Time Series Research Research Articles

Improving osteoarthritis management in primary healthcare: results from a quasi-experimental study

BackgroundTo improve quality of care for patients with hip and knee osteoarthritis (OA), general practitioners (GPs) and physiotherapists (PTs) in a Norwegian municipality initiated an intervention. The intervention aimed to increase provision of core OA treatment (information, exercise, and weight control) prior to referral for surgery, rational use of imaging for assessing OA and improve communication between healthcare professionals. This study assessed the effectiveness of this intervention.MethodsForty-eight PTs and one hundred one GPs were invited to the intervention that included two interactive workshops outlining best practice and an accompanying template for PT discharge reports. Using interrupted time series research design, the study period was divided into three: pre-implementation, transition (implementation) and post-implementation. Comparing the change between pre- and post-implementation, the primary outcome was patient-reported quality of OA care measured with the OsteoArthritis Quality Indicator questionnaire. Secondary outcomes were number of PT discharge reports, information included in GP referral letters to orthopaedic surgeon, the proportion of GP referral letters indicating use of core treatment, and the use of imaging within OA assessment. Analyses involved linear mixed and logistic regression models.ResultsThe PT workshop had 30 attendees, and 31 PTs and 33 GPs attended the multidisciplinary workshop. Two hundred eight and one hundred twenty-five patients completed the questionnaire during pre- and post-implementation, respectively. The adjusted model showed a small, statistically non-significant, increase in mean total score for quality of OA care (mean change = 4.96, 95% CI -0.18, 10.12, p:0.057), which was mainly related to items on OA core treatment. Patients had higher odds of reporting receipt of information on treatment alternatives (odds ratio (OR) 1.9, 95% CI 1.08, 3.24) and on self-management (OR 2.4, 95% CI 1.33, 4.32) in the post-implementation phase. There was a small, statistically non-significant, increase in the proportion of GP referral letters indicating prior use of core treatment modalities. There were negligible changes in the number of PT discharge reports, in the information included in the GP referral letters, and in the use of imaging for OA assessment.ConclusionThis study suggests that a primary care intervention including two inter-active workshops can shift the quality of care towards best practice recommendations.Trial registrationClinicalTrials.gov: NCT02876120.

A Neural Networks Based Method for Multivariate Time-Series Forecasting

In recent years, more and more deep neural network methods have been used in the forecasting research of multivariate time series. Comparing to the traditional methods such as autoregressive models, methods based on neural networks have achieved superior results. However, the sequence data comes from all aspects, and the data contains long-term and short-term models, which is not a small challenge for data prediction research. We builds a model based on a deep neural network, and uses a convolutional network and a recurrent network in the long-term sequence data input and short-term sequence data input of the model. Convolutional networks are mainly used to extract short-term patterns in sequence data, and recurrent networks are mainly used to extract long-term patterns in sequence data. In addition, in order to solve the problem that the output of the neural network is not sensitive to the change of the input scale, we also added an autoregressive network to the model. When constructing the input of the model, we use the corresponding period characteristics to construct the two input of the model for different datasets: long-term historical data and short-term historical data. Our model has achieved better results than traditional prediction models on four public data sets: out of 32 indicators in 8 methods, 24 optimal results have been achieved.

Forecast Methods for Time Series Data: A Survey

Research on forecasting methods of time series data has become one of the hot spots. More and more time series data are produced in various fields. It provides data for the research of time series analysis method, and promotes the development of time series research. Due to the generation of highly complex and large-scale time series data, the construction of forecasting models for time series data brings greater challenges. The main challenges of time series modeling are high complexity of time series data, low accuracy and poor generalization ability of prediction model. This paper attempts to cover the existing modeling methods for time series data and classify them. In addition, we make comparisons between different methods and list some potential directions for time series forecasting.

The stage-specific long non-coding RNAs and mRNAs identification and analysis during early development of common carp, Cyprinus carpio

Cyprinus carpio is considered an alternative vertebrate fish model to zebrafish. However, systemic times-series research on the lncRNAs and mRNAs during early development of C. carpio has not been reported yet. This study provides the first long non-coding RNA (lncRNA)-mRNA expression profiles during six main early development stages (2 h post-fertilization hpf, 6 hpf, 12 hpf, 20 hpf, 64 hpf and 1 day post-hatching). A total of 51,979 lncRNAs were identified. We screened the top 10 abundance lncRNAs and mRNAs and stage-specific lncRNAs and mRNAs (specificity measure SPM > 0.9). We identified significant differentially expressed lncRNAs and mRNAs (|log2 (fold change)| ≥ 1 and false discovery rate FDR of <0.05). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis identified numerous signaling pathways. Additionally, the lncRNA-mRNA co-regulated network analysis of two lncRNAs (lncrps25 and malat1) and two mRNAs (mitf and troponin T) were investigated. Our results provide new insight into the role of lncRNAs and mRNAs, and would advance the understanding of lncRNA-mediated mechanisms in early development of fish.

Evaluation of Test Statistics for Detection of Outliers and Shifts

Existence of outliers and structural breaks having mutually unknown nature, in time series data, offer challenges to data analysts in model identification, estimation and validation. Detection of these outliers has been an important area of research in time series since long. To analyze the impact of these structural breaks and outliers on model identification, estimation and their inferential analysis, we use two data generating processes: MA(1) and ARMA(1,1). The performance of the test statistics for detecting additive outlier(AO), innovative outlier(IO), level shift(LS) and transient change(TC) is investigated using simulation strategy through power of a test, empirical level of significance, empirical critical values, misspecification frequencies and sampling distribution of estimators for the two models. The empirical critical values are found higher than the theoretical cut-off points, empirical power of the test statistics is not satisfactory for small sample size, large cut-off points and large model coefficient. We have explored confusion between LS, AO, TC and IO at different critical values(c) by varying sample size. We have also collected empirical evidence from time series data for Pakistan using 3-stage iterative procedure to detect multiple outliers and structural breaks. We find that neglecting shocks lead to wrong identification, biased estimation and excess kurtosis.&#x0D; JEL Classification Codes: C15, C18, C63, C32, C87, C51, C52, C82&#x0D; AMS Classification Codes: 62, 65, 91, DI, 62-08, 62J20, 00A72, 91-08, 91-10, 91-11 62P20, 91B82, 91B84, 62M07, 62M09, 62M10, 62M15, 62M20

INFLUENCE OF MANAGERIAL ABILITY ON FINANCIAL REPORTING QUALITY: EVIDENCE FROM NIGERIAN LISTED NON-FINANCIAL FIRMS

Users of accounting information crave of quality financial reporting, by emphasising on the quality of the auditors neglecting the attribute of the managers. This study investigates the influence of managerial abilities on financial reporting in Nigerian listed non-financial sectors. The time series research design was employed by selecting 40 non-financial institutions as sample size between 2010 and 2017. Secondary data obtained from the financial report were analysed using correlation and logistic regression. It was found that managerial ability has an inverse relationship on financial reporting quality, which is consistent with the agency theory. The finding implied that managers employ their ability to income smoothing for the benefit of the organisation rather than the interest of the shareholders.

A survey of time series forecasting from stochastic method to soft computing

Forecasting is a part of statistical modelling that is widely used in various fields because of its benefits in decision-making. The purpose of forecasting is to predict the future values of certain variables that vary with time using its previous values. Forecasting is related to the formation of models and methods that can be used to produce a good forecast. This research is a survey paper research that used a systematic mapping study and systematic literature review. Generally, time series research uses linear time series models, specifically the autoregressive integrated moving average model that has long been used because it has good forecasting accuracy. The successfulness of the Box–Jenkins methodology is based on the reality that various models can imitate the behaviour of various types of series, usually without requiring many parameters to be estimated in the final choice of the model. However, the assumption of stationarity that must be met makes this method inflexible to use. With the advances in computers, forecasting methods from stochastic models to soft computing continue to develop and extend. Soft computing for forecasting can provide more accurate results than traditional methods. Moreover, soft computing has many advantages in terms of the amount of data that can be analysed and the time- and cost-effectiveness of the process.

Landsat-Based Estimation of the Glacier Surface Temperature of Hailuogou Glacier, Southeastern Tibetan Plateau, Between 1990 and 2018

Glacier surface temperature (GST) is influenced by both the energy flux from the atmosphere above and the thermal dynamics at the ice–water–debris interfaces. However, previous studies on GST are inadequate in time series research and mountain glacier surface temperature retrieval. We evaluate the GST variability at Hailuogou glacier, a temperate glacier located in Southeastern Tibetan Plateau, from 1990 to 2018. We utilized a modified mono-window algorithm to calculate the GST using the Landsat 8 thermal infrared sensor (TIRS) band 10 data and Landsat 5 thematic mapper (TM) band 6 data. Three essential parameters, including the emissivity of ice and snow, atmospheric transmittance, and effective mean atmospheric temperature, were employed in the GST algorithm. The remotely-sensed temperatures were compared with two other single-channel algorithms to validate GST algorithm’s accuracy. Results from different algorithms showed a good agreement, with a mean difference of about 0.6 ℃. Our results showed that the GST of the Hailuogou glacier, both in the upper debris-free part and the lower debris-covered tongue, has experienced a slightly increasing trend at a rate of 0.054 ℃ a−1 during the past decades. Atmospheric warming, expanding debris cover in the lower part, and a darkening debris-free accumulation area are the main causes of the warming of the glacier surface.

Effectiveness of Mobile Learning Media on Computer Assembly at Vocational High School

The purpose of this study was to determine the effectiveness of mobile learning media in computer assembly subjects in vocational high schools. Previously this media had been declared valid by media experts and material experts, which was then used by students. The research method used in this study is quasi-experimental, with time-series research design. Data collection techniques with pretest and posttest. The effectiveness obtained from the results of the post-test seen from classical completeness, all students declared complete and through the gain score in the medium category. Based on the findings of this study it was concluded that the mobile learning media is effective to be used as a learning media and increase the learning outcomes. This research recommends to be tested more broadly and to provide more complete content for the sake of improvement in the development of this mobile learning media.

HOSPITAL MORBIDITY AND COLORECTAL CANCER MORTALITY: IMPLICATIONS FOR PUBLIC HEALTH IN BRAZIL.

Colorectal cancer is a serious public health problem and one of the most common cancer worldwide. Countries around the world have shown different trends. While incidence and mortality rates for colorectal cancer are on an upward trend in developing countries, these rates have been on a downward trend in most developed countries. To analyze the temporal trend of morbimortality by colorectal cancer in Brazil between 2002 and 2016. Descriptive, time series research. Data were extracted from the national information systems for hospitalizations and deaths of the respective years. There were increasing trends in hospital morbidity and mortality from colorectal cancer in all regions of the country, with the very elderly individuals dying at a higher rate. Women (52.1%) were more affected than men, but death rates were higher for males aged 60 years or more. Regional disparities were evident, with almost 80% of deaths occurring in the South and Southeast, with the largest annual increase in the South and the lowest in the North. Regarding hospitalization, South and Southeast presented higher annual growths. These data add knowledge about the profile of public hospitalizations and deaths, reaffirming that colorectal cancer contributes to an important burden of disease and mortality in Brazil. These elements have implications for the review of colorectal cancer prevention and control strategies, as well as for public health investments.

Effectiveness of Health Counselling on Self-care Practices among Chronic Kidney Disease Patients Undergoing Hemodialysis: A Qausi Experimental Study

Background: Kidneys are the organs that perform various functions to clean the blood and remove excess water from the body and help in maintaining the chemical balance in our body. Chronic Kidney Disease (CKD) occurs when the kidneys are mutilated or cannot clean blood as healthy kidneys. Hemodialysis is done to remove waste electrolytes from blood. Methodology: Quasi experimental time series research design was used to evaluate the effectiveness of health counselling on self-care practices among CKD patients undergoing hemodialysis in selected hospital of Dehradun, Uttarakhand. Simple Random Sampling was used to select total 68 CKD patients who were undergoing hemodialysis. A Structured practice checklist regarding self-care practice containing 38 items was administered to collect the data. Health counselling was given after pretest on day 1st followed by post test on 7th, 15th and 30th day. Result: The health counselling on self-care practices of CKD Patients undergoing Hemodialysis was significantly effective in improving self-care practices as mean of self-care practices score of study participants at pre-test, on 7th day, 15th day and 30th day after intervention. There was significant increase in the self-care practices of study participant, repeated measure ANOVA showed F value was 97 and p value was 0.000. This showed that there was significant improvement in self-care practice, therefore the health counselling was effective. Conclusion: The study concluded that if health care professionals collaborate and identify the needs of CKD Patients undergoing hemodialysis and provide them health counselling regarding self-care practices, they will have better self-care practices

Association between air pollutants and outpatient and emergency hospital visits for childhood asthma in Shenyang city of China.

Effects of air pollution on asthma vary in different study areas, and long-term time series research on the effects of air pollution on asthma outpatients and emergency hospital visits has not been conducted in Northeast China. We assessed the impact of air pollutants on the risk of asthma outpatients and emergency hospital visits in Shenyang, China. A distributed lag non-linear model with a Poisson regression was used to assess the short-term effects of air pollutants on asthma outpatient and emergency hospital visits between January 1, 2013 and December 31, 2017. Confounding factors were adjusted using natural cubic splines. Ozone (O3), carbon monoxide (CO), and suspended particulates < 10μm in aerodynamic diameter (PM10) were positively associated with the number of asthma hospital visits. The largest cumulative effects of O3, CO, and PM10 on hospital visits were on lag day 2 (RR = 1.163, 95% CI 1.051-1.287) for 0-5-year-old childhood asthma, on lag day 3 (RR = 1.386, 95% CI 1.136-1.69) for asthma in winter, and on lag day 10 (RR = 1.148, 95% CI 0.942-1.399) for female asthma, respectively. The cumulative effect of air pollution represented by the air quality index (AQI) was largest on lag day 10 for 0-5-year-old childhood asthma with an increase of 28.6% (95% CI 6.5-55.4) hospital visits every IQR increment of the AQI. CO, O3, and PM10 were the main air pollutants in Shenyang city. Children with bronchitis asthma were more vulnerable to air pollution during the cold season.

Public Expenditure Shocks and Human Capital Development in the Presence of Structural Breaks: Evidence from Nigeria

The study examines the impact of public expenditure shocks on human capital development in in the Presence of Structural Breaks: Evidence from Nigeria. The nature of this study necessitates the use of a time–series research design and an extensive reliance on secondary data sourced from the Central Bank of Nigeria (CBN) statistical bulletins, for the period 1981-2018. The method of data analysis utilized a battery of econometric applications often used in most contemporary economic time-series studies. First, the descriptive and correlation analysis is presented. After that the Augmented Dickey Fuller (ADF) unit root test and Zivot and Andrews Unit root for structural breaks is applied and this is followed by the co-integration test both with and without structural breaks. The Wald test for significance of the structural breaks was also employed and then the Variance Autoregressive (VAR) technique is then utilized. Finally, the impulse-response functions is conducted The study findings reveal that response of HCAP to innovations in HEXP is shown to exhibit oscillations over the period horizon with initial declines showing in the 1st quarter after the shock. An immediate rebound in HCAP response is observed beginning from the 2nd quarter after the shock and this positive rebound is sustained up to 10th quarter after the shock. However, one standard deviation shocks to EDEXP is seen to have immediate positive effects on HCAP lasting till 2-3 quarters after the shock and then followed by a decline sustained at a little below the baseline and declining further in the 7th quarter but again we see a slight rebound which reverts. On the overall, the shocks shows high potentials for asymptotic convergence and stability in HCAP. However, the response of HCAP to investment shocks is the most destabilizing. Furthermore, we observe that the impulse response functions are robust to structural breaks. The evidence of structural breaks reveals few instances of variations with the main analysis without breaks especially in relation the public expenditure. The result shows that, with the inclusion of breaks, the sustained positive effect in HCAP of a one standard deviation shock in HEXP is still observed and also sustained up to 10th quarter after the shock. Again just like in the case of no structural breaks, we also find that the shocks in EDEXP shows high potentials for asymptotic convergence and stability in the response of HCAP but in the case of investment, we find some differences in the response of HCAP comparing with and without structural breaks. The study recommends that need for government to ensure efficiency in public expenditures.

TraceHub - A Platform to Bridge the Gap between State-of-the-Art Time-Series Analytics and Datasets

In this paper, we present TraceHub - a platform that connects new non-trivial state-of-the-art time-series analytics with datasets from different domains. Analytics owners can run their insights on new datasets in an automated setting to find insight's potential and improve it. Dataset owners can find all possible types of non-trivial insights based on latest research. We provide a plug-n-play system as a set of Dataset, Transformer pipeline, and Analytics APIs for both kinds of users. We show a usefulness measure of generated insights across various types of analytics in the system. We believe that this platform can be used to bridge the gap between time-series analytics and datasets by significantly reducing the time to find the true potential of budding time-series research and improving on it faster.

Effect of neural mobilization on pain level changes among myogenic low back pain patients

Low back pain is pain syndrome that occurs in lower back region which result of various causes due to wrong body position and repetitive motion. Neural mobilization is physiotherapy modality that aims to improve the neural tissue mobility (intraneural) and movement on the neural surface (extraneural). The study aims to determine the effect of neural mobilization toward changes in pain level among Myogenic low back pain patients. The study was used quasi experimental with experimental time series research design. The study was conducted at Bitung Hospital from April to May 2017. The samples were 20 patients who met the inclusion criteria. The paired t-test obtained pre-test and post-test with 3 times treatment was p=0.000 and pre-test and post-test with 6 times treatment had obtained p=0.000. These results suggested both 3 times and 6 times of treatment had an effect on the pain level. Mean of pre-test was 67.35, mean of post-test of 3 times treatments was 58.15 and mean of post-test with 6 times treatment was 45.75. Difference mean of pre-test and post-test with 3 times treatment was 9.2 and different mean of 3 times and 6 times treatment was 12.4. This study showed higher frequency of neural mobilization, decrease in the pain level which more significant for patients with low back pain.

Forecasting model selection using intermediate classification: Application to MonarchFx corporation

Organizations rely on accurate demand forecasts to make production and ordering decisions in a variety of supply chain positions. Significant research in time series forecasting techniques and a variety of forecasting methods are available in the market. However, selecting the most accurate forecasting model for a given time series has become a complicated decision. Prior studies of forecasting methods have used either in-sample or out-of-sample performance as the basis for model selection procedures, but typically fail to incorporate both in their decision-making framework. In this research, we develop an expert system for time series forecasting model selection, using both relative in-sample performance and out-of-sample performance simultaneously to train classifiers. These classifiers are employed to automatically select the best performing forecasting model without the need for decision-maker intervention. The new model selection scheme bridges the gap between using in-sample and out-of-sample performance separately. The best performing model on the validation set is not necessarily selected by the expert system, since both in-sample and out-of-sample information are essential in the selection process. The performance of the proposed expert system is tested using the monthly dataset from the M3-Competition, and the results demonstrate an overall minimum of 20% improvement in the optimality gap comparing to the train/validation method. The new forecasting expert system is also applied to a real case study dataset obtained from MonarchFx (a distributed logistics solutions provider). This result demonstrates a robust predictive capability with lower mean squared errors, which allows organizations to achieve a higher level of accuracy in demand forecasts.

Research on power quality prediction of fluctuating load

With the development of intelligent distribution network, power quality prediction is becoming more and more important. In this paper, the power quality prediction methods are studied and applied to a power grid. Firstly, on the basis of time series research, two mathematical models of ARIMA and BP neural network are derived and analyzed, and the corresponding power quality data prediction models are established. Then, the two models are applied to two datasets of different sizes to test and analyze their predictive effects. Based on the analysis and comparison of the prediction results, the improvement direction to further improve the prediction accuracy of the method is proposed.

POVERTY AND CLIMATE CHANGE IN THE NIGER DELTA 2013-2018

This paper set out to examine the nexus between poverty and climate change in the Niger Delta. Based on the theory of Social Production and Time-Series research design, it found out that, the Niger Delta is bedridden by endemic poverty and that has entrenched certain practices that cause environmental degradation. The foregoing has made the attainment of sustainable development appear vague thereby worsening the impact of climate change in the region. Thus, the paper recommended that government should make concerted efforts toward the implementation of poverty reduction programmes in the region as there is a strong nexus between poverty reduction, environmental sustainability and climate change.

RETRACTED ARTICLE: Prediction research of financial time series based on deep learning

Currently, the world economics develops rapidly, and the finance business also develops promptly. As there are more financial activities, the uncertainty of change trend in financial activities is also increased constantly. How to study and grasp the laws of banking activity and calculate their coming tendency has grown into the concentrate and major study substance of scientific and monetary ring. On the one hand, available finance prediction can supply base for making finance plans and relevant decisions, thus ensuring the laudable expansion of the finance market and maximizing the benefits of profit organizations. However, on the other hand, convolution neural network (CNN) is a multilayer neural network composition that can simulate the operation machine-made of biological field system, which can be used to obtain effective feature description. Meanwhile, the features are extracted from the original data. Now, CNN has turned into a study hot point in the fields of giving a lecture discriminate, figure distinguishing, and classifying, and natural language handling. Moreover, it is widely used in these fields, and its application effect has been recognized by most people. Consequently, CNN composition is adopted to predict the finance time succession data. Firstly, the research means of financial time series are summarized, and then, the artificial neural network (ANN) and deep learning methods are briefly introduced. Afterward, the prediction model of stock index according to CNN model is proposed, and the influences of historical factors on model are analyzed. Finally, a few stock indexes are predicted to verify validity and effectiveness of the proposed CNN model through experimental comparison. And a hybrid model combined with CNN is found, thus further improving the cable CNN network model.

Agustín Maravall: An interview with the International Journal of Forecasting

Agustín Maravall Herrero (Madrid, 1944) is one of the world’s authorities in seasonal adjustment and automatic forecasting of economic time series. He studied Agricultural Engineering and completed a doctorate at the Universidad Politécnica de Madrid. With a Ford-Fulbright fellowship he moved to the University of Wisconsin-Madison to obtain a Ph.D. in Economics in 1975. He worked at the Research Division of the Federal Reserve Board of Governors (the Fed) in Washington D.C. and in 1979 returned to Madrid as a Senior Economist in the Research Department of the Banco de España (BE). In the period 1989-96, he was a full professor in the Department of Economics of the European University Institute (EUI) in Florence. He returned to the BE as Chief Economist and Head of the Time Series Analysis Unit and retired in December 2014.Maravall has done outstanding research in time series and has been a pioneer in developing methodology and writing computer programs for automatic estimation and model selection, seasonal adjustment, and forecasting of time series. His programs “Time Series Regression with ARIMA noise, Missing observations and Outliers” (TRAMO) and “Signal Extraction in ARIMA Time Series” (SEATS), jointly developed with Victor Gómez, have had a large influence in applied forecasting, including adjusting series for seasonality and possibly other undesirable effects, such as outliers, or missing observations, and have been used in many economic institutions around the world. He has been very active in promoting the automatic analysis of time series, teaching short courses in many countries. Also, he has stimulated research in this field being on the editorial board of the Journal of Business and Economic Statistics and the Journal of Econometrics. He has been a Special Advisor to the European Central Bank (ECB) and Eurostat in time series analysis. His research contributions have been recognized as Fellow of the Journal of Econometrics, 1995; Fellow of the American Statistical Association, 2000; Julius Shiskin Award for Economic Statistics, 2004, and the highest prizes for Economic Research in Spain: The Rey Jaime I Prize in Economics, 2005 and the Rey Juan Carlos Prize in Economics, 2014.