Nonresponse Bias in a Dual Frame Sample of Cell and Landline Numbers

We conducted a dual frame survey of landline and cell phonenumbers in 2004 to evaluate the feasibility of including cellphone numbers in random digit dial telephone surveys in theUnited States. By sampling cell phone numbers, the coveragebias associated with households that have only cell phones iseliminated. However, we discovered two major sources of nonresponsebias in the dual frame sample. In an attempt to reduce thesebiases, we applied several different estimation schemes. Buta comparison to the 2004 Current Population Survey Cell PhoneSupplement showed that none of the estimation schemes substantiallyreduced the nonresponse bias of the estimates. We suggest othermethods that might be used in future surveys that include cellphones and discuss the need for additional data collection andresearch on this issue.     

Some generalizations of p1: External constraints,interactions and non-binary relations

In 1977, Holland and Leinhardt introduced a new statistical approach to sociometric data analysis. The details of their approach, based on a model termed P₁, were published in 1981 in papers by Holland and Leinhardt, and Fienberg and Wasserman. Since then, many researchers have adopted this model, addressing substantive questions that were unanswerable with existing methodology. The continuing methodological research of Fienberg and Wasserman has allowed this approach to be applied to many different types of sociometric data. We carry on this research by extending p₁ to three new situations: networks of such size that it is impossible for every actor to have contact or knowledge of the other actors; networks in which actor interaction can not be adequately modeled by the simple additive main effects of expansiveness and popularity; and networks in which we measure the strength of the relationship between actors using a non-binary or multivalued relational quantity.     

On The Quantitative Definition of Risk

A quantitative definition of risk is suggested in terms of the idea of a "set of triplets". The definition is extended to include uncertainty and completeness, and the use of Bayes' theorem is described in this connection. The definition is used to discuss the notions of "relative risk", "relativity of risk", and "acceptability of risk".     

Longitudinal analysis of friendship networks

This note discusses and demonstrates methods, both exploratory and confirmatory, for analysing data from friendship networks collected over time. The focus is on stochastic models for dyadic interaction designed to quantify the structural effect of reciprocity on arc changes. The networks studied were previously analysed by Hallinan (Social Networks 1: 193–210) who was concerned with stability of dyadic choices and the direction of change of asymmetric dyads to either mutual or null dyads. These aspects of the networks are really of secondary importance to the effect of reciprocated choices on the probabilities of dyadic change. Measures of this ‘reciprocity effect’ are presented, and comments on the rationale for continuous-time Markov chains as models for networks are given.     

Cross-cultural influences on organizational learning in MNCS: The case of Japanese companies in China

This paper draws on the social construction perspective and on social learning theory to examine the cross-cultural influences on organizational learning in MNCs. Social learning theory suggests that constructive engagement and member solidarity are key constituents of organization-based collective learning. Literature suggests, however, that cross-cultural differences in assumptions about social participation by organization members may impair organizational learning. The paper also reports a qualitative study, conducted at five Japanese-invested manufacturing companies in the Pearl River Delta, China. The research found that managers perceived Chinese frontline workers as lacking constructive engagement and member solidarity as compared with their Japanese counterparts, thus limiting organizational learning, and attributed these perceived differences to deep-seated cultural values. Attempts in two of the companies to ‘Japanize’ the workforces were reported to have had some impact, but appeared not to have substantially changed this picture. Urging caution regarding cross-cultural stereotyping and home country bias, we consider the implications for organizations with international manufacturing operations.     

Efficient algorithms for finding a longest common increasing subsequence

We study the problem of finding a longest common increasing subsequence (LCIS) of multiple sequences of numbers. The LCIS problem is a fundamental issue in various application areas, including the whole genome alignment. In this paper we give an efficient algorithm to find the LCIS of two sequences in time where n is the length of each sequence andr is the number of ordered pairs of positions at which the two sequences match, ℓ is the length of the LCIS, and Sort(n) is the time to sort n numbers. For m sequences wherem ≥ 3, we find the LCIS in Sort(n)) time where r is the total number of m-tuples of positions at which the m sequences match. The previous results find the LCIS of two sequences in O(n ²) and Sort(n)) time. Our algorithm is faster when r is relatively small, e.g., for .