ESTIMATING A PARAMETER WHEN IT IS KNOWN THAT THE PARAMETER EXCEEDS A GIVEN VALUE

In some statistical problems a degree of explicit, prior information is available about the value taken by the parameter of interest, θ say, although the information is much less than would be needed to place a prior density on the parameter's distribution. Often the prior information takes the form of a simple bound, ‘θ > θ₁ ’ or ‘θ < θ₁ ’, where θ₁ is determined by physical considerations or mathematical theory, such as positivity of a variance. A conventional approach to accommodating the requirement that θ > θ₁ is to replace an estimator, , of θ by the maximum of and θ₁. However, this technique is generally inadequate. For one thing, it does not respect the strictness of the inequality θ > θ₁ , which can be critical in interpreting results. For another, it produces an estimator that does not respond in a natural way to perturbations of the data. In this paper we suggest an alternative approach, in which bootstrap aggregation, or bagging, is used to overcome these difficulties. Bagging gives estimators that, when subjected to the constraint θ > θ₁ , strictly exceed θ₁ except in extreme settings in which the empirical evidence strongly contradicts the constraint. Bagging also reduces estimator variability in the important case for which is close to θ₁, and more generally produces estimators that respect the constraint in a smooth, realistic fashion.     

Deconvolution methods for non-parametric inference in two-level mixed models

Summary.  We develop a general non-parametric approach to the analysis of clustered data via random effects. Assuming only that the link function is known, the regression functions and the distributions of both cluster means and observation errors are treated non-parametrically. Our argument proceeds by viewing the observation error at the cluster mean level as though it were a measurement error in an errors-in-variables problem, and using a deconvolution argument to access the distribution of the cluster mean. A Fourier deconvolution approach could be used if the distribution of the error-in-variables were known. In practice it is unknown, of course, but it can be estimated from repeated measurements, and in this way deconvolution can be achieved in an approximate sense. This argument might be interpreted as implying that large numbers of replicates are necessary for each cluster mean distribution, but that is not so; we avoid this requirement by incorporating statistical smoothing over values of nearby explanatory variables. Empirical rules are developed for the choice of smoothing parameter. Numerical simulations, and an application to real data, demonstrate small sample performance for this package of methodology. We also develop theory establishing statistical consistency.     

A variable-neighbourhood search algorithm for finding optimal run orders in the presence of serial correlation

The responses obtained from response surface designs that are run sequentially often exhibit serial correlation or time trends. The order in which the runs of the design are performed then has an impact on the precision of the parameter estimators. This article proposes the use of a variable-neighbourhood search algorithm to compute run orders that guarantee a precise estimation of the effects of the experimental factors. The importance of using good run orders is demonstrated by seeking D-optimal run orders for a central composite design in the presence of an AR(1) autocorrelation pattern.     

Profile of the Present Slovak Society and its Regional Differences

The article is the first attempt in assessment of the development and the present situation of social structure and stratification in Slovakia. Its principal aim is to develop the profile of the present society in Slovakia, which reflects the pace and complexity of the transformation process and its impact on society. Processing of Micro census data from 2003 led to creation of the profile of society in Slovakia at the national level based on income distribution but also knowledge on regional societies and differences between them were obtained. It was found out that the present profile of the society in Slovakia is pear-shaped which means strong representation of lower strata and weaker representation of higher middle and high strata. The profile disclosed some specific features and inconsistencies in the present society of Slovakia, which were, and still are determined by many non standard past and present phenomena and processes often disguised by reforms. The information drawn in regions has facilitated identification of the basic nature and structure of regional societies, some of their specific features and negative elements and to demonstrate their highly differentiated character.

The Best and Worst Times of Life: Narratives and Assessments of Subjective Well-Being by Anamnestic Comparative Self Assessment (ACSA) in the Eastern Cape,South Africa

The Anamnestic Comparative Self Assessment (ACSA) measure of subjective well-being (SWB) aims to reduce the problems of cultural bias and relativity to external standards by allowing people to define the endpoints or ‘anchors’ of the measurement scale. In medical terminology anamnestic denotes ‘based on memory’. The ACSA uses subjects’ memories of the best and worst periods in their lives to define the anchors of the scale. They then assess their current quality of life relative to these personal anchors. The South African pilot study tested the match between self-assessment of SWB with ACSA and the conventional single-item measures of life satisfaction and happiness used in the South African Quality of Life Trends Study and analysed the narratives of the best and worst times of life. The quota sample of 46 consisted of 26 residents of Makana district in the Eastern Cape Province, South Africa, and 20 patients undergoing treatment in the local TB hospital. Mean SWB ratings with all three measures of life satisfaction, happiness and ACSA were between 5 and 6 on a 0–10-point scale. Ratings on all three scales were positively correlated. However, on ACSA the TB patients rated their current SWB 1.84 points lower than the community respondents, suggesting a greater sensitivity of this measure. It was observed that the starting points of the life stories produced by respondents to define the anchor periods for ACSA were related to their current assessment of SWB. A typology was developed that combined the starting point of the life stories with current SWB. The majority of community respondents matched the ‘Achiever’ type who scored positively on ACSA (i.e., above the mid-point of the scale) and whose life stories started with the worst period of their lives and proceeded to the best period. The TB patients were the only respondents to represent the ‘Survivor’ type whose morale had recovered after misfortune in life. ‘Survivors’ started their narratives with the best period in their lives, then moved to the worst (often health-related) one, and gave positive ACSA ratings. Based on the qualitative analysis of narratives, it is concluded that ACSA is a sensitive measurement instrument and therefore particularly useful for monitoring the effects of treatments and social interventions in longitudinal studies. However, further research is required to verify its cross-cultural validity.

The City of Saskatoon’s Local Area Planning Program: A Case Study

The City of Saskatoon’s Local Area Planning (LAP) Program is a community-based approach to developing comprehensive neighbourhood plans. In order to achieve sustainable and implementable Local Area Plans (LAPs), the City of Saskatoon has been using innovative methods of collaborative decision-making to engage citizens. The program has been recognized nationally by the Federation of Canadian Municipalities for demonstrating innovative approaches to citizen engagement in Sustainable Community Planning. A total of eight LAPs have been adopted by City Council and 212 recommendations have been approved, with 101 of these recommendations being completed, 71 currently in progress and 40 to be determined. Great strides have been made to implement the LAPs by allocating resources for coordinating implementation, working with communities, and for implementing the various recommendations. In addition, over 1,000 people representing various interests have participated in one or more LAP Committee or implementation meetings. Through this participation, partnerships have been formed, program and service delivery has been improved, and most importantly, communities have taken ownership of their plans. After completing eight LAPs, the LAP communities, City Council and city planners have felt the need to measure ongoing changes and progress in the LAP communities. In recognition of this, the City of Saskatoon’s City Planning Branch will be working with LAP communities, the Community-University Institute for Social Research (CUISR) and other stakeholders to develop a framework for statistically measuring changes in LAP communities and to monitor “Neighbourhood Success Factors”. The Neighbourhood Success Factors will work to detect serious socio-economic conditions before they reach a point of crisis. This paper will first describe the LAP Program before reviewing the proposed framework for statistically measuring changes in Saskatoon’s neighbourhoods.

Is demography destiny? The role of structural and demographic factors in Australis past and future labour supply

Following the release of the Intergenerational Report, the Australian Treasury identified the levers to address the economic effects of demographic ageing as ‘the three Ps’: population, participation and productivity. To date, the first ‘P’, population, has been treated as an exogenous factor, with the common view being that there is very little that the government can do to supplant demographic ageing. Focusing upon labour supply, this paper shows how variation in Australia’s underlying demography can significantly alter Australia’s future labour supply. Although governments cannot redirect the cohort flow component of population ageing, much can be achieved in promoting growth of the labour supply by maintaining or increasing fertility (in the longer term), or increasing targeted migration (in the short to medium term). This paper also decomposes the relative role of cohort flow, changing demography and changing labour force participation on the growth of the labour supply over the past 20 years. Over this period, the entry of the baby boom generation (cohort flow) and increased labour force participation of women accounted for almost all of the growth in the labour force. Changing demography had very little effect. However, Australias future labour supply will not include a large increase in cohort flow (as caused by the baby boomers) or a very large increase in female labour force participation. Regardless of the assumptions used, labour supply growth will be considerably lower in the next and subsequent 20 years, when compared to the previous 20.     

Intention to emigrate in transition countries: the case of Albania

We analyse the profile of potential emigrants from Albania using data from the Central and Eastern Europe Eurobarometer in 1992. Respondents were asked to rate on a four-point scale the likelihood that they would go to live in Western Europe. Our results show that intention to emigrate is correlated positively with males, education and certain occupations, and negatively with age. There is little relation between emigration and income. Those who support the introduction of a free market in Albania are also more likely to emigrate than those who do not. Received: 24 August 1998/Accepted: 17 April 2000