Tourism Statistics and the Business Register in Italy： A Comparative Analysis and future Outlooks for Integration

After the proposal of a possible insertion of tourism statistics （supply side） （TS） into Framework Regulation Integrating Business Statistics （FR1BS） on which an interesting debate is in progress between Eurostat and NSls, Istat （Italian Institute of Statistics） has started a costs/benefits analysis of this integration. ASIA （Statistical Register of Active Enterprises）, built up by Istat, represents in Italy the official source about the structure and the economic performance of the enterprises. ASIA, whose statistical units are enterprises of industry and services, has been developed through the statistical integration of different administrative sources, other minor archives available （covering particular sectors） and structural business statistics currently produced by Istat. The supply side TS are produced by lstat through surveys via Intermediate Bodies （Local Authorities）： each Intermediate Body has its own local register of accommodation establishments based on Local Kind-of-activity unit （LKAU）. In this paper, the results of a comparative analysis between the statistical units as recorded in ASIA and as surveyed by TS are presented; from first outcomes, considerable issues about data quality appear both at level of coverage for the three Nace groups of the TS （also underlined in the Methodological Manual on Tourism Statistics where for Italy a difference of 70% is reported） and for loss information relating to the location of the activities （switching from LKAU to Enterprises） as well as for timeliness （ASIA has two years of delay）. Then, the administrative local tourism registers （LTR） are analysed to understand： how many they are, their dissemination in the Italian territories, their primary purpose and source, the variables contained, the frequency of updates. This preliminary analysis is needed to identify the operative activities that Istat, together with the Intermediate Bodies, should start to use administrative archives for statistical purposes and to develop a unique tourism satellite archive （TSA）, facing many difficulties related to the reception of several LTR as well as methodological issues for record linkage. On the other hand, a TSA would lead numerous advantages： a unique and official list of internal accommodation establishments; a step towards integration of TS into FRIBS; a starting point to begin to use also administrative data produced by the Italian Police （mandatory communications on guests in the interests of public safety）, having a comparison term to assess their coverage.

Online payment fraud:from anomaly detection to risk management

Online banking fraud occurs whenever a criminal can seize accounts and transfer funds from an individual’s online bank account.Successfully preventing this requires the detection of as many fraudsters as possible,without producing too many false alarms.This is a challenge for machine learning owing to the extremely imbalanced data and complexity of fraud.In addition,classical machine learning methods must be extended,minimizing expected financial losses.Finally,fraud can only be combated systematically and economically if the risks and costs in payment channels are known.We define three models that overcome these challenges:machine learning-based fraud detection,economic optimization of machine learning results,and a risk model to predict the risk of fraud while considering countermeasures.The models were tested utilizing real data.Our machine learning model alone reduces the expected and unexpected losses in the three aggregated payment channels by 15%compared to a benchmark consisting of static if-then rules.Optimizing the machine-learning model further reduces the expected losses by 52%.These results hold with a low false positive rate of 0.4%.Thus,the risk framework of the three models is viable from a business and risk perspective.

The vertical distribution characteristics of integral turbulence statistics in the atmospheric boundary layer over an urban area in Beijing

Turbulence data(2008–2012) from a 325 m meteorological tower in Beijing, which consisted of three layers(47,140, and 280 m), was used to analyze the vertical distribution characteristics of turbulent transfer over Beijing city according to similarity theory. The conclusions were as follows.(1) Normalized standard deviations of wind speeds/ui * were plotted as a function only of a local stability parameter. The values under near-neutral conditions were 2.15, 1.61, and 1.19 at 47 m, 2.39, 1.75,and 1.21 at 140 m, and 2.51, 1.77, and 1.30 at 280 m, showing a clear increase with height. The normalized standard deviation of wind components fitted the 1/3 law under unstable stratification conditions and decreased with height under both stable and unstable conditions.(2) The normalized standard deviation of temperature fitted the.1/3 law in the free convection limit, but was quite scattered with different characteristics under near-neutral conditions. The normalized standard deviations of humidity and the CO2 concentration fitted the.1/3 law under unstable conditions, and remained constant under near-neutral and stable stratification. The normalized standard deviation of scalars, i.e., temperature, humidity, and CO2 concentration, all increased with height.(3) Compared with momentum, and the water vapor and CO2 concentrations, the turbulence correlation coefficient for heat was smaller under near-neutral conditions, but larger under both stable and unstable conditions. A dissimilarity between heat, and the water vapor and CO2 concentrations was observed in urban areas. The relative correlation coefficients between heat and each of momentum, humidity, and CO2 concentration(|rwT/ruw|, |rwT/rwc| and |rwT/ruq|) in the lower layers were always larger than in higher layers, except for the relative correlation coefficient between heat and humidity in an unstable stratification. Therefore, the ratio between heat and each of momentum, humidity, and CO2 concentration decreased with height.

Robust and Efficient Reliability Estimation for Exponential Distribution

In modeling reliability data,the exponential distribution is commonly used due to its simplicity.For estimating the parameter of the exponential distribution,classical estimators including maximum likelihood estimator represent the most commonly used method and are well known to be efficient.However,the maximum likelihood estimator is highly sensitive in the presence of contamination or outliers.In this study,a robust and efficient estimator of the exponential distribution parameter was proposed based on the probability integral transform statistic.To examine the robustness of this new estimator,asymptotic variance,breakdown point,and gross error sensitivity were derived.This new estimator offers reasonable protection against outliers besides being simple to compute.Furthermore,a simulation study was conducted to compare the performance of this new estimator with the maximum likelihood estimator,weighted likelihood estimator,and M-scale estimator in the presence of outliers.Finally,a statistical analysis of three reliability data sets was conducted to demonstrate the performance of the proposed estimator.

Development and Application of Statistical Business Register Guidelines in African Countries

Within the framework of its Statistical Capacity Building Program the African Development Bank （AfDB） is supporting development and improvement of statistical business registers （SBRs） in African countries. As a first step, the AfDB prepared a document entitled Guidelines .for Building Statistical Business Registers in Africa, which describes SBR design, construction, introduction, use and maintenance. To support dissemination, interpretation and effective use of the Guidelines, the AfDB is now sponsoring a programme of review and recommendations for enhancements to SBRs in selected African national statistical offices. The paper outlines the content of the Guidelines and experiences in their application. The views expressed are those of the authors and ,do nnt nec＇e^arilv reflect an official nosition of the AfDB.

Statistical analysis of mechanical properties of biological soft tissue under quasi-static mechanical loading

The mechanical properties of biological soft tissues are inextricably linked to the field of health care,and their mechanical properties can be important indicators for diagnosing and detecting diseases;they can also be used to analyze the causes of organ diseases from a pathological point of view and thus guide the deployment of medical solutions.As an effective method to characterize the mechanical properties of materials,mechanical loading experiments have been successfully applied to the mechanical properties of materials,including tension,compression,pure shear,and so on.Under quasi-static loading,when the material is a biological soft tissue material between a solid and an ideal fluid,its viscoelastic properties strongly respond to the force stimulus,and the stress-strain-time in the elastic phase will have obvious disturbance characteristics.Therefore,the existing statistical methods are often difficult to quantitatively describe the mechanical properties of materials.Therefore,this study proposes an Interval Capture Point based on the principle of integration.The experimental data based on this method can characterize its nonlinear mechanical properties well,especially when the loading speed is extremely low and the soft materials show strong disturbance characteristics.The proposed method can still accurately characterize the hyperelastic and viscoelastic properties of the mechanical properties of biological soft tissues under quasi-static loading.