少导频开销,提出了两种基于期望最大化(Expectation Maximization,EM)估计的半盲迭代改进算法。利用少量正交导频序列估计出信道初值,通过用户与基站间信道的大尺度衰落系数把用户分簇,根据这些系数按比例地分配接收噪声,再利用数据的统计特性推导出信道衰落参数的均值和方差。仿真结果表明,当导频数远少于待估计参数的个数时,半盲估计算法的均方误差(Mean Square Error,MSE)优于导频估计的极大似然(Maximum likelihood,ML)算法。     

Estimating dynamic response models when the data are subject to different temporal aggregation

In estimating response models using secondary data, it can happen that the observations on the variables are subject to different temporal aggregation. Estimating a dynamic model with this type of data is not straightforward, particularly when (a) estimates with good statistical properties are desired, and (b) full use of all information in the data is needed. This paper provides an overview and discussion of the various approaches to the estimation problem when independent variables are observed less frequently than the dependent variable. The superiority of one-step estimation procedures that simultaneously estimate the parameters and the missing disaggregated data points is established.Insead     

基于平均循环周期图方法的Frank编码信号循环谱特征参数估计

针对Frank编码信号非合作条件下参数估计问题,提出了基于平均循环周期图的循环 谱特征参数估计算法。该算法利用信号参数与循环谱特征的联系,通过提取信号的循环谱特 征,实现对其关键参数的估计。分析了算法的计算量,给出了该算法的具体实现步骤,并通 过对信号参数归一化均方根估计误差的仿真计算,分析了噪声环境对参数估计的影响,表明 该算法对Frank编码信号循环谱特征参数估计的有效性。     

强干扰下跳频信号的参数估计

针对通信对抗中跳频信号参数估计问题,考虑存在强干扰的情况下,提出了一种基于时频重心的跳频信号跳周期估计和基于跳频部分接收的跳时估计方法。对于跳周期估计,在短时傅里叶变换（STFT）时频变换的基础上提取信号随时间变化的时频重心,再结合小波变换和谱分析估计出跳频周期;对于跳时估计,采用跳频带宽的部分接收避开强干扰,构造含有跳变信息的参考信号,通过参考信号采用最大似然(ML)方法得到跳时的精确估计。仿真实验表明,算法运算复杂度低,跳频定位精度高,在强定频干扰的情况下仍能有效估计出跳频周期和起跳时刻。     

基于模糊函数的直接序列扩频信号参数估计改进方法

分析了基于模糊函数的直接序列扩频信号参数估计方法,研究了该方法在低信噪比环 境下针对信号码元传输速率、码片周期等参数估计结果的有效性。在此基础上,提出了一种 利用ANFIS（自适应神经模糊推理系统）网络先行去噪,再进行信号参数估计的改进方法。 计算机仿真结果证明了这一改 进方法的有效性。     

A model of consumer information search and online network externalities

This article looks at a consumer who faces a choice between two sources of information: conventional and online. The online source is different from the conventional one because consumers care about how many people are using it along with them. Generally, the more users the better (positive network externality), but, on the other hand, the presence of more users implies a reduction of available capacity, about which consumers also care. We assume that consumers maximize their utility, which is modeled as a function of all other consumption, knowledge, and network externalities. Knowledge is conceptualized as a function of the amount of information spent both on the online network and on conventional sources. Since consumer information searches may differ according to demographic differences, this may result in consumers’ differences in their usage of online networks and conventional sources. We include these externalities in our model to better understand consumer choice behavior for the online network. The consumer utility function is estimated by using the model estimation method developed in this article, since the interactions implied by the consumer utility function are more complex than one could hope to estimate econometrically. We use survey data to regress the demand for online information depending on income, education, the number of users, and remaining capacity. We introduce a methodology to simulate how consumers’ representative utilities will behave in different network environments and derive implications for online network suppliers.     

几种自适应波束形成方法的对比

波束形成在无线通信、雷达、声呐等阵列系统中具有广泛应用。数字波束形成通常是基于接收信号的阵列响应和协方差矩阵的估计设计。由于天线增益、相位、波达方向(Direction-of-Arrival,DOA)和协方差矩阵估计的误差会导致导向矢量(Steering Vector,SV)产生模型失配,而这种模型失配会导致波束形成性能的下降。针对以上问题,给出了基于精度矩阵收缩估计的方法,采用了线性脊估计结构且用数据驱动和留一交叉验证来选择参数。通过Matlab仿真,研究了当存在模型不确定性时,基于精度矩阵收缩估计的方法以及基于协方差矩阵收缩估计和干扰加噪声协方差矩阵重构等方法的鲁棒性。结果显示,当存在模型失配时,基于精度矩阵收缩的波束形成方法在低信噪比时具有更优的鲁棒性。     

Studying the level-effect in conjoint analysis: An application of efficient experimental designs for hyper-parameter estimation

Research in marketing, and business in general, involves understanding when effect-sizes are expected to be large and when they are expected to be small. An example is the understanding of the level-effect in marketing, where the effect of product attributes on utility is positively related to the number of levels present among choice alternatives. Knowing when consumers are sensitive to the competing levels of attributes is an important aspect of merchandising, selling and promotion. In this paper, we propose a model and a method for studying the level-effect in conjoint analysis. The model combines perceptual theories in psychology to arrive at a non-linear specification of hyper-parameters in a hierarchical model. The method applies an experimental design criterion for efficient estimation of hyper-parameters. The proposed model and method are validated using a national sample of respondents.      

采用混合核支持向量机的DOA估计

人工神经网络（ANN）进行建模时通常需要准备大量的数据样本,同时网络结构一般都比较复杂;而采用支持向量机（SVM)进行建模时,不同核函数有不同的效果,各有利弊,且选取SVM模型参数的理论支撑尚不完整。为了解决这些问题,提出了一种基于混合核函数的支持向量机来改善来波到达角（DOA）的估计性能,并结合二进制粒子群算法（PSO）来对混合核函数进行参数寻优。该混合核函数由全局核函数和局部核函数构成,提高了SVM的泛化能力和学习能力。首先通过拟合多项式函数,验证了该混合核SVM的有效性。将该方法用于DOA估计建模,在不同信噪比和快拍数下,通过与径向基函数（RBF）神经网络、基于各单一核函数的SVM和MUSIC算法预测结果对比,混合核SVM均方差有所降低,提高了DOA估计的精度且有更好的稳定性。