Changing methodologies for research

Abstract

The methodology of the social sciences has developed in the 21st century to a sub-optimal state and in this way research programs for handling complex societal problems are frustrated. To manage this deadlock the author returns to the original aims of the social sciences. He shows that in the past, concepts and aims were developed that goes beyond this regression. Those original starting points are connected to modern ideas of advanced interdisciplinary research, such as practiced in action science, system dynamics and computer simulation. With this exploration a more advanced methodology for social change and organisational transformation is outlined.     

THE ANALYSIS OF DISCRETE CHOICE EXPERIMENTS WITH CORRELATED ERROR STRUCTURE

In a stated preference discrete choice experiment each subject is typically presented with several choice sets, and each choice set contains a number of alternatives. The alternatives are defined in terms of their name (brand) and their attributes at specified levels. The task for the subject is to choose from each choice set the alternative with highest utility for them. The multinomial is an appropriate distribution for the responses to each choice set since each subject chooses one alternative, and the multinomial logit is a common model. If the responses to the several choice sets are independent, the likelihood function is simply the product of multinomials. The most common and generally preferred method of estimating the parameters of the model is maximum likelihood (that is, selecting as estimates those values that maximize the likelihood function). If the assumption of within-subject independence to successive choice tasks is violated (it is almost surely violated), the likelihood function is incorrect and maximum likelihood estimation is inappropriate. The most serious errors involve the estimation of the variance-covariance matrix of the model parameter estimates, and the corresponding variances of market shares and changes in market shares.

In this paper we present an alternative method of estimation of the model parameter coefficients that incorporates a first-order within-subject covariance structure. The method involves the familiar log-odds transformation and application of the multivariate delta method. Estimation of the model coefficients after the transformation is a straightforward generalized least squares regression, and the corresponding improved estimate of the variance-covariance matrix is in closed form. Estimates of market share (and change in market share) follow from a second application of the multivariate delta method. The method and comparison with maximum likelihood estimation are illustrated with several simulated and actual data examples.

Advantages of the proposed method are: 1) it incorporates the within-subject covariance structure; 2) it is completely data driven; 3) it requires no additional model assumptions; 4) assuming asymptotic normality, it provides a simple procedure for computing confidence regions on market shares and changes in market shares; and 5) it produces results that are asymptotically equivalent to those produced by maximum likelihood when the data are independent.     

A bound connected with 26 factorial search designs of resolution 3.1

In this paper, we give a lower bound for the number of treatments required

for a plan to be a main effect plus one plan for 2^m (m = 6) factorial experiments, The lower bound problem is important in the event of generating new designs with similar properties or when one wants to study the criteria of optimality for such designs.     

Breaking alias chains in fractional factorials

Some experimenters carry out their investigation in stages. They begin with an initial 2^n-p fraction of resolution IV, in which the main effects are clean and the interactions are aliased in chains, Then, having analyzed the initial experiment, they plan further runs to isolate certain interactions by breaking the chains. In this paper a method called semifolding, for choosing the points in the second experiment, is presented.     

Canonical expansions,correlation structure,and conditional distributions of bivariate distributions generated by mixtures

A simple result concerning the canonical expansions of mixed bivariate distributions is considered. This result is then applied to analyze the correlation structures of the Bates-Neyman accident proneness model and its generalization, to derive probability inequalities based on the concept of positive dependence, and to construct a bivariate beta distribution with positive correlation coefficient applicable in computer simulation experiments. The mixture formulation of the conditional distribution of this class of mixed bivariate distributions is used to define and generate first-order autoregressive gamma and negative binomial sequences.     

引用电脑技术加强年鉴管理

利用计算机进行年鉴的编辑和管理是年鉴现代化管理的需要 ,同时对年鉴编辑工作者提出了更高的要求 ,不但要求年鉴编辑工作者要有现代化的管理意识 ,而且要掌握计算机的操作方法和技能 ,充分利用计算机的功能为年鉴的出版和现代化管理服务     

计算机绘图在求解线间距中的应用

针对线间距的求解问题，介绍了一种综合利用计算机技术及其绘图功能求得线间距的简捷方法．     

面向二十一世纪的计算机绘图教学

深入研究了计算机绘图教学 ,结合我院目前的教学实际情况及大纲中规定的教学基本要求 ,找出了教学中现存的实际问题。为适应新形势下计算机绘图的需要 ,对如何加强计算机绘图课提出了几点合理化建议 ,即适当增加授课时间与学生上机时间 ,尽量使教师参与计算机绘图的研究之中     

Higher order local unbiasedness with computer algebra

Unbiased estimation methods that are in some way local on the parameter space have been initiated by Barankin (1948) and Fraser (1964). The later methods involving local unbiasedness are extended to higher (derivative or difference) order at a parameter value (θ) and provide a basis for a computer algebra implementation concerning the improvement of unbiased estimates.     

Less Pain,More Gain

SUMMARY

Applied social statistics is typically one of the most dreaded courses in a social work program. Technological advances in computer applications offer tools to lessen the pain and increase the gains associated with teaching and learning statistics. This paper reports on a modest research project resulting in a computer-based approach to teaching Applied Social Statistics. This approach makes full use of MicroCase, a statistical software package. Results of evaluative efforts which appraised the computer technology-enhanced statistics course are presented. Course format, classroom procedures, workbook and homework assignments, evaluation tools, and teaching strategies are also suggested.