CUSUM Test Research Articles

Global Mean Sea Level Nexus Climate Change: A Dynamic Cointegration and Causality Analyses

Nowadays, the impact of climate change on the global mean sea level variations is becoming an important issue to the researchers and policy makers as a general concern about environmental degradation is making their way into global policy agenda. That is why, in this paper the principal purpose has been made to investigate the dynamic cointegration and causality relationships between global mean sea level (GMSL) and its determinants. Also another purpose has been made to examine empirically the short-run and long-run effects of climate change, carbon dioxide emissions, energy consumption, trade openness and urbanization on global mean sea level based on the time series data from 1970-2019. From the Augmented Dickey-Fuller (ADF), Phillips-Perron (PP) and Kwiatkowski-Phillips-Schmidt-Shin (KPSS) tests results it is found that all the variables are integrated of order one i.e. I(1). From the bounds test approach, it is found that there exits only one cointegration relationship when GMSL is the dependent variable. From the Granger causality test results of VEC model, it is found that the short-run unidirectional causalities are running from carbon dioxide emissions and energy consumption to global mean sea level, from energy consumption and trade openness to carbon dioxide emissions and from trade openness to energy consumption. It has also been found that the error correction term is statistically significant at any significance level when global mean sea level is treated as endogenous variable indicating that there exists a long-run relationship among the variables in the form of Equation (1). It has also been found that in the short-run the variables temperature, carbon dioxide emissions, and urbanization have significant positive effects while energy consumption and trade openness have significant negative effects on global mean sea level at any significance level. The coefficient of ECM (-1) is statistically significant at any significance level, indicates that speed of adjustment for short-run to research in the long-run equilibrium is statistically significant and within the first year, when global mean sea level is above or below its equilibrium level, it adjusts 66.52%. It has also been found that in the long-run the variables temperature, carbon dioxide emissions, and urbanization have significant positive effects on global mean sea level at any significance level but the variable energy consumption has significant negative effects at 5% significance level. It is also found that over time higher temperature, and carbon dioxide emissions will increase global mean sea level rapidly. The CUSUM and CUSUMSQ tests results support that the VEC model is stable and can be applied for policy formulation and decision making purposes.

Long-Run Money Demand Function: Search for Stability in Twenty (20) Non-EMU Member Countries

This study examined the long-run money demand function in search for stability in twenty (20) Non-EMU member countries by applying Co-integration, an ARDL bounds test, CUSUM, and CUSUM squared estimation techniques to data spanning 1996 – 2019. We found co-integrating relationship between money demand and its determinants for all the countries under consideration (19 out of 20) except for Sweden. Stability in the money demand was also confirmed in seven (7) countries (Russia, Hungary, Montenegro, Bosnia, Bulgaria, Romania, and Croatia) based on both the CUSUM test results and CUSUM squared test. The remaining countries exhibited partial stability as indicated by the non-simultaneous stability of the CUSUM and CUSUM squared test. The divergence and heterogeneity found in the money demand functions and its determinants in these countries only give further impetus to their non - membership in the Eurozone. Hence there is the need for stability and convergence in the monetary policy management and money demand function to be admitted into the Eurozone holding other conditions fixed.

Nexus between China-Pak Business Cycle Synchronization and Human Development in Pakistan

This study has examined the potential impact of China-Pak business cycle synchronization on human development in Pakistan. Data covered the time span of 1975-2017. Other independent variables include inflation, GDP per capita, external debt and FDI. Results of unit root test showed that all variables were stationary with mixture of level and first difference. F-bounds test confirmed the presence of long run relationship among the variables. ARDL technique was applied to obtain long run coefficients. The study found that FDI and GDP per capita had positive and significant impact on human development while China-Pak business cycle synchronization, inflation and external debt had negative and significant relationship with human development in Pakistan. Results showed the value of error correction term -0.16 with 1 percent level of significance which confirmed the presence of short run equilibrium in the model. All independent variables had significant relationship with human development in the short run. CUSUM and CUSUMSQ stability tests showed that parameters of the model were stable. The study suggested that government should focus critically China-Pak business cycle synchronization to uplift human development in Pakistan for which domestic production should be promoted to facilitate domestic producers that might be helpful to improve employment level which finally can raise human development. Control on inflation is significant for the sake of human development. Policy makers should take steps for improvement in GDP per capita and FDI to encourage human development in Pakistan.

Financial Innovation and Demand for Money in Nigeria

This study examined the impact of financial innovation on money demand in Nigeria, using quarterly time series for the period 2009-2019. The dependent variable was money demand, represented by broad money, while the independent variable was financial innovation represented by modern payment channels such as volume of Automated Teller Machines (ATMs) transactions, volume of Point of Sales (POS) transactions, volume of Internet banking transactions, and volume of Mobile banking transactions. The study employed the ordinary least squares (OLS) regression technique as the estimation method within the cointegration, granger causality, and error correction modeling. The result obtained showed that financial innovation has mixed impact on money demand in Nigeria during the period of analysis. For instance, financial innovation has positive impact on money demand through volume of ATM transactions in the current period, two periods lagged of volume of mobile banking transactions, current period and one period lagged of volume of internet banking transactions, and current period’s volume of Point of Sales (POS) transactions in Nigeria. On the other hand, financial innovation has negative impact on money demand through one period lagged of volume of point of sales in Nigeria. On the stability of the demand for money function, the result of the stability tests based on the CUSUM test and CUSUM of squares test showed that the demand for money function was stable during the evaluation period. The study recommended that monetary policy strategy of the central bank of Nigeria (CBN) should be fine-tuned to ensure it is well suited to deal with the challenges posed by financial innovation by way of proliferation of sophisticated payment channels.

Nonparametric volatility change detection

AbstractWe consider a nonparametric heteroscedastic time series regression model and suggest testing procedures to detect changes in the conditional variance function. The tests are based on a sequential marked empirical process and thus combine classical CUSUM tests from change point analysis with marked empirical process approaches known from goodness‐of‐fit testing. The tests are consistent against general alternatives of a change in the conditional variance function, a feature that classical CUSUM tests are lacking. We derive a simple limiting distribution and in the case of univariate covariates even obtain asymptotically distribution‐free tests. We demonstrate the good performance of the tests in a simulation study and consider exchange rates as a real data application.

Finite Sample Change Point Inference and Identification for High-Dimensional Mean Vectors

AbstractCumulative sum (CUSUM) statistics are widely used in the change point inference and identification. For the problem of testing for existence of a change point in an independent sample generated from the mean-shift model, we introduce a Gaussian multiplier bootstrap to calibrate critical values of the CUSUM test statistics in high dimensions. The proposed bootstrap CUSUM test is fully data dependent and it has strong theoretical guarantees under arbitrary dependence structures and mild moment conditions. Specifically, we show that with a boundary removal parameter the bootstrap CUSUM test enjoys the uniform validity in size under the null and it achieves the minimax separation rate under the sparse alternatives when the dimension p can be larger than the sample size n.Once a change point is detected, we estimate the change point location by maximising the ℓ∞-norm of the generalised CUSUM statistics at two different weighting scales corresponding to covariance stationary and non-stationary CUSUM statistics. For both estimators, we derive their rates of convergence and show that dimension impacts the rates only through logarithmic factors, which implies that consistency of the CUSUM estimators is possible when p is much larger than n. In the presence of multiple change points, we propose a principled bootstrap-assisted binary segmentation (BABS) algorithm to dynamically adjust the change point detection rule and recursively estimate their locations. We derive its rate of convergence under suitable signal separation and strength conditions.The results derived in this paper are non-asymptotic and we provide extensive simulation studies to assess the finite sample performance. The empirical evidence shows an encouraging agreement with our theoretical results.

Relationship Between Industrialization and Economic Growth: An Empirical Study of Pakistan

The purpose of this paper is to investigate the long run relationship of Industrialization and Economic Growth in Pakistan. The time series data from 1976-2015 is used. The main source of data is World Development Indicator (WDI). Gross Domestic Product is used as dependent variable, while Industrial Output, Foreign Direct Investment, Saving and Inflation are used as the independent variables. The ARDL testing Approach has been applied on the data. After it, the stability of the function was tested by CUSUM. The results of ARDL bound testing reveals the long run association between industrial output and GDP. This study shows that an increase in Industrial Output increases the Gross Domestic Product in Pakistan. In the end, the stability of results is confirmed by CUSUM test.

Consensus-Based Distributed Quickest Detection of Attacks With Unknown Parameters

Sequential attack detection in a distributed sensor network is considered, where each sensor successively produces one-bit quantized samples of a desired deterministic scalar parameter corrupted by additive noise. The unknown parameters in the pre-attack and post-attack models, namely the desired parameter to be estimated and the injected malicious data at the attacked sensors pose a significant challenge for designing a computationally efficient scheme for each sensor to detect the occurrence of attacks by only using local communication with neighboring sensors. The generalized Cumulative Sum (GCUSUM) algorithm is considered, which replaces the unknown parameters with their maximum likelihood estimates in the CUSUM test statistic. For the problem under consideration, a sufficient condition is provided under which the expected false alarm period of the GCUSUM can be guaranteed to be larger than any given value. Next, we consider the distributed implementation of the GCUSUM. We first propose an alternative test statistic which is asymptotically equivalent to that of GCUSUM. Then based on the proposed alternative test statistic and running consensus algorithms, we propose a distributed approximate GCUSUM algorithm which significantly reduce the prohibitively high computational complexity of the centralized GCUSUM. Numerical results show that the proposed distributed approximate GCUSUM algorithm can provide a performance that is comparable to the centralized GCUSUM.

Test for parameter change in the presence of outliers: the density power divergence-based approach

ABSTRACT This study considers the problem of testing for parameter change, particularly in the presence of outliers. To lessen the impact of outliers, we propose a robust test based on the density power divergence introduced by Basu et al. (Biometrika, 1998), and then derive its limiting null distribution. Our test procedure can be naturally extended to any parametric model to which MDPDE can be applied. To illustrate this, we apply our test procedure to GARCH models. We demonstrate the validity and robustness of the proposed test through a simulation study. In a real data application to the Hang Seng index, our test locates some change-points that are not detected by the existing tests such as the score test and the residual-based CUSUM test.

Mean targeting estimation for integer-valued time series with application to change point test

This study considers the mean targeting estimation for integer-valued time series models and a parameter change test as its application. We first introduce the mean targeting quasi-maximum likelihood estimator (QMLE) based on generalized autoregressive conditional heteroscedastic (INGARCH) models and then consider the CUSUM test of (standardized) residuals. To evaluate the performance, we conduct a Monte Carlo simulation study applying a negative binomial mean targeting QMLE to Poisson INGARCH, Poisson integer-valued autoregressive (INAR), and log-linear Poisson INGARCH times series of counts, and demonstrate its validity. A real data analysis is also conducted using the drug offense data in Pittsburgh and Goldman Sachs Group stock data for illustration.

IMPACT OF COUNTRY RISK AND RETURN ON FPI

This study measures the economic content of three different inductors of country risk: political, economic and financial risk indices, and fundamental attributes, such as earning-to-price ratios, and its impact on net foreign portfolio equity investment inflow in Egypt. We explore whether any of these measures contain information about net foreign portfolio equity investment inflow in Egypt. The study uses the autoregressive distributed lag (ARDL) bounds testing approach. Quantitative estimates based on the time series annual data from 2004 to 2018. The empirical results prove that there is a univariate cointegrated and stable long-run relationship among net foreign portfolio equity investment inflow and three different measures of country risk and E/P ratio. The results show that three measures of country risk have a significant effect on net foreign portfolio equity investment inflow in Egypt in the long and short run. But Political risk is a positive effect, While Economic and Financial risks are a negative effect. And E/P ratio has a positive significant effect on net foreign portfolio equity investment in Egypt in the short run only. The results confirm that after Procedure the CUSUM and CUSUMSQ tests, net foreign portfolio equity investment inflow function is stable.Keywords: Country Risk, Return, FPI, ARDL, EgyptJEL Classifications: C12, F21, G11, G15DOI: https://doi.org/10.32479/ijefi.10495

Appraisal of Determinants of Real Exchange Rate Alignment in Kenya

Real exchange rate is an important indicator of competitiveness in the foreign trade of a country. Any changes in real exchange rates would therefore lead to fluctuations in capital flows. It is therefore important to align real exchange rates within the equilibrium levels to avoid negative consequences on the economy. This study sought to understand the determinants of real exchange rate alignment in Kenya using annual data from 1988 to 2019 using Autoregressive Distribution Lag (ARDL) model. The study estimated the long run and short run dynamics of real exchange rate alignment in Kenya. The ARDL bounds test confirmed that a long run relationship exists between real exchange rate and the explanatory variables. Real exchange rate was the dependent variable while the explanatory variables were external public debt, government expenditure, interest rate differentials and productivity differentials. The results revealed that external public debt, government expenditure and productivity differentials are significant determinants of real exchange rate alignment. Interest rate differential was found to be not significant. The Error Correction Model was found to be significant and having the right (negative) sign. This shows that Kenya’s real exchange rate adjusts to the long run equilibrium as a response short run shocks of previous periods. The speed of adjustment was found to be 86 percent per year. Both the long run and error correction models were found to be stable as per the CUSUM and CUSUMQ tests. The models also passed all the diagnostic tests including serial correlation, normality, heteroscedasticity, and multicollinearity.

Estimating a Fiscal Reaction Function for Nigeria

The study examines the determinants of fiscal balance and the impact of the selected macroeconomic variables on the primary balance of government. It aims to estimate the fiscal reaction function for Nigeria and determine whether the implementation of fiscal policy is sustainable in the long-run. A Fiscal Reaction model was developed and ARDL technique was used to establish the relationships and interactions among the variables. The study investigated whether the fiscal measures pursued by the government from 2000:Q1 to 2018:Q4 was adequate in addressing the accumulation of huge debt. The analysis of the stylized facts reveals that the government had continued to run budget deficits for almost the entire period, except for a few period. The public debt to GDP, which is a major determinant of the primary balance, is negative and significant implying that a fiscal rule that encourages a strong reduction in debt-to-GDP levels would result in substantial pressure for Nigeria to run large primary surpluses in the future. The CUSUM and CUSUMSQ tests show the recursive residual plots of the fiscal reaction function are within the 5 per cent critical lines, hence, providing evidence of stable fiscal reaction function for Nigeria. The study thus, recommends that, apart from the urgent need for the fiscal authorities to adopt urgent reforms to discourage huge debt accumulation, improve revenue generation capacity and more fundamentally, expenditure switching to improve the quality of expenditure, the transition from primary deficits to primary surpluses should follow a gradual process.

Change-point detection based on adjusted shape context cost method

Change-point problems which originated from the field of quality control have become an important area of research. Although existing methods have been successful in detecting change-points, most of them require the underlying data to follow a specific distribution. Heuristically speaking, those methods only perform well when the data set is hypothesised to follow a normal distribution. In this paper, instead of traditional statistical inference, we propose a new algorithm from a shape perspective, which provides a more robust approach to addressing change-point problems. Our new algorithm will define a novel statistic based on shape context, a rich local shape descriptor, to replace the CUSUM test statistic considered by traditional methods. In addition, some areas which do not have change-points are abandoned through segmentation and screening, reducing computational complexity and increasing available storage. At the same time, we introduce the idea of peak recognition, which increases the robustness and effectiveness of the detection. The experimental results demonstrate that the proposed algorithm significantly outperforms some other methods with regard to accuracy and efficiency, especially when a longer time series is under study. We include analyses of two real-world data sets which demonstrate the practical effectiveness of this algorithm.

The Comparison of Hemoglobin Values Measured by Blood and Continuous Non-Invasive Monitoring (SpHb) in Newborn Infants.

Hemoglobin (Hb) measurement is one of the most commonly used laboratory tests in medical practice. Unnecessary blood sampling, especially in neonatal intensive care units (NICUs), contributes to iatrogenic anemia. Continuous non-invasive monitoring of total Hb (SpHb) was compared with invasive venous blood samples (tHb) in NICU patients. Three hundred and ten patients were identified in NICU. Non-invasive Hb measurement was performed immediately before venous blood sampling and comparison of invasive with non-invasive values was undertaken. There was a strongly positive correlation between SpHb and tHb (r = 0.965, p < 0.001). Bland-Altman analysis was performed in 95% limits of agreement for Hb values measured by both methods. The mean bias between tHb and SpHb measurements was 0.05 g/dl (-1.85 to 1.96). In Passing-Bablok regression analysis, the CUSUM test p value was found to be 0.98 for Hb levels measured by SpHb and tHb; and the difference between the methods was not significant. In newborns, SpHb method offers reliable Hb values, which are comparable with the more traditional tHb method. Continuous non-invasive monitoring of total Hb may help prevent unnecessary blood sampling and iatrogenic anemia. Further clinical studies are required for the effectiveness of the method in critically ill patients with circulatory disorders.

IMPACT OF FINANCIAL GROWTH ON THE ECONOMIC DEVELOPMENT OF OMAN

Purpose of the study: This paper aims to empirically test the long and short-run effects of financial development on the economic growth of Oman.&#x0D; Methodology: This paper has applied the Unit root test, ARDL Bound Test for Cointegration, CUSUM, and CUSUMSQ Test for testing of hypotheses. The data used to test the relationship between financial development and economic growth covers the period from 1980 to 2017.&#x0D; Main Findings: The major finding of the study suggested that the financial development variables measured in the research influence the economic growth in Oman. &#x0D; Applications of the Study: This study can be useful to assess the strength of the empirical link between the financial sector and economic growth in Oman as one of the oil-exporting states of the Middle East Region, where such studies are inadequate.&#x0D; The novelty of the Study: The finding of the study with an addition to the existing literature by incorporating the new variables like employment or poverty in the existing model provides new insight on the financial development of Oman.&#x0D; Limitations and forward of the Study: The study has considered a set of data which in general acts as a catalyst for economic development in a particular country. &#x0D; Implications of the Study: The outcome of the study suits the nature of the country and its socio-economic conditions. The outcomes of the study will not be suitable for every country and may result in spurious outcomes.

Quickest attack detection in smart grid based on sequential Monte Carlo filtering

Quick and accurate detection of cyber attack is key to the normal operation of the smart grid system. In this paper, a joint state estimation and sequential attack detection method for a given bus with grid frequency drift is proposed that utilizes the commonly monitored output voltage. In particular, based on a non-linear state-space model derived from the three-phase sinusoidal voltage equations, we employ the sequential Monte Carlo (SMC) filtering to estimate the system state. The output of the SMC filter is fed into a CUSUM test to detect the attack in a fastest way. Moreover, an adaptive sampling strategy is proposed to reduce the rate of taking measurements and communicating with the controller. Extensive simulation results demonstrate that the proposed method achieves high adaptivity and efficient detection of various types of attacks in power systems.

On CUSUM test for dynamic panel models

In this study, we consider the problem of testing for a parameter change in dynamic panel models with fixed effects. As a test, we suggest using the CUSUM test based on the score vectors and show that under regularity conditions, the test converges weakly to the supremum of a Gaussian process. The test is then compared with the location-scale CUSUM (LSCUSUM) test through Monte Carlo simulation, showing its superiority to the LSCUSUM test. We also conduct a real data analysis using the real energy consumption data of OECD countries along with their GDPs for illustration.

The Role of Political Stability, Labor Market and Education on Migration: The Empirical Evidence from Sri Lanka

This study employs annual data from Sri Lanka over the period of 1990 – 2018 in order to investigate the impact of political instability and the existence of violence, unemployment rate, wage differential and level of education on migration. ADF unit root test confirmed that none of the variables are I(2), which allows us to examine the long run relationship between the variables using Autoregressive Distributed Lag (ARDL) Bound testing method. AIC is suggested to adapt ARDL (1, 0, 0, 2, 0) model among the top 20 models. ARDL Bound testing approach identified the cointegrating relationship between the variables. The results of both ARDL Bound test and the ARDL version of ECM detected that unemployment rate, political instability and the existence of violence/terrorism and level of education have a positive and significant impact on net migration whereas wage differential do not have significant impact on it even though it affect the net migration negatively both in the long run and in the short run respectively. Also, the coefficients of long run results and the Wald test confirm that the impact of unemployment rate is higher than wage differential, political instability and level of education on net migration in the long run. The result of CUSUM test of selected ARDL model discloses that the estimated model is stable and this model passes the all the diagnostic test. Moreover, Granger causality test identified a causal relationship that stemming from unemployment to net migration, wage differential to net migration, political instability to net migration and level of education to net migration. These findings could be useful to policy makers when they formulating and implementing the policy related to labor markets and good governance.

Block wild bootstrap-based CUSUM tests robust to high persistence and misspecification

It is well-known that the conventional CUSUM tests are over-sized in the presence of high persistence and misspecification. In this article, we propose a block wild bootstrap-based CUSUM test (CUSUM-BWB) for detecting changes in mean and variance shifts under possible high persistence and misspecification. We establish the asymptotic properties of the proposed test and our simulation study shows that CUSUM-BWB tests achieve the correct sizes and comparable powers in finite samples. Our method is also applied to the realized volatility of the KOSPI stock index.