Conditional Autocorrelation Research Articles

Comparative study of conditional methods in slope reliability evaluation

This paper investigates the performances of three conditional methods in slope reliability evaluation with spatially variable soils, considering various sampling strategies and rotated transverse anisotropy. The first method is based on conditional random field (RF) (i.e., conditional RF model 1), where the fluctuation component of the RF model is simulated using Kriging interpolation. The second method is also based on conditional RF (i.e., conditional RF model 2), where matrix decomposition is implemented on the conditional autocorrelation matrix. The third method originates from Sobol’ index formulation, which is extended to enable the use of correlated input random variables. When sample points are distributed sparsely or near strata orientation, conditional RF model 1 would produce significantly smaller magnitude of uncertainty reduction and reliability index (β) than those by other conditional methods. Also, in these situations, the standard deviation of factor of safety (FS) after conditioning by conditional RF model 1 may be larger than the unconditional standard deviation of FS. This is unexpected in slope reliability evaluation. Besides, β by conditional RF simulation methods for reverse slopes may be smaller than that for dip slopes, which is against engineering experiences, while this issue cannot be found when using unconditional RF.

What Is the Conditional Autocorrelation on the Stock Market?

We derive lower and upper bounds on the conditional market autocorrelation index at various investment horizons without using the precise form of the utility function. The bounds are derived in terms of option prices and can be computed at daily frequency for any given horizon. The bounds incorporate all the information contained in the entire distribution of returns. We use options on the S&P 500 index to quantify the bounds and document that asset prices imply a negative upper bound on the market conditional autocorrelation index. The upper bound on the market conditional autocorrelation index is highly volatile, skewed, and exhibits fat tails. It varies from -28% to -3% and takes extremely negative values during crisis or recession periods while being close to zero during normal times. On average, the upper bound on the market conditional autocorrelation index is -14%. We also document that periods of extremely negative market conditional autocorrelation index coincide with periods of a high Sharpe ratio, and we show that leading asset pricing models cannot reproduce both the negative market conditional autocorrelation index and the negative average market conditional autocorrelation index implied by asset prices.

The Conditionally Autoregressive Hidden Markov Model (CarHMM): Inferring Behavioural States from Animal Tracking Data Exhibiting Conditional Autocorrelation

One of the central interests of animal movement ecology is relating movement characteristics to behavioural characteristics. The traditional discrete-time statistical tool for inferring unobserved behaviours from movement data is the hidden Markov model (HMM). While the HMM is an important and powerful tool, sometimes it is not flexible enough to appropriately fit the data. Data for marine animals often exhibit conditional autocorrelation, self-dependence of the step length process which cannot be explained solely by the behavioural state, which violates one of the main assumptions of the HMM. Using a grey seal track as an example, along with multiple simulation scenarios, we motivate and develop the conditionally autoregressive hidden Markov model (CarHMM), which is a generalization of the HMM designed specifically to handle conditional autocorrelation. In addition to introducing and examining the new CarHMM, we provide guidelines for all stages of an analysis using either an HMM or CarHMM. These include guidelines for pre-processing location data to obtain deflection angles and step lengths, model selection, and model checking. In addition to these practical guidelines, we link estimated model parameters to biologically meaningful quantities such as activity budget and residency time. We also provide interpretations of traditional "foraging" and "transiting" behaviours in the context of the new CarHMM parameters.

Exploring the Influence of Built Environment on Car Ownership and Use with a Spatial Multilevel Model: A Case Study of Changchun, China.

Although the impacts of built environment on car ownership and use have been extensively studied, limited evidence has been offered for the role of spatial effects in influencing the interaction between built environment and travel behavior. Ignoring the spatial effects may lead to misunderstanding the role of the built environment and providing inconsistent transportation policies. In response to this, we try to employ a two-step modeling approach to investigate the impacts of built environment on car ownership and use by combining multilevel Bayesian model and conditional autocorrelation (CAR) model to control for spatial autocorrelation. In the two-step model, the predicting car ownership status in the first-step model is used as a mediating variable in the second-step car use model. Taking Changchun as a case study, this paper identifies the presence of spatial effects in influencing the effects of built environment on car ownership and use. Meanwhile, the direct and cascading effects of built environment on car ownership and use are revealed. The results show that the spatial autocorrelation exists in influencing the interaction between built environment and car dependency. The results suggest that it is necessary for urban planners to pay attention to the spatial effects and make targeted policy according to local land use characteristics.

Does higher-frequency data always help to predict longer-horizon volatility?

No. Conditional autocorrelation in realized shocks due to misspecification in expected return process affects the relative performance of longer-horizon volatility predictions of models using different frequencies of data. This is because, for multi-step forecasts of volatility, small violations of residual serial independence are compounded in temporal aggregation. In this paper, we show that the conditional autocorrelation in return residuals is a strong predictor of the relative performance of different frequency models of volatility. When the conditional autocorrelation is high, the higher frequency model performs markedly worse than its lower frequency counterpart. Empirically, we show that residual autocorrelation exists in the large cross section of stocks at any given point in time, and that this misspecification can substantially decrease the accuracy of multi-step forecasts generated by higher frequency models. Comparing the monthly volatility predictions from daily models and monthly models, we show that there is a trade-off between the gains from high-frequency data and the susceptibility of its multi-period ahead forecasts to returns model misspecification.

The Relationship Between Public Investment To GDP Ratio And External Debt Stocks In Kenya

Debt is a two-edged sword. External borrowing for productive investment is associated with macroeconomics stability, increased domestic savings, improved welfare and enhanced debt repayment ability; while over accumulation of debt is associated with increased repayment and debt-service costs, depressed domestic investment, crowding out of private investment and increased vulnerability to debt crisis. The paper sought to establish the relationship between public investment to GDP ratio and external debt in Kenya over the period of 1972-2012. The study used time-series data for public investment, GDP, and external debt from IMF International Financial Statistics database. All data was evaluated, cross-checked, compared and critically analyzed. To ensure that the data does not violate the assumptions of classical linear regression model (CLRM) and test for stationarity, the study tested for unit tests using Augmented Dickey-Fuller (ADF). To test for the verifiability of the estimated long run model, additional diagnostic tests, notably: heteroskedasticity, autoregressive conditional heteroskedasticity (ARCH), autocorrelation and normality, were carried out before regression was used to determine the relationship between external debt and inflation. The gauge the relationship between the external debt and growth in Kenya, a simple open macroeconomic debt growth model will be applied. Regression analysis of Ordinary Least Squares (OLS) will be used to determine the relationship between public investment to GDP ratio and external debt over the 1972 and 2012 period in Kenya. The correlation findings indicated a Spearman's correlation coefficient of -0.5618 with a P value of 0.0001, implying a negative and significant correlation. The regression results show an R square of 0.0067 indicating that 0.7 percent of variations in external debt are explained by variations in total investment/GDP ratio, F statistic of 0.26 and a p value of 0.1828. The study recommends sustaining lower inflation rates through tight fiscal and monetary policies, financing of budget deficit from non- inflationary sources, implementation of price stabilization program by subsiding basic food items, and effectively managing external debt.

A Gaussian random field model for similarity-based smoothing in Bayesian disease mapping.

Conditionally specified Gaussian Markov random field (GMRF) models with adjacency-based neighbourhood weight matrix, commonly known as neighbourhood-based GMRF models, have been the mainstream approach to spatial smoothing in Bayesian disease mapping. In the present paper, we propose a conditionally specified Gaussian random field (GRF) model with a similarity-based non-spatial weight matrix to facilitate non-spatial smoothing in Bayesian disease mapping. The model, named similarity-based GRF, is motivated for modelling disease mapping data in situations where the underlying small area relative risks and the associated determinant factors do not vary systematically in space, and the similarity is defined by "similarity" with respect to the associated disease determinant factors. The neighbourhood-based GMRF and the similarity-based GRF are compared and accessed via a simulation study and by two case studies, using new data on alcohol abuse in Portugal collected by the World Mental Health Survey Initiative and the well-known lip cancer data in Scotland. In the presence of disease data with no evidence of positive spatial correlation, the simulation study showed a consistent gain in efficiency from the similarity-based GRF, compared with the adjacency-based GMRF with the determinant risk factors as covariate. This new approach broadens the scope of the existing conditional autocorrelation models.

Shocks to Product Networks and Post-Earnings Announcement Drift

This paper examines whether shocks to less visible product market network peers explain industry level post-earnings announcement drift (IPEAD). On the real-side, we find that peer earnings shocks propagate slowly through the peer network, creating a complex and conditional autocorrelation structure in earnings shocks. This impacts the financial-side, and IPEAD arises only when shocked peers are less visible in the network and when shocks are driven by persistent supply-side shocks to expenses rather than by demand-side shocks to sales. In addition, IPEAD is particularly strong when 10-K expense disclosures are opaque. Collectively, our results suggest that inattention to less visible peers, complex autocorrelation in earnings shocks, and a poor informational environment on the expense side are likely channels that generate IPEAD. IPEAD returns are economically large in subsamples motivated by this explanation.

Does Higher Frequency Data Always Help to Forecast Longer-Horizon Volatility?

No. Conditional autocorrelation in realized shocks due to misspecification in expected return process affects the relative performance of longer-horizon volatility predictions of models using different frequencies of data. This is because, for multi-step forecasts of volatility, small violations of residual serial independence are compounded in temporal aggregation. In this paper, we show that the conditional autocorrelation in return residuals is a strong predictor of the relative performance of different frequency models of volatility. When the conditional autocorrelation is high, the higher frequency model performs markedly worse than its lower frequency counterpart. Empirically, we show that residual autocorrelation exists in the large cross section of stocks at any given point in time, and that this misspecification can substantially decrease the accuracy of multi-step forecasts generated by higher frequency models. Comparing the monthly volatility predictions from daily models and monthly models, we show that there is a trade-off between the gains from high-frequency data and the susceptibility of its multi-period ahead forecasts to returns model misspecification.

Mean Reversion Based on Autocorrelation: A Comparison Using the S&P 100 Constituent Stocks and the 100 Most Liquid ETFs

The motivation for this paper is to show that even a simple strategy based on conditional autocorrelation can give traders an edge. Our simple mean reversion strategy takes the position in a pair consisting of Exchange traded funds (ETFs) or shares based on the normalized previous period's return and the actual conditional autocorrelation. We conclude that ETFs are more suitable financial instrument for our strategy than stocks. Yet, another finding is that the strategy is significantly improved when we use half-daily (open-close-open-...) sampling frequency as opposed to the daily one (close-close). Information ratios after accounting for transaction costs (TC) range between 1.4 and 2.8 for ETF pairs at half-daily sampling frequency.

Using the autoregressive conditional duration model to analyse the process of default contagion

Credit events are not independent, and the contagion effect is very common. The seriousness of the contagion effect depends on the change in the default contagion duration before and after credit events. This study uses the Autoregressive Conditional Duration (ACD) model to capture the durations of a series of credit events and to study the characteristics of a default duration series. The empirical samples are listed and Over-The-Counter (OTC) companies in Taiwan. The Moving Block Bootstrap (MBB) in Liu and Singh (1992) is employed to copy the sample data. The sample period is from October 1982 to December 2007. The results show that, in the entire sample and subsamples of the electronic information industry and construction industry, the default duration series demonstrates the conditional autocorrelation and cluster effect. The ACD model helps capture the contagion effect of credit events.

Avaliação de fundos de investimento utilizando o Índice de Sharpe AR-GARCH-M

The Sharpe ratio, a well known and widely used measure for ex post facto performance evaluation of diversified financial asset portfolios, has an important limitation, the assumption of normally and independently distributed (NID) daily excess log-returns. This paper proposes an econometric Sharpe ratio and an estimation method derived from an AR-GARCH-M model. The proposed Sharpe ratio is compared to the standard Sharpe ratio. Daily log-returns of mutual funds in the Brazilian market were used and Sharpe ratios were estimated for each. The Spearman rank correlation coefficient between proposed and standard Sharpe ratios was found to be positive, but the ratios led to different conclusions about the performance of the funds. The proposed Sharpe ratio relaxes the NID hypothesis for log-returns and includes as stylized facts conditional heteroskedasticity, autocorrelation and dependence between log-return and

Return autocorrelations in the stock markets

This article investigates the return autocorrelation in four stock markets around the Asia-Pacific rim: the USA, Japan, Taiwan and South Korea. The results indicate that there are conditional return autocorrelation in Taiwan's and South Korea's stock markets for daily data. Moreover, there are negative relationships between autocorrelation and two factors (trading volume and return volatility) significantly in Taiwan and South Korea, implying that the stock markets in Taiwan and South Korea are not as efficient as those in developed countries (the USA and Japan). For weekly data, however, none of the above four markets has significant return autocorrelation.

Conditional Autocorrelation and Stock Market Integration in the Asia-Pacific

This chapter considers the relationship between stock market autocorrelation and (i) the presence of international investors which is proxied by the level of capital market integration and (ii) stock market volatility. Drawing from a sample of nine Asia-Pacific stock indices, significant evidence of a relationship between the presence of international investors and the level of stock market autocorrelation is found. This evidence is consistent with the view that international investors are positive feedback traders. Robustness testing of this model suggests that the trading strategy of international investors changed as a result of the Asian currency crisis. The evidence for the role of volatility in explaining autocorrelation is, however, is generally weak and varies across the sample countries.

Evidence of an asymmetry in the relationship between volatility and autocorrelation

This paper focuses on the general determinants of autocorrelation and the relationship between autocorrelation and volatility in particular. Using UK stock market index and individual stock price data, a multivariate generalized autoregressive conditional heteroskedasticity (M-GARCH) model is used to generate estimates of conditional autocorrelation. The covariance equation of this model is modified to include the potential determinants of autocorrelation including volatility, which is proxied using the time series of filtered probabilities of a Markov regime switching model. Consistent with the previous literature, this paper documents a negative relationship between volatility and autocorrelation. The results suggest that an asymmetry exists in this relationship which is attributed to the constraints placed on short selling.

An Investigation of Conditional Autocorrelation and Cross-Autocorrelation in Emerging Markets

We extend the feedback trader model by including a cross-market feedback trader. Our analysis of eighteen emerging markets suggests that there exists both positive and negative feedback traders in the markets and their activity is related to stock index return volatility. For cross-market feedback traders however, we show that, although cross-market autocorrelation among emerging markets is high and variable, the hypothesized negative relationship between cross-market autocorrelation and volatility is much weaker than its domestic counterpart.

Modeling conditional return autocorrelation

Empirical estimates of conditional return autocorrelation are generated over the period 1973 to 2000 for S&P500 index data, as well as for a small selection of individual U.S. stocks. We find that conditional autocorrelation is highly variable, and these dynamics are consistent with changes in point autocorrelation estimates generated in various subperiods. The conditional autocorrelation estimates for some stocks exhibited a pattern of mean reversion, while for others, evidence of long-term trends and structural breaks was found. While we were unable to uncover what characteristics drive the nature of these autocorrelation patterns, our analysis ruled out industry, investor type or degree of internationalisation as explanations.

The Determinants of Conditional Autocorrelation in Stock Returns

AbstractWe investigate whether return volatility, trading volume, return asymmetry, business cycles, and day‐of‐the‐week are potential determinants of conditional autocorrelation in stock returns. Our primary focus is on the role of feedback trading and the interplay of return volatility. We present empirical evidence using conditional autocorrelation estimates generated from multivariate generalized autoregressive conditional heteroskedasticity (M‐GARCH) models for individual U.S. stock and index data. In addition to return volatility, we find that trading volume and market returns are important in explaining the time‐varying patterns of return autocorrelation.