Eddie McKenzie

Discrete variate time series

Publisher Summary Modeling discrete variate time series is the most challenging and, as yet, least well developed of all areas of research in time series. The fact that variate values are integer renders most traditional representations of dependence either impossible or impractical. Discrete variate time series occur in many contexts, often as counts of events, objects or individuals in consecutive intervals or at consecutive points in time. Some simple examples are the numbers of accidents in a manufacturing plant each month, the numbers of patients treated by a hospitals accident and emergency unit each hour, the numbers of fish caught in a particular area of sea each week, the numbers of busy lines in a telephone network noted every thirty minutes, and the numbers of lifts in a tall office building, which are fully operational at the start of business each day. Such data may also arise from the discretization of continuous variate time series.

Why the Damped Trend Works

The damped trend method of exponential smoothing is a benchmark that has been difficult to beat in empirical studies of forecast accuracy. One explanation for this success is the flexibility of the method, which contains a variety of special cases that are automatically selected during the fitting process. That is, when the method is fitted, the optimal parameters usually define a special case rather than the method itself. For example, in the M3-competition time series, the parameters defined the damped trend method only about 43% of the time using local initial values for the method components. In the remaining series, a special case was selected, ranging from a random walk to a deterministic trend. The most common special case was a new method, simple exponential smoothing with a damped drift term.

Form and uncertainty in stock-recruitment relations : observations and implications for Atlantic salmon (Salmo salar) management

This paper reports an investigation of stock–recruitment relations for Atlantic salmon (Salmo salar). We regard these relations as stochastic functions characterized by an expected stock–recruitment relation and deviations from this expectation driven by observational error and uncharacterised environmental variability. We estimate model parameters by standard Bayesian methods. Analysis of the input–output characteristics of segments of the salmon life cycle in the Girnock Burn (Northeast Scotland) reveals two independent regulatory processes, one between ova and fry and the other between fry and smolts. Comparison of stock–recruitment relations for Atlantic salmon in Scotland, Ireland, and Canada, reinforced by an extended series of simulation studies, shows that even when comparatively long time series of high quality data are available, it is frequently difficult to exclude the possibility of low stock depensation — an effect whose implication of enhanced extinction risk implies that precautionary mana...

Increasing abundance of Calanus finmarchicus in the central and eastern North Atlantic between 1958 and 1996

The abundance of Calanus finmarchicus is known to have fallen between the present and the late 1950s in north-eastern Atlantic shelf waters. Further west in deeper water, however, long-term abundance of the copepod has risen.

Maturity Dispersion, Stock Auto-Correlation, and Management Strategy in Exploited Populations

Fishery management policies need to be based on historical summaries of stock status which are well correlated with the size of the group of individuals who will be affected by any harvest. This paper is motivated by the problem of managing stocks of Atlantic salmon, which can be accurately monitored during the riverine stages of their life-history, but which spend a lengthy period at sea before returning to spawn. We begin by formulating a minimal stochastic model of stock-recruitment driven population dynamics, which linearises to a standard ARMA form. We investigate the relation between maturity dispersion and the auto-covariance of stock fluctuations driven by process noise in the recruitment process and/or random variability in survival from recruitment to spawning. We demonstrate that significant reductions in fluctuation intensity and/or increases in long-run average yield can be achieved by controlling harvesting in response to the value of a historical summary focussed on lags at which the uncontrolled population dynamics produce strong correlations. We apply our minimal model to two well-characterised Atlantic salmon populations, and find poor agreement between predicted and observed stock fluctuation ACF. Re-examination of the ancilliary data available for one of our two exemplary systems leads us to propose an extended model which also linearises to ARMA form, and which predicts a fluctuation ACF more closely in agreement with that observed, and could thus form a satisfactory vehicle for policy discussion.

Simulation of a stationary autoregression: A characterization of the normal distribution

Abstract Simulating a stationary AR( p ), X t = ∑ p i =1 α i X t − i + Z t , when the innovations { Z t } are assumed to be i.i.d. is straightforward. Starting the process in the stationary state, however, requires generation of ( X 1 , X 2 ,…, X p ) from the stationary p -dimensional distribution. When Z t is normal this may be achieved by generating X i as a linear function of X 1 , X 2 ,…, X i −1 and an independent normal variate for i = 2,3,…, p . It is shown that the ability to initialize a stationary AR( p ) in this way characterizes the normal distribution.

Seasonal weight variation in people with diabetes - fact or fiction?

To assess the contention of many people with diabetes that they gain weight in winter and lose weight in summer we have investigated 10836 weights recorded during all the routine clinic visits of 3119 patients (age 18-93 years, 51.7% male, 31.2% diet controlled, 32.8% on oral hypoglycaemic agents, 36.0% on insulin)between February 1992 and July 1995. Efforts to fit a sinewaveform to the weight data (raw and log transformed) plotted against time of the year were unsuccessful and a smoothed mean weight plotted over time closely matched the overall mean. Linear modelling was applied to data from each clinic visit relating log transformed weight to age, gender, diabetes therapy, random plasma glucose and the interactions of these terms. The best fitting model accounted for 23.3% of the observed variability with gender, diabetes therapy, age, age squared and interactions between these as the key factors; interpatient variation accounted for over 95% of the residual variance from the model. Addition of time of year as a continuous variable or as 12 discrete factors (months) did not improve the fit of the model. We conclude that there is no general tendency to seasonal weight variation in people with diabetes.S 161 like D. m. ohioensis than D. m. macrospina. Wild flies captured in Texas display all intergrades of phenotype between the described D. m. macrospina and D. m. ohioensis; others are more extreme than the latter in the same general direction. Autosomal mutants in the progeny of single wild type females parallel those described for the closely related species D. funebris, although mutant eye colors are more prevalent. MARSHAK, A., Radiation Laboratory, University of California, Berkeley, Calif. : Chromosome abnormalities produced in interphase nuclei with x-rays and neutrons.-Previous experiments showed the frequency of chromosome abnormalities observed in anaphase a t three hours after treatment with x-rays or neutrons to be an exponential function of the dose. Abnormalities observed in V.fuba root tips a t 12 and a t 24 hours after neutron bombardment likewise vary exponentially with dose. The slopes of the curves for the 3,12 and 24 hour intervals are ,070, .o51, .036 respectively. The slope for the Vicia x-ray curve a t 24 hours is .0025. The ratio of the neutron to x-ray slopes (n/x) a t 24 hours is 14.3 as compared with the comparable ratio of 6.6 a t 3 hours. Thus chromosomes of the same organism a t different stages of the nuclear cycle give different n/x although a constant ratio has been obtained with chromosomes of very different species a t the same stage of the nuclear cydle. Pisum and Allium also give exponential curves a t 24 hours, but data are not yet sufficient for obtaining n/x. However the ratio of about 16 obtained by GILES for chromatid dicentrics in Tradescantia microspores is sufficiently close to the 14.3 for Vicia to suggest that a constancy comparable to the one observed for abnormalities induced a t the onset of prophase may be found for similar parts of the interphase in different species. MILLER, DWIGHT D., University of Rochester, N. Y.: Interspecijc hybrids involving Drosophila athabasca.-Drosophila athabasca hybridizes with D. azteca (STURTEVANT and DOBZHANSKY, 1936). I t has also been found to form interspecific hybrids with two other members of the affinis group:-D. algonquin and D. afinis. Hybrids have been obtained between algonquin females and athabasca males. The frequency of insemination is low, but a good number of apparently quite viable offspring are produced in cases of mating. Female hybrids are fertile and have been backcrossed to algonquirc males. Male hybrids produce no sperm. The salivary gland chromosomes of hybrid larvae show few cases of synapsis, but certain definite homologies have been found. These involve regions in both arms of the B chromosome, both arms of C, and the entire dot-like D chromosome. The frequency of insemination of Drosophila afinis females by D. athabasca males is quite high, but hybrid production is low. The nature of the mechanism whereby such interspecifically inseminated females fail to produce off spring is being studied. The athabasca-afinis hybrids seem to be well viable. Neither sex has been shown to be fertile. Spermatogenesis appears to be grossly abnormal, involving the production of large, multinuclear masses within the testes. ABSTRACTS OF PAPERS PRESENTED AT THE 1940 MEETINGS OF THE GENETICS SOCIETY OF AMERICAS OF PAPERS PRESENTED AT THE 1940 MEETINGS OF THE GENETICS SOCIETY OF AMERICA PHILADELPHIA, PA., DECEMBER 3 e J A N . I, IQ41 E. W. LINDSTROM, Secretary Department of Genetics Iowa State College, Ames, Iowa ATWOOD, SANFORD S., U. S. Regional Pasture Research Laboratory, State College, Pa. : Cytogenetic basis of self-compatibility in Trifolium repens.When 615 plants, selected a t random from approximately IO,OOO, were selfpollinated under bags in the field in 1938, only one plant set seeds averaging over IOO per head. Except for descendants from this plant, no other has since shown a similar self-compatibility, whereas this high seed-set was duplicated on clones from the original plant by (I) different techniques of selfing in the greenhouse, (2) rubbing under bags in the field, and (3) bee pollination under a cage in the field. This plant was crossed with a self-incompatible individual, and 14 selected F1 plants were diallely intercrossed and backcrossed to both parents in the greenhouse. Two intra-sterile, inter-fertile groups of five and six F1 plants, respectively, were found, and these 11 plants were reciprocally compatible with both parents. The other three F1 plants were cross-compatible with both of these groups, with both parents, and with each other. When the entire F1 of 21 plants was selfed in the field, 16 ranged from almost complete self-incompatibility to moderate pseudo-self-compatibility, while the other five were highly self-compatible. Among these latter were the three which were cross-compatible with all others in the greenhouse. Also there have been selfed in the field 112 first-generation inbreds from the self-compatible parent; most of them were highly self-compatible, but a few were self-incompatible, and several had low pseudo-self-compatibility. It is postulated that both the selfcompatible parent and F1 plants were heterozygous for a self-compatibility factor which is a member of the multiple-allelic series conditioning selfand cross-incompatibility . BARROWS, FLORENCE L., Stafford Springs, Conn. : Inheritance in Cucurbita pollen.-Pure lines of Cucurbita Pepo L. have constant and inherited differences in pollen pattern. Sharp spined types are dominant to blunt surface spines. Surface and cap spines seem to be inherited independently. Incomplete Fz data suggest more than a single factor difference. BERGER, C. A., Fordham University, New York, N. Y. : A new criterion of the degree of polyploidy of “resting” nuclei-In the periblem of the root tips of Spinacia, diploid, tetraploid and octoploid cells are regularly found. One of the six haploid chromosomes of Spinacia has an heteropycnotic satellite. In diploid resting cells the satellites can be seen as two small chromatic bodies in contact with the nucleolus. From each satellite a single or double chromatic thread passes through the clear perinucleolar region and joins the chromatic GENETICS 26: 137 Jan. r p q ~

A statistical model for the response patterns to chemical tests for the absence or presence of trace materials

A statistical method is described which enables comparisons to be made between two sets of data where each datum can only be expressed as a positive or negative value. The method is based upon logistic regression analysis. It has been applied to patterns of positive and negative responses to chromatographic analyses carried out on hand swabs taken from a number of subjects suspected of handling explosives, and experimentally simulated data acquired on the basis of a contamination hypothesis. The analyses indicate that both patterns demonstrate ordering and that these orders are statistically indistinguishable.