Predicting the Number of Suicides in Japan: A Vector Autoregression Time Series Model Using Internet Search Queries (Preprint)

BACKGROUND The number of suicides in Japan increased during the COVID-19 pandemic. Predicting the number of suicides is critical to take timely preventive measures. OBJECTIVE In this study, we examine whether the number and characteristics of suicides can be predicted based on the Internet search behavior and the search queries. METHODS The monthly number of suicides by gender, collected and published by the National Police Agency, was used as an outcome variable. The number of searches by gender on the queries associated with "suicide" on "Yahoo Search" from January 2016 to December 2020 was used as a predictive variable. The following five phrases highly relevant to "suicide" were searched before searching for the keyword "suicide," and extracted and used for analyses: "abuse," "work, don’t want to go," "company, want to quit," "divorce," and "no money." The Augmented Dickey–Fuller and Johansen's tests were performed for the original series and to verify the existence of unit roots and cointegration for each variable, respectively. The vector autoregression model was applied to predict the number of suicides. The Breusch–Godfrey Lagrangian multiplier (BG-LM) test, autoregressive conditional heteroskedasticity Lagrangian multiplier (ARCH-LM) test, and Jarque–Bera (JB) test were employed to confirm model convergence. In addition, a Granger causality test was performed for each predictive variable. RESULTS In the original series, unit roots were found in the trend model, whereas in the first-order difference series, both men (minimum tau 3: −9.24, max tau 3: −5.38) and women (minimum tau 3: −9.24, max tau 3: −5.38) had no unit roots for all variables. In Johansen's test, a cointegration relationship was observed among several variables. The queries used in the converged models were "divorce" for men (BG-LM test: p= 0.55; ARCH-LM test: p= 0.63; JB test: p= 0.66) and "no money" for women (BG-LM test: p = 0.17; ARCH-LM test: p = 0.15; JB test: p= 0.10). In the Granger causality test for each variable, "divorce" was significant for both men (F= 3.29, p = 0.041) and women (F = 3.23, p = 0.044). ¬ CONCLUSIONS The number of suicides can be predicted by the search queries related to the keyword "suicide." Previous studies have reported that financial poverty and divorce are associated with suicide. The results of this study, in which search queries on "no money" and "divorce" predict suicide, support the findings of previous studies. Further research on the economic poverty of women and those with complex problems is necessary.

Inflation and Economic Growth Paradox: A Co-integration Analysis in Nepal

The empirical study investigates the relationship between economic growth, inflation and broad money supply in Nepal. Data since 1965 to 2020 are taken from World Bank and Autoregressive Distributive Lag Model is used to find cointegration between the variables to show long run and short run dynamics. Augmented Dickey- Fuller and Philips- Perron tests are conducted to find the unit roots in the model. Result shows the error correction term is negative (-0.75) and significant (0.0043) where bounds test supports the long run cointegration and error correction model suggest the speed of adjustment. The estimated regression equation is found robust and stable (serial correlation and heteroskedacity tests). The research shows inflation has short run and long run impact on economic growth so inflation should be kept within its threshold level from sound monetary and fiscal policy mechanism.

Parallels and Differences in Earnings Management of the Visegrad Four and the Baltics

Earnings management is a legal and widely preferred phenomenon of business finance that financial managers use to maintain and improve the enterprise’s competitiveness. Managers purposely manipulate business earnings to achieve the required status of the enterprise. The consequence of these activities is to provide a positive perspective for the owners, encourage the profitability for the creditor and the investors as well as demonstrate economic strengths to competitors. This article aims to identify parallels and differences in earnings management of enterprises in the Visegrad Four and the Baltics in terms of competitiveness for the nineyear period 2010-2018. The research uses a final sample of 4,543 observations from the EBITs of Slovak, Czech, Hungarian and Polish enterprises as well as 1,633 observations from the EBITs of Latvian, Lithuanian and Estonian enterprises. Time-series methods with all necessary assumptions have been run for the analyzed financial dataset. The results of the econometric modeling of unit roots show significant parallels in these groups of countries. The enterprises from the Visegrad group and the Baltics group use the apparatus of earnings management to be competitive. The obtained results confirm the systematic but legal manipulation from the side of management. A quantitative analysis of homogeneity tests using 1,000,000 Monte Carlo simulations indicates significant time differences of manipulation in these emerging countries. The year 2014 signaled a radical “accelerando” in earnings management for the V4, and the year 2016 is highlighted for the Baltics.

Analisis Kausalitas Pertumbuhan Ekonomi, Indeks Pembangunan Manusia Dan Belanja Modal Di Provinsi.Jambi

This research aims toaanalyze the causal relationshipbbetween several variables including economiccgrowth using the value of PDRB at constant prices, the variable humanndevelopment index (HDI) and capitaleexpenditures in Jambi Province during 2010-2020 period. The data used in this research is secondary data with a database obtained from BPS Jambi Province and Regional Financial Statistics Jambi Province. The method used in this research is the Granger causality analysis method, which was previously tested using unit roots and cointegration methods to see the long-termrrelationship betweenrresearch variables. The results showed that there was a long-term relationship between the research variables. Economic growth has a one-way causal relationship with HDI. Economic growth increases the supply of resources needed for human development which in turn will encourage better human development. The capital expenditure variable has a one-way causal relationship with the economic growth variables. The allocation of capital for the implementation of various community economic activities and become an economic stimulus in Jambi Province.

Effects of Digitalisation on Higher Education in a Sustainable Development Framework—Online Learning Challenges during the COVID-19 Pandemic

Throughout the planet, the medical challenges posed by the pandemic caused by the SARS-Cov-2/COVID-19 coronavirus have overlapped, inter alia, with the necessity to continue the academic process on every level. Romania was no exception. With the new vaccines against COVID-19, the hope of resuming face-to-face activity, considered as ‘normal’ before 2020, has emerged. In these circumstances, not at all far-fetched, certain questions have arisen, such as: should and must the online university education be completely removed? Should this form of education be continued? If so, to what extent? We have used econometric methods related to ARDL (auto regressive distributed lag models) such as pooled mean group (PMG) and mean group (MG) and used different tests for unit roots for the stationarity check of the series implied. The results show the positive effect of digitalisation on tertiary education and also the positive impact of the latter on sustainable development, as a base for future stimulation in public policies. The present study also aims to harness the university experience of these times, from some of the main Romanian university centres; the method used was a quantitative and qualitative research based on a questionnaire, which was answered by a number of 258 university teachers and 1569 students from prestigious public and private universities. The results of this analysis allowed us to conclude that most of the participants in the university educational process have adapted to the online activity, and the latter ‘saved’ the academic years 2019–2020 and, respectively, 2020–2021. The present study is useful for tertiary education institution and policymakers in terms of formulating strategies and policy recommendations to support teachers and students during any future pandemics.

Stationarity in the Prices of Energy Commodities. A Nonparametric Approach

In this paper, we address the classical problem of testing for stationarity in the prices of energy-related commodities. A panel of fourteen time series of monthly prices is analyzed for the 1980–2020 period. Nine of the series are classical nonrenewable, GHG-emissions-intensive resources (coal, crude oil, natural gas), whereas the remaining, low-emission group includes both uranium and four commodities employed in biofuels (rapeseed, palm, and soybean oils, and ethanol). A nonparametric, bootstrap-based stationarity testing framework is employed. The main advantage of this procedure is its asymptotically model-free nature, being less sensitive than parametric tests to the risks of misspecification and detection of spurious unit roots, although it has the potential limitation of typically requiring larger samples than mainstream tools. Results suggest that most of the series analyzed may be trend stationary. The only exception would be crude oil, where different conclusions are obtained depending on whether a seasonal correction is applied or not.

Characterizing growth instability: new evidence on unit roots and structural breaks in countries’ long run trajectories

In this paper we investigate whether long run time series of income per capita are better described by a trend-stationary model with few structural changes or by unit root processes in which permanent stochastic shocks are responsible for the observed growth discontinuities. For a group of advanced and developing countries in the Maddison database, we employ a unit root test that allows for an unspecified number of breaks under the alternative hypothesis (up to some ex ante determined maximum). Monte Carlo simulations studying the finite sample properties of the test are reported and discussed. When compared with previous findings in the literature, our results show less evidence against the unit root hypothesis. We find even fewer rejections when relaxing the assumption of Gaussian shocks. Our results are broadly consistent with the implications of evolutionary macro models which posit frequent growth shifts and fat-tailed distribution of aggregate shocks.

Dynamic Linkage between Monetary Policy and Stock Performance in Nigeria: Cointegration and ECM Techniques

Aims: To explore the dynamic relationship between stock performance and the monetary policy instruments that influence Nigeria’s stock market activities. Study Design: It uses secondary data collected from the Central Bank of Nigeria (CBN) Statistical Bulletin. The annual time series data cover a period of 38 years, from 1981-2018. Methodology: The Augmented Dickey-Fuller (ADF) unit roots' test technique was used to verify the variables' time-series properties while the Johansen procedure was applied to confirm cointegration among variables. The short- and long-run relationships were analyzed after estimating the vector error correction model. Common diagnostic tests were conducted to validate the robustness of the model estimates. Results: The results of tests of unit roots reveal all included variables as integrated of order one, I(1). The Trace-statistics showed that at least one cointegrating relationship exited among the time series, and the ECM was estimated. The emerging error correction term equation revealed the stock market performance as inversely related to both the credit to the private sector and the lending rate, but positively related to the money supply. Each variable was statistically significant (P<0.01). Also, the error correction term was well-behaved, being statistically significant (t=-3.17; P<0.01) and the desired negative sign, implying that previous periods' errors are correctable by adjustments in the subsequent periods, and to attain convergence. The error term had an adjustment speed of 44.19%. Granger-Causality analysis revealed a unidirectional causality relationship between the stock performance and the lending rate, with causality running from lending rate to stock performance, without a boomerang. The implication of the findings are threefold: the subsisting restrictive interest rate policy is unfavorable to long-term investment from the investors' perspective; the existing terms and conditions of the commercial credit packages had proven to be disadvantageous to long-term investment in Nigeria; and money supply as a monetary policy instrument in Nigeria had been used to boost investment and stock market performance. It is recommended that boosting investment and performance of the stock market in Nigeria would require the use of a more investment-friendly commercial lending rate, and relaxation of the stringent terms and conditions attached to the commercial private sector credit and loan packages. These measures would guarantee better access to fund and enhance ease-of-doing-business for investors.

Asymptotic Properties of Estimators for Seasonally Cointegrated State Space Models Obtained Using the CVA Subspace Method

This paper investigates the asymptotic properties of estimators obtained from the so called CVA (canonical variate analysis) subspace algorithm proposed by Larimore (1983) in the case when the data is generated using a minimal state space system containing unit roots at the seasonal frequencies such that the yearly difference is a stationary vector autoregressive moving average (VARMA) process. The empirically most important special cases of such data generating processes are the I(1) case as well as the case of seasonally integrated quarterly or monthly data. However, increasingly also datasets with a higher sampling rate such as hourly, daily or weekly observations are available, for example for electricity consumption. In these cases the vector error correction representation (VECM) of the vector autoregressive (VAR) model is not very helpful as it demands the parameterization of one matrix per seasonal unit root. Even for weekly series this amounts to 52 matrices using yearly periodicity, for hourly data this is prohibitive. For such processes estimation using quasi-maximum likelihood maximization is extremely hard since the Gaussian likelihood typically has many local maxima while the parameter space often is high-dimensional. Additionally estimating a large number of models to test hypotheses on the cointegrating rank at the various unit roots becomes practically impossible for weekly data, for example. This paper shows that in this setting CVA provides consistent estimators of the transfer function generating the data, making it a valuable initial estimator for subsequent quasi-likelihood maximization. Furthermore, the paper proposes new tests for the cointegrating rank at the seasonal frequencies, which are easy to compute and numerically robust, making the method suitable for automatic modeling. A simulation study demonstrates by example that for processes of moderate to large dimension the new tests may outperform traditional tests based on long VAR approximations in sample sizes typically found in quarterly macroeconomic data. Further simulations show that the unit root tests are robust with respect to different distributions for the innovations as well as with respect to GARCH-type conditional heteroskedasticity. Moreover, an application to Kaggle data on hourly electricity consumption by different American providers demonstrates the usefulness of the method for applications. Therefore the CVA algorithm provides a very useful initial guess for subsequent quasi maximum likelihood estimation and also delivers relevant information on the cointegrating ranks at the different unit root frequencies. It is thus a useful tool for example in (but not limited to) automatic modeling applications where a large number of time series involving a substantial number of variables need to be modelled in parallel.