Constant Mean Model Research Articles

The reaction of the Egyptian stock market to recurring devaluations: an event study approach

PurposeThis paper examines the reaction of the Egyptian stock market to two substantial devaluations of the Egyptian pound (EGP) in 2022 and tests the informational efficiency of the Egyptian market.Design/methodology/approachThe paper uses the event study framework to analyze the significance and direction of abnormal returns of the leading index of the Egyptian stock market (EGX30) on and around the devaluation days. It employs both the constant mean model and the market model to estimate the normal returns of the EGX30. Additionally, the paper uses data on two equity indices, one global and one for emerging markets, as benchmarks for normal returns.FindingsThe paper finds that the Egyptian stock market experienced significant positive abnormal returns on the devaluation days of the EGP in March and October of 2022, indicating a positive market reaction to the devaluation. Furthermore, evidence suggests that the Egyptian market may not be informationally efficient as significant positive abnormal returns were observed two weeks before and two weeks after the devaluation day, suggesting news leaks and delayed reactions, respectively.Originality/valueThis study is the first to examine the impact of the recent two devaluations of the EGP in 2022 on the Egyptian stock market. It complements existing literature by analyzing the immediate market reaction to two consecutive devaluations in an African country. Furthermore, the paper evaluates the efficiency of the Egyptian market in processing information related to exchange rates.

Does banning cryptocurrencies affect stock markets?

PurposeThis paper aims to investigate the impact of banning cryptocurrencies on stock markets.Design/methodology/approachThe paper uses an event study approach and data from stock market indices in nine countries that imposed a ban. It uses the constant mean model and the market model, with two different benchmarks for global returns, to analyze if any of the stock indices show abnormal returns on or around the announcement of a cryptocurrency ban.FindingsThe analysis shows that banning cryptocurrencies did not affect the returns of stock markets in any of the countries studied, indicating that the cryptocurrency market and stock markets are decoupled from each other, or the ban was not effectively implemented.Originality/valueTo the best of the author’s knowledge, this paper is the first to explore the potential spillover effect of a cryptocurrency ban on stock markets. It also bridges two strands of literature: the relationship between cryptocurrencies and traditional assets, and the impact of cryptocurrency regulation on their returns.

Money laundering, media and European banks

PurposeThis paper aims to assess, from an empirical perspective, the research question if public media reports which relate concrete banks to concrete allegations of money laundering have an adverse impact on banks stock prices and what are the drivers of such impact?Design/methodology/approachThe paper makes use of event study methodology and uses the constant mean and the market model. The event window is calibrated towards a five-day window, and the estimation window has a length of 90 days, in line with best academic practices. Drivers are identified by correlation analysis. and the market model uses ordinary least squares regression.FindingsThe application of event study methodologies yields the results that stock prices of affected banks generate, at the date of the news appearance, statistically significant negative abnormal returns under both the market model and the constant mean model. As negative abnormal returns have been mainly found at the date of the event itself, the findings confirm that the impacts of money laundering may be severe but short natured. In addition, the paper finds that the identified negative abnormal returns may be driven by the banks’ size in terms of total assets, by the bank’s profitability in terms of return on assets and by the bank’s sustainability risk.Practical implicationsThe findings have implications in terms of banking and supervisory practices. In specific, the findings help to argue that banking consolidation is needed to lower the impacts of AML cases, as stock prices of larger banks show less sensitivity. In addition, the findings could be used to determine financial sanctions against banks violating AML regulation. Finally, the findings imply that AML news can have severe and fast-moving financial stability considerations and are, therefore, important in crisis situations.Originality/valueAs there appears to be no substantial research that applies event study methodology to the money laundering context, the combination of research question and methodology has an innovative character. In addition, there is no clear literature on media and money laundering.

Effect of Ukraine-Russia Conflict on the Cryptocurrency Market: an Event Study Perspective

Russia massively invaded Ukraine on February 24, 2022, unavoidably having an effect on the world economy and finance. This paper uses the event study to research the short-term response of the February 2022 top 5 variable-price cryptocurrencies (BTC, ETH, BNB, XRP, SOL) to the Russia-Ukrainian war under the constant mean model. The cryptocurrency volatility was dramatic during the event window, and cryptocurrencies did not show the characteristics of safe haven. Overall, the result of the effect of the Russia-Ukraine war on the cryptocurrency market was negative, with the least negative impact on SOL and the most negative impact on BNB, XRP. Finally, Using the different event window analysis, it shows the cryptocurrency market return volatility rebounded, but it does not sufficiently indicate there is a positive trend in the cryptocurrency market after the event. The analysis of this paper can provide some help for cryptocurrency investors in the event of unforeseen circumstances. And in the data selection, this paper doesn’t consider stablecoins.

Oil-Price Uncertainty and International Stock Returns: Dissecting Quantile-Based Predictability and Spillover Effects Using More than a Century of Data

We investigate whether oil-price uncertainty helps forecast the international stock returns of ten advanced and emerging countries. We consider an out-of-sample period of August 1925 to September 2021, with an in-sample period between August 1920 and July 1925, and employ a quantile-predictive-regression approach, which is more informative relative to a linear model, as it investigates the ability of oil-price uncertainty to forecast the entire conditional distribution of stock returns Based on a recursive estimation scheme, we draw the following main conclusions: the quantile-predictive-regression approach using oil-price uncertainty as a predictor statistically outperforms the corresponding quantile-based constant-mean model for all ten countries at certain quantiles (capturing normal, bear, and bull markets), and over specific forecast horizons, compared to forecastability being detected for eight countries under the linear predictive model. Importantly, we detect forecasting gains in many more horizons (at particular quantiles) compared to the linear case. In addition, an oil-price uncertainty-based state-contingent spillover analysis reveals that the ten equity markets are connected more tightly at the upper regime, suggesting that heightened oil-market volatility erodes the benefits from diversification across equity markets.

Financial Time Series Modelling of Trends and Patterns in the Energy Markets

Precise recognition of a time series path is important to policy makers, statisticians, economists, traders, hedgers and speculators alike. The correct time series path is also a key ingredient in pricing models. This study uses daily futures prices of crude oil and other distillate fuels. This paper considers the statistical properties of energy futures and spot prices and investigates the trends that underlie the price dynamics in order to gain further insights into possible nuances of price discovery and energy market dynamics. The family of ARMA-GARCH models was explored. The trends depict time varying variability and persistence of oil price shocks. The return series conform to a constant mean model with GARCH variance.

Reliability Estimation of Existing Concrete Bridge Based on Bayesian Dynamic Model

It is of great significance to timely and accurately forecast the safety state of the bridge as far as the maintenance is concerned. Bayesian forecasting is a method of deriving posterior distribution in accord with the sampling information and prior information, where real time online forecasting is realized by means of recursive algorithm and the stationary assumption. Bayesian dynamic linear model is created to forecast the reliability of the bridge on the basis of the observed stress information of a bridge structure. According to the observed information, the model created is a superposition of constant mean model and seasonal effect model. The analysis of a practical example illustrates that Bayesian dynamic linear modes can provide an accurate real time forecast of the reliability of the bridge

Assessing uncertainty in soil organic carbon modeling across a highly heterogeneous landscape

To understand if soil carbon acts as a sink or source in the global carbon cycle it is not only important to make reliable estimates, but also determine upper and lower prediction bounds through uncertainty analysis that represent best and worst case conditions. In this study, the Bayesian geostatistics was applied to assess the uncertainty associated with the predictive models of SOC (top soils) in a large region — Florida, USA. Results showed that the Bayesian estimates of model parameters were comparable to the conventional geostatistical methods especially the restricted maximum likelihood (REML). The Bayesian prediction uncertainty assessment was encouragingly accurate based on the validation of 50 and 95% prediction intervals with the validation dataset. Generally, the width of prediction intervals increased with the posterior mean SOC predictions — large prediction intervals were found in the Everglades Agricultural Area (Histosols) and the wetland areas in the Suwannee River Basin. The Bayesian constant mean model (high model inadequacy) had marked prediction uncertainty which was reduced by accounting for the effects of environmental covariates in the Bayesian linear trend model (low model inadequacy), indicating that model inadequacy had a negative impact on prediction uncertainty. Analyses of factors impacting SOC prediction uncertainty suggest that effects that explained more of the SOC variance contributed more uncertainty to the SOC prediction. These findings are critical to quantify SOC stocks in the southeastern USA where a heterogeneous mosaic of high and low carbon in soils occurs ranging from 0.45 to 34.15kgm−2. Although this study considers only the topsoil, the results are valuable for global carbon cycling research. The uncertainty of SOC predictions not only enables identification of “hot” and “cold” spots in a landscape to mitigate and adapt to global climate change, but also informs scenario assessment to imagine possible carbon- rich, -neutral, and -poor futures.

Leverages and Influential Observations in a Regression Model with Autocorrelated Errors

This article deals with the general form of the hat matrix and the DFBETA measure to detect the influential observations and the leverages in the linear regression model with more than one regressor when the errors are from AR(1) and AR(2) processes. Previous studies dealing with the influential observations and the leverages in the constant mean model and regression through the origin model are obtained as special cases. To demonstrate the utility of the hat matrix and the DFBETA measure, two numerical examples based on the ice cream consumption data with AR(1) errors and the Fox-Hartnagel data with AR(2) errors are analyzed. The results show that the parameter of the autoregressive process affects the influential and leverage points.

On the existence of sports sentiment: the relation between football match results and stock index returns in Europe

We test for a relation between football match results and the specific national stock index returns during the period 1990–2006 by means of an event study approach. We employ two different econometric frameworks to cross-check our results and prevent them from being solely model driven: the constant mean model and a two-state Markov-switching market model. Both approaches find no significant results. Consequently, in a modified setup, we control for expectations about probable game results by applying a “surprise” variable, which is computed from betting odds and is integrated into a regression analysis. Again, there does not seem to be a connection between a specific national soccer team’s win or loss and stock index prices. In addition, through a few modifications in our empirical setup, we show how easy it would be to “produce” significant results. Our results are contrary to those of Ashton et al. (Appl Econ Lett 10:783–785, 2003) and Edmans et al. (J Finance 62(4):1967–1998, 2007) and support market efficiency.

Modelling the spatial distribution of Echinococcus multilocularis infection in foxes

Alveolar echinococcosis is a rare but fatal disease in humans and is caused by the fox tapeworm Echinococcus multilocularis. The densities of fox and grassland rodent populations and the interactions between them influence E. multilocularis transmission rates in Europe. Successful rabies control has caused fox populations and E. multilocularis prevalence rates to increase in many European countries. The potential increase of the infection pressure on the human population motivates the monitoring of the infection status of foxes over space and time. Detection of E. multilocularis antigen levels in fox faecal samples collected in the field might provide a pragmatic methodology for epidemiological surveillance of the infection status in wildlife hosts across large areas, as well as providing an indication of the spatial distribution of infected faeces contaminating the environment. In this paper, a spatial analysis of antigen levels detected in faeces collected in the Franche-Comté region of eastern France is presented. In Franche-Comté, rodent outbreaks have been observed to originate in areas rich in grassland. Spatial trends in fox infection levels were modelled here as a function of the composition ratio of grassland in the landscape derived from the CORINE land-cover map. Kriging models incorporating the grassland trend term were compared to a variety of models in which five alternative trend expressions were used: the alternative trend expressions included linear and quadratic polynomials on the x and y coordinates with and without a grassland term, and a constant mean model. Leave-one-out cross-validation indicated that the estimation errors of kriging with a trend models were significantly lower when the trend expression contained the grassland index term only. The relationship between observed and predicted antigen levels was strongest when the estimated range of autocorrelation was within the home range size of a single fox. The over-dispersion of E. multilocularis in foxes may therefore account for the majority of spatial autocorrelation locally, while regional trends can be successfully modelled as a function of habitat availability for intermediate hosts.

The Stochastic Properties of Systematic Risk for U.S. Mutual Funds

This paper investigates three possible processes by which mutual fund betas may develop over time. The paper proposes the idea that the underlying structure of fund returns can be interpreted as an indicator of management style. Due to the pressures placed on fund managers to remain within certain risk guidelines, laid out in the funds prospectus, over time the beta of an actively managed fund should exhibit mean reversion. We impose three different time-varying models on mutual fund betas using the Kalman filter algorithm. The three processes are: Firstly a random coefficient with constant mean model where any disturbance or shock to the funds systematic risk in one period has no effect on future beta values, possibly indicating an immediate re-alignment of the funds risk profile by the manager. Secondly an AR(1) model where shocks would have some persistence, and finally a random walk process where shocks will persist indefinitely. Our findings, over all funds in the sample, show an equal split between the random coefficient model and the random walk model. Furthermore, when we split the sample into fund classifications we find that the random walk model dominates the small company funds, suggesting these funds have adopted a more passive management style, possibly due to the reduced liquidity of the underlying stocks. The random coefficient model on the other hand dominates growth funds and speciality funds, indicating a more active management style is being used to counteract any shocks to the underlying systematic risk of the fund.

The deal of the century in Chile Endesa España's takeover of Enersis

We analyze the effect of the announcement of the tender offer made by Endesa España to control Enersis Chile through the Chispas holding structure. In this clinical study of the case, we summarize the salient points of the Chispa case—one of the most controversial in Chile—and obtain the abnormal returns to the shareholders of the target firm using three alternative models for robustness of results: the constant mean model, the market model, and the market model adjusted for non-synchronous trading problems. Contrary to expectations based on prior empirical research in the United States and United Kingdom, our results demonstrate the absence of positive cumulative abnormal returns (CARs) for Chispa stockholders during the takeover bidding event window. We present evidence in this case that the governance structure of the target firm led to this seeming anomaly and conclude that the generally accepted theories of corporate control and governance in the United States and United Kingdom do not automatically apply to developing countries with differing legal environments.

Optimum influence of initial observations in regression models with AR(2) errors

This article considers an optimal procedure of identifying the influential observations in a regression model with AR(2) errors. It develops some diagnostic techniques using a “hat matrix”. The likelihood ratio and F-test statistic have been discussed and an example of a constant mean model with AR(2) error shows its practical application in time series.

On statistical inference on the mean-variance efficient set

A proof of the asymptotic distribution of the estimated mean-variance frontier is given. A Bayesian prediction interval is derived for the capital asset pricing model. Numerical illustrations show that the prediction intervals for the CAPM are smaller than those for the constant mean model, if the fit of the CAPM is better than that of the constant mean model.

On detecting and estimating a major level or slope change in general exponential smoothing

AbstractExponential smoothing methods do not adapt well to a major level or slope change. In this paper, Bayesian statistical theory is applied to the dynamic linear model, altered by inclusion of dummy variables, and statistics are derived to detect such changes and to estimate both the change‐point and the size. The paper also gives test statistics for such problems related to exponential smoothing. The statistics are simple functions of exponentially weighted moving averages of the forecast errors, using the same discount factor used in the exponential smoothing. Gardner has derived an approximate test statistic to detect a mean change in the constant mean model. When the present results are applied to this model they give the exact statistic.