On Second Order Admissibilities in Two-Parameter Logistic Regression Model

In two-parameter family of distribution, conditions for a modified maximum likelihood estimator to be second-order admissible are given. Applying these results to two-parameter logistic regression model, it is shown that the maximum likelihood estimator is always second-order inadmissible and the Rao-Blackwellized minimum logit chi-squared estimator is second-order admissible if and only if the number of the doses is greater than or equal to 6.     

Some comments on escoufier's RV- coefficient as a sensitivity measure in principal component analysis

The RV-coefficient (Escoufier, 1973; Robert and Escoufier, 1976) is studied as a sensitivity coefficient of the subspace spanned by dominant eigenvectors in principal component analysis. We use the perturbation expansion up to second order term of the corresponding projection matrix. The relationship with the measures by Benasseni (1990) and Krzanowski (1979) is also discussed.     

On the stability of the stock-harvesting system controlled by a feedback management procedure

Summary Stability of the stock-harvesting system regulated by a feedback control procedure of catch quota is examined. In the procedure considered, catch quota is changed proportionally to the difference between current and the target stock level (with a proportionality constanth) and to the annual stock growth rate (with a proportionality constantg). Condition for the local stability of the target equilibrium is obtained as a function of the stock-recruitment relation, survival probability of adults, target stock level, time lag before implementation of regulation, age of sexual maturity of the stock, and proportionality constantsg andh. It is shown that, (1) the procedure has the stabilizing effect; it can stabilize the target stock level that is unstable under constant harvest, (2) lower target stock level favors largerg and smallerh, when the target is set around MSYL (the stock level that gives MSY), (3) the degree of stability, measured by the time required to recover the target stock level, is an increasing function of the target stock level, (4) stability and sustainable yield are in trade-off, (5) time delay caused by the time needed before sexual maturity does not affect the stability significantly, but the effect of the time lag before implementation of regulation is significant. Comparison between harvest-control and effort-control procedures is also made, and the advantage of the latter in terms of stability is shown.     

Inquiry into effects of prebaiting on removal census in a vole population

Summary A field work with two plots of grid, a snap trap being set on each station spaced 5 m apart, was executed in the summer of 1968 to evaluate prebaiting in census trapping by comparing the result in one plot, prebaited for three days, with that in the other not prebaited. Since the population was as high as some 230 per acre on the average in density and formed of the vole,Microtus montebelli, alone, sufficient samples were gathered irrespective of the plot size as small as 50×50 m. Owning to the circumstances, multiple collisions inflicted so intense influence on sampling especially in the prebaited plot thatz-equation for census adjusted to the effect was well applicable to the data in either plot. In sampling, the fact that small voles are apt to be caught later than large voles was statistically evidenced in either sex, and yet any proof that males tend to be caught prior to females was not offered. It was ascertained in either plot that the daily catch was realized according to the same rule through the whole period of trapping in both external belt and internal square within the plot; hence it follows that no considerable immigration occurred. One of the beneficial effects of prebaiting is sure to be that the probability of capture was markedly enhanced in the prebaited plot, and a second is supposed, though inconclusively, to be that a good sampling could be executed consistently through the census period giving rise to no inordinate catches perhaps due to heterogeneous sampling as was seen in earlier days in the not prebaited plot. The supposition has derived from the condition that most of the whole population is trappable, which is established by interrelation among population density, size of home range and trap spacing. It was suggested that the effect of prebaiting should be evaluated from the view-point of the interrelation, because the basic utility of prebaiting consists in that it may help to our utlimate purpose to estimate the whole population. Contribution from JIBP-PT No. 55, carried out by the grant from the expenditure of Education Department to the specific study on “Dynamics of Biosphere”     

New regression formula to estimate the whole population for recapture-addicted small mammals

Summary We have devised a census formula of curvilinear regression suitable for capture-recapture data of recapture-addicted populations of the Japanese field vole (Microtus montebelli) obtained under a grid-plan with single-catch traps in order to estimate the whole population. The equation is founded on the assumption that the trappable population on the initial day is increased in way of an exponential curve until it reaches to the whole during one trapping period. The effect of trap-preoccupation by marked and multiple collisions is considered in the formula. As a result of its application to field data of the vole, it has turned out that the equation is required for the data gained under the trapping plan with trap spacing 10m, but not for those under the plan with spacing 5m, to estimate the whole. A convenient method of analysis of the formula is offered here, but we have been yet unable to introduce assymptotic variance of estimates. Contributions from JIBP-PT No. 19, carried out by the grant from the expenditure of Education Department to the specific study on “Dynamics of Biosphere”.     

Age specificity of inbreeding depression during a life cycle ofCallosobruchus chinensis (Coleoptera: Bruchidae)

Summary Age-specific effects of inbreeding on fecundity were assayed for adzuki bean weevilCallosobruchus chinensis by comparing inbred lines and their cross. Four consecutive full-sib matings reduced only 10.3 percent in total fecundity, and did not decrease early fecundity at all until third day from the onset of reproduction. It is suggested that recessive detrimental genes have been eliminated from the early period of adult life span when reproductive value is high. There was a slight tendency that inbreeding depression increased as age proceeded though not statistically significant.     

On improved estimation of a gamma shape parameter

This paper deals with improved estimation of a gamma shape parameter from a decision-theoretic point of view. First we study the second-order properties of three estimators – (i) the maximum-likelihood estimator (MLE), (ii) a bias corrected version of the MLE, and (iii) an improved version (in terms of mean squared error) of the MLE. It is shown that all the three estimators mentioned above are second-order inadmissible. Next, we obtain superior estimators which are second order better than the above three estimators. Simulation results are provided to study the relative risk improvement of each improved estimator over the MLE.     

Genetic variance and covariance patterns of larval development in the small white butterflyPieris rapae crucivora Boisduval

Summary Quantitative genetic theory indicates that genetic covariance patterns among life history characters should have played an important role as genetic constraint in life history evolution. Highly positve (and negative) genetic correlations between larval development time (or larval growth rate) and adult size characters were detected by means of sib analysis for the small white butterflyPieris rapae crucivora. The genetic associations suggested that evolution of developmental characteristics and adult phenotypic traits were constrained by pleiotropy. The positive genetic correlations between development time and adult body size may be compatible with the trade-off between them, but the negative genetic correlations between larval growth rate and adult body size are not predicted from theories of optimal energy allocation. That phenotypic correlations drastically differed from the genetic correlations indicates limitations of evolutionary inferences based only on phenotypic variation.     

Standardization as a Means for Globalizing a Commodity: The Case of Rapeseed in China*

Abstract Not all commodities are things, nor are all things available in society commodities. Then, what are commodities? Using the case of rapeseed and its products in China, this paper examines the role of grades and standards (G&S) in simultaneously determining the life of things as commodities and the position of humans as market participants. In the first section, we summarize our conceptual understandings of commodities. Next, the paper examines tests and trials to which rapeseed in China were subjected by the mid 1990s. We then discuss how G&S represent political processes among commodity chain actors for creating, legitimizing and maintaining the social relations between things and people. Lastly, we discuss our conclusion that the analysis of tests and trials helps us understand the process of commodification as simultaneous transformations of humans and things in a commodity chain while reorganizing linkages among these actors.