Statistical Forecasting Research Articles

An Atmospheric Signal Lowering the Spring Predictability Barrier in Statistical ENSO Forecasts

AbstractThe loss of autocorrelations of tropical sea surface temperatures (SST) during late spring, also called the spring predictability barrier (SPB), is a factor that strongly limits the predictability of El Nino Southern Oscillation (ENSO), and especially the statistical SST‐based ENSO forecasts starting from the winter‐spring season. Recent studies show that Pacific atmospheric circulation anomalies in winter‐spring may have a long‐term impact on the summer tropical climate via the SST footprint. Here, we infer an index based on sea level pressure (SLP) data from February to March in a single area surrounding Hawaii, and show that this area is the most informative part of the large SLP pattern initiating the SST footprinting mechanism. We then construct a statistically optimal linear model of the Nino 3.4 index taking this atmospheric index as a forcing. We find that this forcing efficiently lowers the SPB and provides significant improvements of interseasonal Niño 3.4 forecasts.

Climate‐sensitivity of sugarcane yield in the southeastern Africa lowlands

AbstractWe have analysed the relationships between local and regional climate and sugarcane yield over the southeastern Africa lowlands (31°–23.5°S, 28.5°–32.5°E) for the period 1970–2017. The temporal associations for preceding December–May rainfall and temperature, and indices of the Pacific El Niño Southern Oscillation and Indian Ocean Dipole, demonstrate the climate‐sensitivity of sugarcane yield and its proxy: the Palmer Drought Severity Index (PDSI). The composite differences revealed how the atmospheric circulation over the Mozambique Channel shifts the moisture gradient over southeastern Africa. Predictors of sugarcane yield were identified in point‐to‐field maps of global sea surface temperature, sea level air pressure, and upper winds with respect to the PDSI. It was found that four climate predictors account for half of the PDSI variance at 1 year lead time. We also investigated the long‐term change using coupled model simulations. These exhibit weak drying trends but large year‐to‐year swings in soil moisture. Our research offers a basis for mitigating climate variability for the benefit of the sugar industry in southeastern Africa, through statistical forecasts that inform crop management.

Основные принципы профилактики и реабилитации основных патологий лиц старше 75 лет

J u s t i f i c a t i o n : the Current demographic situation in the country and statistical forecasts indicate an increase in the number of elderly and senile people in the total population. In most regions of Russia, the proportion of people over 75 years of age ranges from 15 to 19% of the total population of the region. According to demographers, by 2020, every fifth Russian will be over 60 years old. Patients of older age groups, on average, make up 25–30% of those who seek medical care in outpatient clinics. The level of their hospitalization and emergency medical treatment is 5 times higher than that of the rest of the population combined. O b j e c t i v e : to Substantiate and develop the principles of step-by-step rehabilitation treatment of patients after hip replacement, to develop differentiated rehabilitation complexes at the sanatorium-resort stage, depending on the timing of referral after surgical treatment, its features, age and concomitant pathology of patients. M e t h o d s : General clinical, orthopedic, goniometric, biomechanical: support reactions, dynamometric, stabilographic; functional tests and tests, questionnaires, statistical. R e s u l t s : change curve of the reference reactions, namely the reduction in force characteristics of front and rear shocks 34,6% and 37,0%, improving the power characteristics bestolkovoe period by 12,4%, and the total time of support in 2 times; decrease in the force characteristics of muscle in 2,5 times the power mm. abductor 65,2%, mm. adductor 59,6%, mm. extensor at 76,7 percent, mm. rec. femoris by 20,0%; displacement of the projection of the General center of gravity back and towards the intact limb; reduction of the volume of movements in the hip joint by 1,7 times; reduced walking speed by 1,8 times, the quality of life of patients and daily functions, which justifies the need for rehabilitation measures. C o n c l u s i o n : a basic rehabilitation complex was developed for patients after hip replacement at the early postoperative stage, which included the following activities: kinesotherapy-therapeutic gymnastics, therapeutic dosed walking with additional support, mechanical therapy, Cycling, hydrokinesotherapy, orthopedic regimen; physiotherapy.

Relationships between Wintertime Sea Ice Cover in the Barents Sea and Ocean Temperature Anomalies in the Era of Satellite Observations

AbstractInvestigation of the predictability of sea ice cover in the Barents Sea is of paramount importance since sea ice changes in this part of the Arctic not only affect local marine ecosystems and human activities but may also influence weather and climate in northern midlatitudes. Here, observational data from the period 1981–2018 are used to identify statistical linkages of wintertime sea ice cover in the Barents Sea region to preceding sea surface temperature (SST) and Atlantic Water temperature anomalies in that region. We find that the ocean temperature anomalies formed by local air–sea interactions during the winter-to-spring season are a significant source of predictability for sea ice area (SIA) in the Barents Sea region the following winter. Optimal areas for constructing SST predictors of Barents Sea SIA and skill scores from retrospective statistical forecasts are shown to differ between the periods up to and since the onset of rapid sea ice decline in the region. In the EARLY period (1982–2003), springtime SSTs in the western Barents Sea predicted 44% of the variance of the following winter Barents Sea SIA. In the LATE period (2003–17), springtime SSTs in the southern Barents Sea predicted 70% of the variance of the following winter Barents Sea SIA. Regression analysis suggests that feedbacks from anomalous winds may be important for the predictability of wintertime sea ice cover in the Barents Sea region.

Statistical Forecasts for the Occurrence of Precipitation Outperform Global Models over Northern Tropical Africa

AbstractShort‐term global ensemble predictions of rainfall currently have no skill over northern tropical Africa when compared to simple climatology‐based forecasts, even after sophisticated statistical postprocessing. Here, we demonstrate that 1‐day statistical forecasts for the probability of precipitation occurrence based on a simple logistic regression model have considerable potential for improvement. The new approach we present here relies on gridded rainfall estimates from the Tropical Rainfall Measuring Mission for July‐September 1998–2017 and uses rainfall amounts from the pixels that show the highest positive and negative correlations on the previous two days as input. Forecasts using this model are reliable and have a higher resolution and better skill than climatology‐based forecasts. The good performance is related to westward propagating African easterly waves and embedded mesoscale convective systems. The statistical model is outmatched by the postprocessed dynamical forecast in the dry outer tropics only, where extratropical influences are important.

Markov Chain Monte Carlo simulation and regression approach guided by El Niño–Southern Oscillation to model the tropical cyclone occurrence over the Bay of Bengal

Tropical cyclone (TC) is one of the most devastating weather systems that causes enormous loss of life and property in the coastal regions of Bay of Bengal (BoB). Statistical forecasting of TC occurrence can help decision-makers and inhabitants in shoreline zones to take necessary planning and actions in advance. In this study, we have investigated the impact of El Nino–Southern Oscillation (ENSO) on the frequency of TC over the BoB by using 100 years TC and Southern Oscillation Index data. The frequency of TC is approximated through observation and Markov Chain Monte Carlo (MCMC) simulation. Two-sample Student’s t test has been applied for examining the statistical significance where the results are significant at 5% level for all cyclonic disturbances. The monthly and seasonal distribution show this feature more distinctly. The total annual frequency of depressions and cyclonic storms in El Nino and La Nina conditions does not differ much, but the monthly/seasonal distribution shows high differences for certain months and seasons. The simulated frequency of TC landfall using MCMC matches well with the observation. The proposed methodology is illustrated through a case study in BoB rim countries-Bangladesh, India, Sri Lanka and Myanmar. Poisson and Bayesian regression have also been used to predict the probabilities of TC frequency over the BoB. Both the regression approaches show 10 and 32% improvement than climatology for the forecast and cross-validation skill respectively. We have also analyzed TC impact over Bangladesh as a case study. Possible links of the variation of TC activities with the largescale geographical distribution of sea surface temperature, vertical wind shear, vorticity, moisture and relative humidity are also explored.

Development of Forest Shelterbelts Considering Statistical Forecasts Modelling of Local Weather

This work aims to study the effect of high temperatures and phytopathogenic bacteria on different types of trees in the forest shelterbelts. Therefore, in 2018, 17 tree species were studied from 50 sample sites in the Moscow oblast (Russia). Leaf scorching, diseases caused by phytopathogenic bacteria, and heat damage to the crowns were examined in 5224 tree species. Based on the degree of crown damage, the studied tree species were divided into four classes. It was found that the heat damage to tree crowns was identical between the three sampling aspects (correlation coefficient 0.99). The plant species composition must be considered when developing forest shelterbelts. A long-term forecast on structural changes of planted areas is possible, considering the species composition and climatic characteristics of the region. Class 5 includes only chestnut; class 4 includes three species; class 3 is represented by seven species. Class 2, includes six species, and is the most suitable in developing forest plantations. No tree species in class 1 were found (trees with no damage). There is a connection between pathologies and heat injuries in trees from classes 4 to 5 (correlation 0.89).

Probability assessments of an ice-free Arctic: Comparing statistical and climate model projections

The downward trend in the amount of Arctic sea ice has a wide range of environmental and economic consequences including important effects on the pace and intensity of global climate change. Based on several decades of satellite data, we provide statistical forecasts of Arctic sea ice extent during the rest of this century. The best fitting statistical model indicates that overall sea ice coverage is declining at an increasing rate. By contrast, average projections from the CMIP5 global climate models foresee a gradual slowing of Arctic sea ice loss even in scenarios with high carbon emissions. Our long-range statistical projections also deliver probability assessments of the timing of an ice-free Arctic. These results indicate almost a 60 percent chance of an effectively ice-free Arctic Ocean sometime during the 2030s — much earlier than the average projection from the global climate models.

Comparing actual and forecasted numbers of unique patients dispensed select medications for opioid use disorder, opioid overdose reversal, and mental health, during the COVID-19 pandemic, United States, January 2019 to May 2020

BackgroundCOVID-19 community mitigation measures (e.g., stay-at-home orders) may worsen mental health and substance use-related harms such as opioid use disorder and overdose and limit access to medications for these conditions. We used nationally-representative data to assess dispensing of select substance use and mental health medications during the pandemic in the U.S. MethodsIQVIA Total Patient Tracker data were used to calculate U.S. monthly numbers of unique patients dispensed buprenorphine, extended-release (ER) intramuscular naltrexone, naloxone, selective serotonin or serotonin-norepinephrine reuptake inhibitors, benzodiazepines, and for comparison, HMG-CoA reductase inhibitors (statins) and angiotensin receptor blockers (ARBs) between January 2019-May 2020. Forecasted estimates of number of unique patients dispensed medications, generated by exponential smoothing statistical forecasting, were compared to actual numbers of patients by month to examine access during mitigation measures (March 2020-May 2020). ResultsBetween March 2020-May 2020, numbers of unique patients dispensed buprenorphine and numbers dispensed naloxone were within forecasted estimates. Numbers dispensed ER intramuscular naltrexone were significantly below forecasted estimates in March 2020 (-1039; 95 %CI:-1528 to -550), April 2020 (-2139; 95 %CI:-2629 to -1650), and May 2020 (-2498; 95 %CI:-2987 to -2009). Numbers dispensed antidepressants and benzodiazepines were significantly above forecasted estimates in March 2020 (977,063; 95 %CI:351,384 to 1,602,743 and 450,074; 95 % CI:189,999 to 710,149 additional patients, respectively), but were within forecasted estimates in April 2020-May 2020. Dispensing patterns for statins and ARBs were similar to those for antidepressants and benzodiazepines. ConclusionsOngoing concerns about the impact of the COVID-19 pandemic on substance use and mental health underscore the need for innovative strategies to facilitate continued access to treatment.

The Complementarity Between Man and Machine in Forecasting

This paper quantifies the amount of noise and bias in analysts’ forecast of corporate earnings at various horizons. We first show analyst forecasts outperform statistical forecasts at short-horizons, but underperform at longer horizons. We next decompose the relative accuracy of these forecasts into three components: (i) noise, (ii) bias and (iii) analysts’ information advantage over statistical forecasts. We find the information advantage is constant across forecasting horizons, while both noise and bias are increase linearly. We then show most existing models lack a mechanism to account for these facts. To generate such a mechanism, we consider a parsimonious variant of the model of Patton and Timmermann (2010) with a noisy cognitive default and show it quantitatively fits the data. The intuition underlying this model is that forecasters rely on their biased and noisy defaults more at longer horizons, as rational forecasts are less accurate. This model also quantitatively matches two non-targeted empirical relationships: (i) analyst disagreement increases with horizon and (ii) noise is an increasing function of volatility. Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.

Noise in Expectations: Evidence from Analyst Forecasts

This paper quantifies the amount of noise and bias in analysts’ forecast of corporate earnings at various horizons. We first show analyst forecasts outperform statistical forecasts at short-horizons, but underperform at longer horizons. We next decompose the relative accuracy of these forecasts into three components: (i) noise, (ii) bias and (iii) analysts’ information advantage over statistical forecasts. We find the information advantage is constant across forecasting horizons, while both noise and bias are increase linearly. We then show most existing models lack a mechanism to account for these facts. To generate such a mechanism, we consider a parsimonious variant of the model of Patton and Timmermann (2010) with a noisy cognitive default and show it quantitatively fits the data. The intuition underlying this model is that forecasters rely on their biased and noisy defaults more at longer horizons, as rational forecasts are less accurate. This model also quantitatively matches two non-targeted empirical relationships: (i) analyst disagreement increases with horizon and (ii) noise is an increasing function of volatility.

Employment and Stability due to Innovations: a Look at Russia

Abstract The high rates of the scientific and technical process have made significant adjustments to the methods for assessing the country’s GDP, labor productivity, and the number of the economically active population. Industry 4.0 has fundamentally changed the structure of the labor market and employment of the population in all countries, presenting new requirements for employers and employees. The use of self-driving vehicles, robots, automation of most business processes in various sectors of the national economy significantly increases labor productivity, ensures GDP growth, and reduces employment. Industry 4.0 makes available new, digital formats for continuous professional development, making it possible to adapt educational content to personnel and enterprise management quickly. A mathematical model was developed to predict the significant indicators of the economy and the labor market. It is a linear equation system that, given the initial conditions, provides the formation of various forecast scenarios. The results of computational experiments on calculating labor productivity, changes in the number of employees and earnings, as well as the number of the economically active population of the Russian Federation in 2021-2035, are presented. The calculations were carried out for three main combinations: a) changes in GDP; b) changes in labor productivity c) changes in numbers. The research’s information base is the state statistical sources and forecasts both in general and individual enterprises.

Comprehensive analysis of sustainable development of the countries of the Eurasian Economic Union

Research background: the economies of the member states of the Eurasian Economic Union are of a raw material nature, therefore they have a large carbon footprint in their products and serious environmental problems. This complicates the transition to sustainable development, which presupposes the coordinated development of the economy, ecology and social sphere. Purpose of the article: based on the analysis of the system of indicators of the effectiveness of sustainable development, identify the existing problems of the EAEU countries and propose a system of measures to resolve them. Methods: the study analyzed the literature on sustainable development, studied and analyzed strategies for the transition to sustainable development of the EAEU countries, used statistical analytical reports and forecasts of the main indicators of sustainable development presented on the websites of the UN, the Eurasian Economic Commission, the World Data Atlas “Knoema”, Yale Center for Environmental Law and Policy, Boston Consulting Group. Findings: An assessment of the indicators of the sustainability of development of the EAEU member states was carried out, an analysis of their policies within the framework of the Paris Agreement was given. The conclusion is made about the decrease in the efficiency of the rational use of ecosystems and natural resources in the EAEU countries, the growth of environmental problems. This hinders the progress of the EAEU countries along the path of sustainable development. The need for the formation of a unified supranational environmental legislation within the EAEU has been proved.

Rare earth elements in deposited hard coal fly ash in Poland

Rare Earth Elements (REEs), due to their unique properties, are nowadays a desirable raw material, especially in the development of modern technologies. This paper describes a 4-step research methodology for the task of identifying the potential for REE recovery in landfilled fly ash. A literature analysis was performed on their significance, occurrence in both primary and secondary deposits. Opportunities for REE recovery from coal fly ash in conventional power plants were identified and selected technologies were described. Poland, as a country whose energy sector is to a large extent based on coal, has a potential in this respect. Taking into account studies of the Polish Central Statistical Office (GUS) and forecasts of the Polish energy policy, the article determines the approximate value of REE in the waste stream from coal-fired power plants burning hard coal.

The Improvement of Forecasting Accuracy Egyption Tourism Demand Using Combining Statistical and Judgmental Forecasts

The Improvement of Forecasting Accuracy Egyption Tourism Demand Using Combining Statistical and Judgmental Forecasts

Macroeconomic performance of the Czech Republic during the global pandemic crisis

Research background: The global SARS-CoV-2 pandemic is unprecedented for human society. Despite the continuing uncertainty about the future, it is certain that the global consequences of the pandemic will have many dimensions. Among others, the economic impacts are extremely significant. However, the sudden slowdown in economic activity, the declared quarantines, and the state of emergency have many specific impacts in individual countries. The Czech economy (as well as other countries in the world) was exposed to an unexpected exogenous shock. The data confirm that, in 2020, the decline in the performance of the Czech economy was the deepest in its history. Purpose of the article: The primary goal of this article is to analyze the macroeconomic performance of the Czech Republic during a pandemic crisis. However, we also research the impact of the pandemic on individual sectors of the national economy in the context of government measures. Methods: The analytical part of the article is processed on the basis of publicly available statistical data, economic analyses, and economic forecasts of renowned institutions. The derivation and argumentation of the conclusions are based on an empiric-inductive approach, methods of synthesis, and comparison. Findings and value added: The article maps the direct and mediated macroeconomic effects of the pandemic crisis in the reality of the Czech Republic. At the theoretical level, the aim of the article is to bring new knowledge to current economic theory, especially in the field of macroeconomics and sectoral analysis as well as the theory of public choice.

ОСНОВНЫЕ НАПРАВЛЕНИЯ РЕШЕНИЯ НАУЧНОЙ ПРОБЛЕМЫ ФОРМИРОВАНИЯ И ОЦЕНКИ СТОИМОСТИ ПРОФЕССИОНАЛЬНОГО ПОРТФЕЛЯ АРЕНДНОГО ЖИЛЬЯ

The article presents a comparative fundamental and statistical analysis and forecast of the professional rental housing segment development in Russia. According to the authors, the rental housing market development and the growth of its capitalization will lead to the reduction of system risks of the Russian market by limiting the volatility of housing market prices. Thus, the development of professional rental business, including companies with state participation, may become a promising direction in the new institutional environment. After researching factors that limit the development of the professional rental housing and evaluation of the influence of rental business on the housing markets, the authors make some proposals for stimulating rental segment of the market. Development of the professional rental business requires solving such scientific problems in the sphere of evaluation of housing development projects and financial management of economic entities’ as: theoretical substantiation of approaches to form and evaluate rental housing value, development of methodological tools and practical recommendations on value management of rental housing projects portfolio.

Electricity price forecasting on electricity spot market: a case study based on the Brazilian Difference Settlement Price

Developing predictive models is a complex task since it deals with the uncertainty and the stochastic behavior of variables. Specifically concerning commodities, accurately predicting their future prices allows us to minimize risks and establish more reliable decision support mechanisms. Although the discussion on this question is extensive, there is academic attention being paid to the construction of nonparametric models applied to energy markets, as they have presented promising predictive results, what justifies the present study. This paper applies classical statistical models and Dynamic Time Scan Forecasting (DTSF) to the short-term electricity market prices, in Brazil, from 2006 to 2019. DTSF consists of scanning a time series and then identifying past patterns (so-called “matches”), similar to the last available observations. We predict Brazilian electricity spot prices, according the most similar matches, using aggregation functions, such as median. Recent research on the electricity spot market is increasing, indicating research significance. Our predictive approach exhibited greater accuracy than seminal statistical models. Our approach was designed for a high frequency series. Its predictive performance remained robust when other models presented both high predictive errors (spring), as well as when those models are highly accurate (winter). For future research, we recommend a more finely-tune study on DTSF parameters.

Economic cycle and economic consequences of the global SARS-CoV-2 pandemic in the Czech Republic

Research background: The global SARS-CoV-2 pandemic is for human society unprecedented. Coronavirus is dramatically changing people’s lives, and despite of uncertainty about the future, it is certain that its global consequences will have many dimensions. The it is undeniable that there have been significant economic impacts are unquestionable today impacts. The Czech economy, like the rest of the world, is facing an unexpected exogenous shock. This being manifests itself with varying intensity both at the level of sub-markets and on the side of aggregate supply and demand. It is literally a textbook example, explaining the outbreak of the downturn phase of the business cycle. Nevertheless, the sudden slowdown of economic activity as a result of the coronavirus pandemic, quarantine and the state of emergency, has many specificities across countries. Purpose of the article: The primary goal of this article is to analyze the economic consequences of the pandemic crisis in the reality of the Czech Republic. On this basis, it identifies the specifics of a pandemic crisis, in the context of a broader framework of economic theories of business cycles. Methods: The analytical part of the article is processed based on publicly available statistical data and economic forecasts. The derivation and argumentation of the conclusions is based on an empiric-inductive approach, methods of synthesis and comparison. Findings & Value added: The article maps the business direct and mediated economic contexts of the economic cycle caused by the coronavirus pandemic in the reality of the Czech Republic. It identifies the differences and specifics of the downward phase of the pandemic business cycle and derives their possible long-term impacts. At the theoretical level, the ambition of the article is to bring new knowledge to the contemporary economic theory of business cycles.

APPLICATION OF PREDICATIVE-REDEFINABLE STRUCTURES FOR MODELING A VARIATIVE DEVELOPMENT OF BIOLOGICAL PROCESSES

In the article we considered a new original method of organizing hybrid computing structures for simulating abrupt changes in controlled natural processes and analyzing extreme environmental phenomena. Our Method uses systems of differential equations on adjacent intervals of hybrid time with a dynamically redefined right-hand side at special moments – events. Transition conditions for such events are obtained by calculating the equations for additional characteristics. Threshold states in the dynamics of the process become a consequence of the inclusion of trigger functions. Their values on the right-hand side specifically differ from neutral only in narrow space ranges of the changing characteristics of the hybrid system, for example, initial conditions. The limits of the functions and their range of values proceed from the essence of the nonlinear effects of the biosystem we are modeling under this effect. The approach allows realizing current qualitative changes in control scenarios – such as bifurcations or the boundary crisis of an attractor. The author has investigated computational scenarios for such different processes as the collapse of fish stocks in the case of the Northern Atlantic cod and rapid outbreak of the forest pests in Australia. The outbreak of insects in the hybrid model ends spontaneously with the threshold for the exhaustion of forest resources, with a transition to ordinary for the environent fluctuations of the pest. The practical novelty of our modeling of the outbreak of pests is that extreme phenomenon in the script ends spontaneously according to the internal logic of the process. In this method, we do not need to include a change in parameters from external factors that causes a stop in reproductive activity. Similarly, the epidemic of viruses ends in the formation of collective immunity. The functions of the trigger action will allow targeted bifurcation and change the position of the extremes of dependence. The method is successfully applied to the analysis of situations of collapse of biological resources – quick and unexpected degradation of fish stocks for specialists, which is not replaced by restoration contrary to statistical forecasts. The technique is further generalized to describe a wide range of extreme processes with changes in biological systems.