Family size and children’s education in Vietnam

Data from the nationally representative 1994 Inter-Censal Demographic Survey are used to examine the association between family size and children s schooling in Vietnam. The data provide information on several education measures for all children over age 10, including children no longer residing in the household. Although a clear inverse bivariate association between family size and children s school attendance and educational attainment is evident, multivariate analysis controlling for urban/rural residence, region, parents’ education, household wealth, and child’s age, reveals that much of this association, especially that predicting educational attainment, is attributable to these other influences. Moreover, much of the effect that remains after statistical adjustment for the other influences is seen mainly at the largest family sizes. We consider the implications of these findings for current population policy in Vietnam and the possible features of the Vietnamese context that might account for the modest association.     

Making sense of census data: A components analysis of employment change among indigenous Australians

The 1996 Census count of indigenous Australians included a substantial number of individuals who were not recorded as indigenous by the previous census. This paper considers the implications of this for interpreting change in employment numbers. Two adjustments are made to employment change data. First, reverse survival of the 1996 population is applied to reconstruct 1991 employment figures. Second, administrative data are used to discount employment generated by participation in labour market programs. The effect is to substantially deflate the strong intercensal employment growth apparent from census counts with the conclusion that the rate of indigenous employment in the mainstream labour market has fallen.     

Effects of Group Practice of the Transcendental Meditation Program on Preventing Violent Crime in Washington,D.C.: Results of the National Demonstration Project,June--July 1993

This paper reports the results of a prospective experiment in which a group of approximately 4,000 participants in the Transcendental Meditation and TM-Sidhi programs of Maharishi Mahesh Yogi assembled in Washington, D.C., from June 7 to July 30, 1993. It was hypothesized that levels of violent crime in the District of Columbia would fall substantially during the Demonstration Project, as a result of the group's effect of increasing coherence and reducing stress in the collective consciousness of the District. A 27-member Project Review Board comprising independent scientists and leading citizens approved the research protocol and monitored the research process. Weekly crime data was derived from database records provided by the District of Columbia Metropolitan Police Department (DCMPD), which are used in the FBI Uniform Crime Reports. Statistical analysis considered the effect of weather variables, daylight, historical crime trends and annual patterns in the District of Columbia, as well as trends in neighboring cities. Consistent with previous research, levels of homicides, rapes and assaults (HRA crimes) correlated with average weekly temperature. Robberies approximately followed an annually recurring cycle. Time series analysis of 1993 data, controlling for temperature, showed that HRA crimes dropped significantly during the Demonstration Project, corresponding with increases in the size of the group; the maximum decrease was 23.3% (p < 2 × 10–9) [24.6% using a longer baseline, with 1988--1993 data (p < 3 × 10–5)], coincident with the peak number of participants in the group during the final week of the assembly. When the same period in each of the five previous years was examined, no significant decreases in HRA crimes were found. Robberies did not decrease significantly. However, a model that jointly estimated the effect of the Demonstration Project on both HRA crimes and robberies showed a significant reduction in violent crimes overall of 15.6% (p = 0.0008). Further analysis showed that the effect of the coherence-creating group on reducing HRA crimes could not be accounted for by additional police staffing. The time series analysis for HRA crimes gave results that are highly robust to alternative model specifications, and showed that the effect of the group size was cumulative and persisted after the Demonstration Project ended. Also, calculation of the steady state gain based on the time series model predicted that a permanent group of 4,000 coherence-creating experts in the District would have a long-term effect of reducing HRA crimes by 48%.     

ON ESTIMATING PARAMETERS FOR BETA DISTRIBUTIONS

The purpose of this paper is to comment on and give historical perspective to two methdologies for estimating parameters of beta distributions. Fielitz and Myers [3] [4] developed and advocated a methodology using the method of moments, while Romesburg [20] advocated a methodology usingthe method of maximum likelihood. However, what Fielitz and Myers presented as new research and suggested as an area needing further study is ground already trampled. The authors have prepared a graph to underline the superiority of the maximum likelihood method in fitting beta distributions.     

Does product complexity matter for competition in experimental retail markets?

We describe a first experiment on whether product complexity affects competition and consumers in retail markets. We are unable to detect a significant effect of product complexity on prices, except insofar as the demand elasticity for complex products is higher. However, there is qualified evidence that complex products have the potential to induce consumers to buy more than they would otherwise. In this sense, consumer exploitability in quantities cannot be ruled out. We also find evidence for shaping effects: consumers’ preferences are shaped by past experience with prices, and firms may in principle exploit this to sell more.     

Transforming sub-Saharan Africa

This article provides an analysis of my personal experience and research on the need for sub-Saharan African economic transformation. It contains relevant references to econometric modeling which are consistent with this analysis. After presenting the causes of African failures, ranging from the alleged role of slavery and colonization, to trade composition and relative decline, to present day problems of governance, low level of foreign investment in Africa, and mass unemployment, the article concludes with an agenda for the transformation of sub-Saharan Africa.     

Identifying the most successful dose (MSD) in dose-finding studies in cancer

For a dose finding study in cancer, the most successful dose (MSD), among a group of available doses, is that dose at which the overall success rate is the highest. This rate is the product of the rate of seeing non-toxicities together with the rate of tumor response. A successful dose finding trial in this context is one where we manage to identify the MSD in an efficient manner. In practice we may also need to consider algorithms for identifying the MSD which can incorporate certain restrictions, the most common restriction maintaining the estimated toxicity rate alone below some maximum rate. In this case the MSD may correspond to a different level than that for the unconstrained MSD and, in providing a final recommendation, it is important to underline that it is subject to the given constraint. We work with the approach described in O'Quigley et al. [Biometrics 2001; 57(4):1018-1029]. The focus of that work was dose finding in HIV where both information on toxicity and efficacy were almost immediately available. Recent cancer studies are beginning to fall under this same heading where, as before, toxicity can be quickly evaluated and, in addition, we can rely on biological markers or other measures of tumor response. Mindful of the particular context of cancer, our purpose here is to consider the methodology developed by O'Quigley et al. and its practical implementation. We also carry out a study on the doubly under-parameterized model, developed by O'Quigley et al. but not     

A Multiple Imputation Approach to Linear Regression with Clustered Censored Data

Weextend Wei and Tanner's (1991) multiple imputation approach insemi-parametric linear regression for univariate censored datato clustered censored data. The main idea is to iterate the followingtwo steps: 1) using the data augmentation to impute for censoredfailure times; 2) fitting a linear model with imputed completedata, which takes into consideration of clustering among failuretimes. In particular, we propose using the generalized estimatingequations (GEE) or a linear mixed-effects model to implementthe second step. Through simulation studies our proposal comparesfavorably to the independence approach (Lee et al., 1993), whichignores the within-cluster correlation in estimating the regressioncoefficient. Our proposal is easy to implement by using existingsoftwares.     

Bounding convergence rates for Markov chains: An example of the use of computer algebra

Kolassa and Tanner (J. Am. Stat. Assoc. (1994) 89, 697–702) present the Gibbs-Skovgaard algorithm for approximate conditional inference. Kolassa (Ann Statist. (1999), 27, 129–142) gives conditions under which their Markov chain is known to converge. This paper calculates explicity bounds on convergence rates in terms calculable directly from chain transition operators. These results are useful in cases like those considered by Kolassa (1999).     

A modified likelihood ratio test for homogeneity in finite mixture models

Testing for homogeneity in finite mixture models has been investigated by many researchers. The asymptotic null distribution of the likelihood ratio test (LRT) is very complex and difficult to use in practice. We propose a modified LRT for homogeneity in finite mixture models with a general parametric kernel distribution family. The modified LRT has a χ-type of null limiting distribution and is asymptotically most powerful under local alternatives. Simulations show that it performs better than competing tests. They also reveal that the limiting distribution with some adjustment can satisfactorily approximate the quantiles of the test statistic, even for moderate sample sizes.