Temporal Aggregation in Dynamic Linear Models

One important aspect concerning the analysis and forecasting of time series that is sometimes neglected is the relationship between a model and the sampling interval, in particular, when the observation is cumulative over the sampling period. This paper intends to study the temporal aggregation in Bayesian dynamic linear models (DLM). Suppose that a time series Y_t is observed at time units t and the observations of the process are aggregated over r units of time, defining a new time series Z_k=Σ^r_i=1Y_rk+i. The relevant factors explaining the variation of Z_k can, and in general will, be different, depending on how the sampling interval r is chosen. It is shown that if Y_t follows certain dynamic linear models, then the aggregated series can also be described by possibly different DLM. In the examples, the industrial production of Brazil is analysed under various aggregation periods and the results are compared. © 1997 John Wiley & Sons, Ltd.     

Unit dimensions and space group of Tl2Cl3

Zusammenfassung Die Struktur von Tl₂Cl₃ gehört wahrscheinlich der Raumgruppe D _3d ² an. Die hexagonale Zelle hat die Dimensionena=14·3 k X,c=25·1 k X und enthält 32 Einheiten Tl₂Cl₃.     

Effects of pCai and pHi on cell-to-cell coupling

Summary Internal longitudinal resistance (r_i), a determinant of cardiac conduction, is affected by changes in intracellular calcium and protons. However, the role and mechanism by which H⁺ and Ca²⁺ may modulate r_i is uncertain. Cable analysis was performed in cardiac Purkinje fibers to measure r_i during various interventions. In some experiments, intracellular pH (pH_i) was recorded simultaneously to study the pH_i-r_i relation. Both intracellular Ca²⁺ and H⁺ independently modified r_i. However, internal resistance of cardiac fibers was insensitive to pH_i changes compared to other tissues. A latent period preceded the pH_i-related changes in r_i and the amount of change depended upon methodology. The results suggest that direct action of protons on r_i may be subordinate to other regulatory processes. Ionic regulation of internal longitudinal resistance may occur by more than one mechanism: i) direct cationic binding to sites on junctional membrane proteins; and ii) H⁺- or Ca²⁺-dependent phosphorylation of junctional proteins.     

Cell-to-cell coupling studied in isolated ventricular cell pairs

Summary Cell pairs isolated from adult rat and guinea pig ventricles were used to study the electrical properties of the nexal membrane. Each cell of a pair was connected to a voltage-clamp system so as to enable whole-cell, tight-seal recording. The current-voltage relationship of the nexal membrane was found to be linear, revealing a resistance r_n of 2–4 M. r_n was insensitive to the sarcolemmal membrane potential (range:–90 to +30 mV), and exerted no time-dependent gating behavior (range: 0.1 to 10 s). Lowering pH_i yielded a small increase in r_n. Vigorous elevations in [Ca²⁺]_i gave rise to an increase in r_n which was associated with a cell shortening. Uncoupling caused by aliphatic alcohols or halothane did not produce cell shortening. Cell pairs were also used to study action potential transfer.     

Sensitivity of univariate AR(1) time‐series forecasts near the unit root

We consider the linear time‐series model y_t=d_t+u_t(t=1,...,n), where d_t is the deterministic trend and u_t the stochastic term which follows an AR(1) process; u_t=θu_t−1+ϵ_t, with normal innovations ϵ_t. Various assumptions about the start‐up will be made. Our main interest lies in the behaviour of the l‐period‐ahead forecast y_n+1 near θ=1. Unlike in other studies of the AR(1) unit root process, we do not wish to ask the question whether θ=1 but are concerned with the behaviour of the forecast estimate near and at θ=1. For this purpose we define the sth (s=1,2) order sensitivity measure λ_l^(s) of the forecast y_n+1 near θ=1. This measures the sensitivity of the forecast at the unit root. In this study we consider two deterministic trends: d_t=β_t and d_t=β_t+β_tt. The forecast will be the Best Linear Unbiased forecast. We show that, when d_t=β_t, the number of observations has no effect on forecast sensitivity. When the deterministic trend is linear, the sensitivity is zero. We also develop a large‐sample procedure to measure the forecast sensitivity when we are uncertain whether to include the linear trend. Our analysis suggests that, depending on the initial conditions, it is better to include a linear trend for reduced sensitivity of the medium‐term forecast. Copyright © 2001 John Wiley & Sons, Ltd.     

Forecasting and trading currency volatility: an application of recurrent neural regression and model combination

In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley & Sons, Ltd.     

Chemical defense in the three European species ofCrematogaster ants

The composition of the Dufour gland of the antC. scutellaris has been reinvestigated by gas chromatography/mass spectrometry. The major components of the gland are (2E,5E,12Z)-4-oxoheneicosa-2,5,12-trien-1-ol acetate (1a) its ¹⁴ and ¹⁶ double bond isomers (1b and1c), and the corresponding (Z,Z)-dienes5a and5b, all containing an acetylated C₂₁ chain. The previously proposed structures1d, 1e, and5c, which are based on an homologous acetylated C₂₃ chain, correspond to minor derivatives present in the gland. Traces of acetylated C₁₉ homologs, tentatively identified as1g-1i, have also been found. The Dufour gland contents of the two other EuropeanCrematogaster species have also been studied.C. auberti is very similar toC. scutellaris in producing mainly1a, 1b and1c, together with the same higher and lower homologs, but it lacks the dienic derivatives5, whereasC. sordidula contains essentially the acetylated C₁₉ compounds1g, 1h, and1i, accompanied by acetylated C₁₇ homologs.     

A new quantitative relation between internal and external steady-state concentrations in active transport

Zusammenfassung Im aktiven Transport der Aminosäureanalogen (-Aminoisobuttersäure und Cyclopentan-1-aminocarbonsäure) in Gehirnschnitten folgt das Verhältnis im stationären Zustand zwischen der intrazellulären Konzentration und der Lösungskonzentration derFreundlich Adsorptionisotherme,C _i =AC ₀ ⁿ . Dieses Verhältnis stimmt mit dem Modell einer aktiven Pumpe, die der Michaelis-Menten Kinetik folgt und mit einer passiven Ausdiffusion ausgeglichen ist, nicht überein. Es wird vermutet, dass eine Kontrolle des aktiven Transports durch intra- und extrazelluläre Konzentrationen reguliert wird.     

Mutant expression in inbred lines and crosses

Zusammenfassung In Versuchen mit der Mutanteci ^D vonDrosophila melanogaster wurden die Komponenten der nichtgenetischen Varianz der Merkmalsausprägung bestimmt durch Einkreuzen vonci ^D in verschiedene Inzuchtstämme, Die unabhängige Komponente (V _i ) für die beiden Flügel ist mehrere Male grösser als die gemeinsame Komponente (V _c ). Nach Kreuzung zwischen den Inzuchtstämmen wurde keine Veränderung derV _i -Werte und in den Werten der Merkmalsausprägung keine Annäherung an den normalen Phänotypus festgestellt.     

Folic acid and the inhibition of brain L-glutamic decarboxylase

Summary Folic acid competitively inhibited brainl-glutamic decarboxylase (K _i=1.62×10^–3 M). This inhibition could possibly be associated with epilepsy.This work was supported by the United Parkinson Foundation.     

Sopra un caso particolare della superficie F 4 (3) di M. Noether

Summary The Noetherian surfaceF ₄ ⁽³⁾ , which is represented on a plane by a linear ³ system ofC ₉(A ₁ ³ A ₂ ³ A ₃ ³ A ₄ ³ A ₅ ³ A ₆ ³ A ₇ ³ A ₈ ³ A ₉ ² A ₁₀), possesses generally only one linear pencil of elliptic cubics. IfA _i (i=1, 2, , 9) are the basis points of aHalphen pencil ofC ₉,A ₁₀ is infinitely near toA ₉, and in this caseF ₄ ⁽³⁾ is a not trivial example of such a surface with two pencils of elliptic cubics.     

ARFIMA approximation and forecasting of the limiting aggregate structure of long‐memory process

This article studies Man and Tiao's (2006) low‐order autoregressive fractionally integrated moving‐average (ARFIMA) approximation to Tsai and Chan's (2005b) limiting aggregate structure of the long‐memory process. In matching the autocorrelations, we demonstrate that the approximation works well, especially for larger d values. In computing autocorrelations over long lags for larger d value, using the exact formula one might encounter numerical problems. The use of the ARFIMA(0, d, d?₁) model provides a useful alternative to compute the autocorrelations as a really close approximation. In forecasting future aggregates, we demonstrate the close performance of using the ARFIMA(0, d, d?₁) model and the exact aggregate structure. In practice, this provides a justification for the use of a low‐order ARFIMA model in predicting future aggregates of long‐memory process. Copyright © 2008 John Wiley & Sons, Ltd.     

An in vitro kinetic study of the mixed inhibition of honeybee hemolymph PNP-α-D-glucosidase by sucrose

Summary Sucrose acts in vitro as a mixed inhibitor of (V+K+n) type towards honeybee hemolymph PNP--D-glucosidase activity. Between the stages of emergence and foraging, there is little change in the effect of the inhibitor on V_M (f_i=from 1.31 to 1.35 respectively) or n (f_i=from 1.09 to 1.07) but K is more markedly affected (f_i ^–1=from 1.17 to 1.87)^M. These observations reflect the decrease of K_i from 277 to 98 mM and of I₅₀ from 154 to 111 mM, but K_i scarcely alters during development (from 477 to 425 mM). These inhibitory effects of sucrose are intermediate between those previously reported for trehalose and glucose.Acknowledgments. Particular appreciation is due to Mrs C. Joliet for her meticulous technical assistance, and to Mr R. Paris for his care as beekeeper. Dr M.R.J. Morgan is grateful for financial support from The Leverhulme Trust. The Royal Society, I.C.I. Plant Protection and Shell International Petroleum.     

Polarographic determination of the reaction rate of the second step in an SN1 displacement

Zusammenfassung Die Zeitabhängigkeit des polarographischen Stromes, welche man bei der gemäss SN1 verlaufenden Hydrolyse vonp-Methoxy-2-phenylpropylchlorid beobachtet, ermöglicht die Bestimmung der Geschwindigkeitskonstantenk ₁ der Gesamtreaktion sowie auch der Geschwindigkeitskonstantenk ₂ des zweiten raschen Schrittes, welcher nach pseudo-erster Ordnung verläuft. Fürk ₂ ergibt sich in Aceton, das 5% Wasser enthält, bei 25°Ck ₂=2,0×10³ sec^–1.

---

---

We would like to thank the N.R.C. for provision of a grant to purchase the Electrochemical System and the University of New Brunswick for a Fellowship for one of us (D.B.).     

Der Mitosezyklus im diploiden und triploiden Wurzelmeristem vonScilla sibirica

Summary In meristematic root tip cells ofScilla sibirica (2n=12 and 3n=18) the following results were obtained with the aid of autoradiography: 1. The average duration of the mitotic cycle (2n=12) is 69.5 h. The G₁-phase lasts 36.5 h, the DNA synthetic phase 17.5 h, the G₂-phase 8 h and mitosis 7.5 h. 2. There are no marked differences in the lengths of the cell cycles nor in the duration of the various phases between diploid and triploid plants.     

Étude quantitative de la régénération caudale,avec ou sans moelle épinière,chez la larve de Salamandre

Summary Tail regeneration in the absence of spinal cord was studied quantitatively in larval salamanders. Growth parameters were calculated according to the function =1/ny _i /x _i (Rao).The regeneration rate of despinalized tails was found to be approximatively half the normal rate in both the length and volume.The real nature of despinalized tail regenerates is discussed and two hypotheses are proposed for their explanation.

---

---

Travail exécuté grâce une subvention de la «DonationGeorges etAntoine Claraz, instituta et curataJohannis Schinz professoris auspiciis».     

Forecasting carbon price using a multi-objective least squares support vector machine with mixture kernels

For improving forecasting accuracy and trading performance, this paper proposes a new multi-objective least squares support vector machine with mixture kernels to forecast asset prices. First, a mixture kernel function is introduced into taking full use of global and local kernel functions, which is adaptively determined following a data-driven procedure. Second, a multi-objective fitness function is proposed by incorporating level forecasting and trading performance, and particle swarm optimization is used to synchronously search the optimal model selections of least squares support vector machine with mixture kernels. Taking CO₂ assets as examples, the results obtained show that compared with the popular models, the proposed model can achieve higher forecasting accuracy and higher trading performance. The advantages of the mixture kernel function and the multi-objective fitness function can improve the forecasting ability of the asset price. The findings also show that the models with a high-level forecasting accuracy cannot always have a high trading performance of asset price forecasting. In contrast, high directional forecasting usually means a high trading performance.     

Exact test for opposite trends of probability changes in one or several 3×2 tables

Zusammenfassung Der «Likelihood»-Quotiententest wird auf einer 3×2-Kontigenztafel mit unbekannten Wahrscheinlichkeitenp _ij (i=1,2,3;j=1,2) angewandt, um die Hypothese H₀:p _i1=p _i2 (i=1,2,3) gegen die alternative Hypothese H₁:p ₁₁>p ₁₂ p ₃₁<p ₃₂ zuprüfen, und zwar wenn kleine Stichproben vorhanden sind. Ausserdem wird die Kombination solcher Tests behandelt. Als Beispiel wird diese Testtheorie beim Wahlverhalten des Kabeljaus im Dressurversuch über akustische Lokalisation in zwei Stimulussituationen verwendet.

---

---

The close cooperation with Drs.E. Meelis, Institute of Theoretical Biology Leyden, The Netherlands, in applying the likelihood ratio test to this case is gratefully acknowledged.

---

The author is greatly indebted to Dr.J. Oosterhoff, Mathematical Institute, University of Nijmegen, The Netherlands, for introducing the subclasses 1b and 1c in the computation of vector and for the explicit expressions in these cases which eliminated the need for a numerical optimization. Further more valuable remarks regarding the combination problem were obtained.     

Analysis of many short time sequences: Forecast improvements achieved by shrinkage

Credibility models in actuarial science deal with multiple short time series where each series represents claim amounts of different insurance groups. Commonly used credibility models imply shrinkage of group-specific estimates towards their average. In this paper we model the claim size yu in group i and at time t as the sum of three independent components: y_it = μ_r + δ_i + ?_it. The first component, μt = μ_t?1 + m_t, represents time-varying levels that are common to all groups. The second component, δ_i, represents random group offsets that are the same in all periods, and the third component represents independent measurement errors. In this paper we show how to obtain forecasts from this model and we discuss the nature of the forecasts, with particular emphasis on shrinkage. We also assess the forecast improvements that can be expected from such a model. Finally, we discuss an extension of the above model which also allows the group offsets to change over time. We assume that the offsets for different groups follow independent random walks.