ALL-BIAS DESIGNS FOR POLYNOMIAL SPLINE REGRESSION MODELS

Polynomial spline regression models of low degree have proved useful in modeling responses from designed experiments in science and engineering when simple polynomial models are inadequate. Where there is uncertainty in the number and location of the knots, or breakpoints, of the spline, then designs that minimize the systematic errors resulting from model misspecification may be appropriate. This paper gives a method for constructing such all‐bias designs for a single variable spline when the distinct knots in the assumed and true models come from some specified set. A class of designs is defined in terms of the inter‐knot intervals and sufficient conditions are obtained for a design within this class to be all‐bias under linear, quadratic and cubic spline models. An example of the construction of all‐bias designs is given.     

Socioeconomic,sociodemographic and attitudinal correlates of the tempo of divorce

The association between sociodemographic, demographic, and attitudinal measures and the timing or tempo of marital dissolution over a 14-year time span is examined. Separation is considered equivalent to divorce. Early and late divorce are differentiated by whether the event occurred before or after the average number of years married prior to divorce. Data were obtained on husbands and wives within childbearing years (up to 39 years) in the 1st years of the 1st marriage. A random stratified sample of 610 couples was drawn from records of marriages in a midwestern county between 1972-77. Reinterviews were conducted on 544 couples in April 1985. socioeconomic variables included educational attainment, occupational prestige, wife's employment status, wife's future work plans, husband's attitude to wife's future work plans, total family income, and level of satisfaction with current financial status. Demographic variables are age at marriage, number of children in 1985, marital duration, and desired family size. Attitudinal items were religiosity and gender role orientations (traditionalism, modernism, egalitarianism). Exposure to divorce was not equitably distributed for the 108 who divorced, but this was not statistically significant. The results indicate that those divorced earlier were wives who worked outside the home, worked at more prestigious jobs, planned to be employed throughout married life, and whose father had a higher level of educational attainment. This finding is not consistent with prior research which has shown that favorable socioeconomic conditions lower the probability of divorce. The timing of divorce was affected by the presence of children. Those married at younger ages divorced earlier and couples with children delayed divorcing longer than couples without children. These findings were consistent with earlier research. Catholic wives delayed divorce longer than non-Catholic wives. Males lower in sexual satisfaction divorced earlier. Divorce was postponed longer for husbands with traditional values and wives who had higher scores on egalitarianism. Wives with scores on modernism had earlier divorces than wives scoring lower on modernism. The tempo of divorce was in multiple classification analysis predicted best by wife's employment status and number of children. Cross-classification was not possible.     

The birds and the bees: interactive graphics and problem solving in the teaching of statistics

Software which allows interactive exploration of graphical displays is widely available. In addition there now exist sophisticated authoring tools which allow more general textual and graphical material to be presented in computer-based form. The role of an authoring tool in providing a graphical interface to a strategy for solving simple statistical problems in the context of teaching is discussed. This interface allows a variety of resources to be integrated. Specific examples, including the use of dynamic graphical displays in exploring data and in communicating the meaning of a model, are proposed. These ideas are illustrated by a problem involving the identification of the sex of a herring gull.     

How the Resource-based and the Dynamic Capability Views of the Firm Inform Corporate-level Strategy

This paper explains that the resource‐based view essentially addresses issues of competitive strategy, but by integrating some arguments from its evolutionary version, the dynamic capability view, it can be extended to inform our understanding of corporate‐level strategy. We concentrate on the issue of value creation from corporate centres and ask how the centre can possess or provide resources. The primary dynamic capabilities identified by Teece, Pisano and Shuen (1997) are elaborated into six distinct modes of resource creation. Each mode is considered in relation to a set of organizational design parameters. We then propose resource‐creating configurations that are congruent with respect to the modes and the required states of the design parameters. We point out areas of tension that are likely to arise if corporations try to combine different modes of resource creation. We conclude that corporate centres may possess resources but must display dynamic capabilities otherwise they will destroy shareholder value.     

Sums of powers of binomial coefficients

An asymptotic series for sums of powers of binomial coefficients is derived, the general term being defined and usable with a computer symbolic language. Sums of squares of coefficients in the symmetric case are shown to have a link with classical moment problems, but this property breaks down for cubes and higher powers. Problems of remainders for the asymptotic series are mentioned. Using the reflection formula for I'(.), a continuous form for a binomial function is set up, and this becomes oscillatory outstde the usual range. A new contmued fraction emerges for the logarithm of an adjusted sum of binomial squares. The note is a contribution to the problem of the interpretation of asymptotic series and processes for their convergence acceleration.     

Approaches to the Fertility Transition in Victorian England

The secular decline of marital fertility which took place in late nineteenth and early twentieth-century England and Wales is considered by using a number of approaches. Among the theoretical approaches considered are those of transition models, and social diffusion. The former overemphasises the role of industrialization and urbanization; the latter is inappropriate when dealing with the development of a small-family ideal in Victorian society. Explanations of fertility decline using ecological and time-series analysis are considered. The registration districts of England and Wales provide the framework for analyses of spatial variations in marital fertility and its correlates in 1861, 1891 and 1911. A time-series analysis attempts to establish the sequential nature of social, economic and demographic changes during the sixty years preceding the First World War. The following points are emphasised in conclusion. The Victorian fertility transition was not directly related to the development of an urban-industrial society, the social diffusion of family ideals or the use of appliance methods of contraception. But its immediate cause was probably linked to the substantial increase in family planning literature available from the 1870s, and the challenge that this posed to the tradition of unlimited marital fertility. This critical change in social attitudes to family planning was facilitated both by developments in mass education and, ultimately by the decline of infant mortality.     

An Evaluation of Staff Preference for Graphic Characteristics

The purpose of the current study was to assess staff preference for how data were displayed on graphs. Specifically, preference for line versus bar graphs was assessed, as well as preference for data displayed as one date in time versus multiple dates showing performance trends. A secondary purpose of the study was to assess staff comprehension of the data presented across different graphic displays. Participants included 60 entry-level direct care staff and 25 seasoned therapists. Therapists had more advanced training in applied behavior analysis than the direct care staff. The vast majority of direct care staff preferred data depicted as a bar graph versus data depicted as a line graph, even preferring a single bar graph over a time-series line graph. The therapists preferred time-series line graphs to bar graphs. Most staff demonstrated understanding of the data, regardless of how it was depicted.