China 
Africa 
Explore chapters and articles related to this topic
Understanding the Relationship between Digital Currencies and Search Engines
Published in Amina Omrane, Khalil Kassmi, Muhammad Wasim Akram, Ashish Khanna, Md Imtiaz Mostafiz, Sustainable Entrepreneurship, Renewable Energy-Based Projects, and Digitalization, 2020
Naveed Ahmad Lone, Yousfi Karima, Hurmat Sumaiya Binti Bashir
For all series we tested the null hypothesis of the unit root, using Augmented Dickey-Fuller (ADF), the Phillips-Perron (PP) test, and the Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) unit root test (Maddala & Kim, 1998). Each series was tested for the presence of a unit root. The unit root test statistics suggest the presence of a unit root in the level, while first differencing the series yields the apparent lack of a unit root in the two variables, the Bitcoin price index and Google Trends in the log. From these results, we can conclude that each series has a unit root at levels and it is stationary when the first difference is taken. It can be said that all variables are integrated of order 1, I(1). We then check for the presence of cointegrating relations between these variables (Table 9.3).
Relationship between Nuclear Energy Consumption and Economic Growth
Published in Stephen A. Roosa, International Solutions to Sustainable Energy, Policies and Applications, 2020
Korhan Gokmenoglu, Mohamad Kaakeh
This study utilized time series econometrics techniques to examine the relationship between nuclear energy consumption and economic growth. To choose the most suitable econometric methods to investigate the long-term and causal relationships between the variables, stochastic properties of the variables should be investigated first. To determine if the series have a unit root, we used the Dickey and Fuller unit root test and the Kwiatkowski, Phillips, Schmidt, and Shinn stationarity test for confirmation [40,41]. Because all series have a unit root, the Johansen cointegration test was used to examine the existence of a long-term relationship among the variables [42]. Vector error correction models were used to estimate the long-term coefficients. The Granger causality test was applied to find the direction of the causal relationship.
Complexity Analysis of Pathogenesis of Coronavirus Epidemiological Spread in the China Region
Published in Jyoti Mishra, Ritu Agarwal, Abdon Atangana, Mathematical Modeling and Soft Computing in Epidemiology, 2020
Rashmi Bhardwaj, Aashima Bangia, Jyoti Mishra
Basically, a unit root test is used to check stationarity as these unit roots can cause unpredictable results in the autoregressive models of time-series analysis. Time series is different in comparison with the predictive modeling. As in modeling, the assumptions exist that summary statistics of observations are consistent. In context with time series, these expectations are referred as time domain, which is stationary.
Spatial analysis of accidents involving food delivery motorcycles in Taiwan
Published in Transportation Planning and Technology, 2022
Pei-Chun Lin, Chung-Wei Shen, Jenhung Wang, Chuan-Ming Yang
The dynamic panel data model shown in Equation (2) includes the first-order time-lag term, , as a regressor and is estimated performing the Arellano and Bond (1991) test for autocorrelation. The Arellano and Bond estimator is implemented in STATA software, and it employs moment conditions in which the dependent variable's delays and first differences of the exogenous variables serve as instruments for the first-differenced equation. A generalized method of moments (GMM) for a panel data model generates the unbiased estimate of and , solving endogeneity and bias in estimation because of the presence of a correlation between the lagged values of dependent variables and errors terms . The augmented Dickey-Fuller (ADF) unit root test (Dickey and Fuller 1979) is used to determine whether the time series is stationary before model fitting. It must measure times difference on the ADF test until it is stationary. Furthermore, in order to determine whether the time series of the dependent variable and the independent variable have a causal relationship, the Engle and Granger (1987) cointegration test examines whether the lagged trends of these two time series share a similar stochastic one. where:
Electricity consumption and economic growth nexus in Zimbabwe revisited: fresh evidence from Maki cointegration
Published in International Journal of Green Energy, 2019
Remember Samu, Festus Victor Bekun, Murat Fahrioglu
In order to establish the asymptotic traits and maximal order of integration of time series variables, stationarity test is crucial. However, various unit root test abounds in the applied economics literature namely: (Augmented Dickey-Fuller ADF, 1981; Phillips & Perron PP, 1988; Ng and Perron, 2001; Elliot et al., 1996) among others. The above-mentioned tests fail to account for structural breaks which are known to plague most macro/financial series. Thus, Zivot and Andrews (1992) ameliorate the aforementioned issue. Zivot- Andrews (ZA) unit root test accounts for a single structural break. The ZA test comprises of three models given as:
Ensemble of ARIMA: combining parametric and bootstrapping technique for traffic flow prediction
Published in Transportmetrica A: Transport Science, 2020
Siroos Shahriari, Milad Ghasri, S. A. Sisson, Taha Rashidi
However, in real-world data, we typically have additional unknown factors that produce additional stochasticity. Examples of these externalities in the traffic volume context include special events, adverse weather conditions and public holidays. The impact of these events on traffic volume is usually longer than one-time interval. For instance, one day public holiday impacts 1440 data points of a time series data which is collected on minute basis. In this experiment, the value of is assumed to vary every 1,440 intervals () to generate data representing real-world data. Under this assumption the generated data violates the stationary requirement; however, when the standard deviation of is relatively small, the data passes the Augmented Dickey-Fuller (ADF) test (Dickey and Fuller 1979). ADF is a unit-root test with the null hypothesis of the presence of unit root in data and the alternative hypothesis of the stationary conditions (Dickey and Fuller 1979). The ADF test statistic in this example for the generated datasets rejects the null hypothesis and indicating the data is not distinguishable from stationary series. In other words, even though these datasets are not in fact pure stationary datasets, they practically pass the ADF test, therefore can be modelled using ARIMA. Figure 2 shows pure ( = N (0,0)) and one of the real-world ( = N (0,1)) generated datasets.