Finite-sample properties of estimators for first and second order autoregressive processes

The class of autoregressive (AR) processes is extensively used to model temporal dependence in observed time series. Such models are easily available and routinely fitted using freely available statistical software like . A potential problem is that commonly applied estimators for the coefficients of AR processes are severely biased when the time series are short. This paper studies the finite-sample properties of well-known estimators for the coefficients of stationary AR(1) and AR(2) processes and provides bias-corrected versions of these estimators which are quick and easy to apply. The new estimators are constructed by modeling the relationship between the true and originally estimated AR coefficients using weighted orthogonal polynomial regression, taking the sampling distribution of the original estimators into account. The finite-sample distributions of the new bias-corrected estimators are approximated using transformations of skew-normal densities, combined with a Gaussian copula approximation in the AR(2) case. The properties of the new estimators are demonstrated by simulations and in the analysis of a real ecological data set. The estimators are easily available in our accompanying -package for AR(1) and AR(2) processes of length 10–50, both giving bias-corrected coefficient estimates and corresponding confidence intervals.

Determination of Extractable and Bound Organochlorine in Sediment by Instrumental Neutron Activation Analysis

Extractable organochlorine (EOC) and bound organochlorine (BOC) compositions in sediments from Lake Bosomtwi have been determined with instrumental neutron activation technique. Within the limit of experimental errors, the precision and accuracy of the method for the determination were within 3% and 4% respectively. The mean levels of EOC and BOC were in the range of 1.71 mg/kg to 5.18 mg/kg and 0.31 mg/kg to 0.68 mg/kg respectively. Analysis of organochlorine data showed the EOC content on the average was about seven times more than those of BOC. Washing of chloride from sediment fortified with an insoluble chloride, thus PbCl2, with various concentrations of sodium nitrate (NaNO3) solutions was investigated and washing with 0.1 M solution of NaNO3 gave the optimum yield of chloride. Organic carbon (OC) and BOC compositions in the sediments were subjected to correlation analysis and results showed that the two correlated very well with corrected coefficient of 0.65. OC in sediments could therefore, be one of the carrier phases of BOC in sediments.

Airbnb and taxation: Developing a seasonal tax system

This study applies tax planning theory to develop a seasonal tax strategy as an alternative to a fixed tax rate for shared lodging platforms such as Airbnb, to increase hosts’ revenue and to address seasonality in tourism. The annual revenue of the various types of accommodation is used to calculate a seasonality index by the moving average method, which is incorporated as a corrected coefficient in a seasonal tax formula. The sample includes data from 1258 active Airbnb listings in Boston, Massachusetts. Using a mean comparison test, this study reveals that the application of a seasonal tax strategy significantly increases the revenue of Airbnb hosts compared to a fixed tax rate system. Drawing on the flexibility tenet of tax planning theory, policymakers can use the proposed seasonal tax strategy as an instrument to revisit the taxation system for sharing economy businesses based on changes to the socio-economic, environmental and political conditions. Implications for all stakeholders are discussed.

Studies of Hard Rubber Reactions VIII. The Corrected Coefficient of Vulcanization, and Its Upper Limit in the Accelerated Raw Rubber Compound

In a previous paper (J. Soc. Chem. Ind. Japan 40, 111B (1939)) it was shown that compounds containing up to 60 per cent of sulfur give coefficients of vulcanization higher than the theoretical maximum value of 47. Strictly speaking, however, the sulfur present in these cases can be divided into the following parts : sulfur soluble in acetone; (a) true elementary sulfur; (b) sulfur combined with organic matter; sulfur insoluble in acetone; (c) sulfur combined with rubber; (d) sulfur combined with resins and proteins; (e) metallic sulfide. In the present experiments, these five kinds of sulfur were separated as far as possible to determine the true or corrected coefficient of vulcanization, and its upper limit.