In-sample Tests Research Articles

Continuous glucose monitoring for the prediction of posttransplant diabetes mellitus and impaired glucose tolerance on day 90 after kidney transplantation—A prospective proof-of-concept study

Posttransplant diabetes mellitus (PTDM) and prediabetes represent serious complications after kidney transplantation and are associated with increased cardiovascular morbidity and mortality. We assessed the predictive performance of continuous glucose monitoring (CGM) compared with plasma glucose and hemoglobin A1c in 46 kidney transplant recipients (KTRs) without known preexisting diabetes mellitus. CGM (14-day recording duration) was performed on days 8, 30, 45, 60, 90, and 180 posttransplant. Eight patients (17%) developed PTDM and nine (20%) impaired glucose tolerance (IGT), as diagnosed by oral glucose tolerance test (oGTT)–derived 2-hour plasma glucose (2hPG) or glucose-lowering therapy on day 90. CGM-readouts percent of time >140 mg/dL (%TAR (140 mg/dL)) and percent of time >180 mg/dL (%TAR (180 mg/dL)) showed excellent in-sample test characteristics regarding PTDM from day 8 onward (days 8-90 receiver operating characteristic area under the curve: 0.88-0.99) and regarding PTDM/IGT with the commencement of maintenance immunosuppression from day 30 onward (days 30-90 receiver operating characteristic area under the curve: 0.88-0.91). Exploratory CGM-%TAR (140 mg/dL)–screening thresholds of 31.8% on day 8 and 13.2% on day 30 yielded sensitivities/specificities of 88%/83% for PTDM and 94%/78% for PTDM/IGT on day 90, respectively. Although our findings need to be replicated in studies with larger sample sizes, CGM bears promising potential to facilitate clinical practice and research regarding PTDM.

Can U.S. macroeconomic indicators forecast cryptocurrency volatility?

This research examines the ability of 28 U.S. macroeconomic variables to forecast the volatility of six cryptocurrencies. In- and out-of-sample analyses are performed to validate their forecasting ability. Our analysis shows that during the full-sample period, 15 variables display forecasting ability, while post-COVID-19 period, this number is 17. Among these variables, the most influential include the consumer confidence index, leading economic index, consumer price index, U.S. exports and U.S. imports. Importantly, the predictive ability of these variables appears to have strengthened during the post-COVID-19 period. The out-of-sample results confirm the effectiveness of those macroeconomic variables in the in-sample tests. Furthermore, the robustness test reveals that incorporating these U.S. macroeconomic variables can enhance the performance of the GARCH volatility model. In this study, combination methods are used to enhance forecasting stability and are proven to have good forecasting ability. Our research also indicates that integrating global macroeconomic variables can enhance forecasting ability while recognizing the valuable information provided by U.S. macroeconomic variables. Additionally, we find that variables such as the short-term government bond yield and the M1 money supply emerge as important predictors of cryptocurrency bubbles.

Analysing implied volatility smirk to predict the US stock market crash during the global financial crisis

This study analyses the presence of implied volatility smirk (IVS) and its predictability of the US stock market crash during the Global Financial Crisis (GFC) through the in-sample and out-of-sample tests. The in-sample investigation was conducted for 18 cases (cases 1–18) to confirm the development of IVS during GFC (2007–2009). It also examined another 18 cases (cases 19–36) to ensure the absence of the IVS in the post-GFC period (2010–2011). Finally, an out-of-sample test analysed 63 cases (cases 37–99) to assess the predictability of IVS for the stock market crash during the GFC. The study reveals several critical findings. The in-sample test results show the negative return from simultaneous trading of out-of-the-money put options (OTMP) and at-the-money call options (ATMC) due to out-of-the-money put options implied volatility (OTMPIV) is higher than at-the-money call options implied volatility (ATMCIV) for all 18 cases (cases 1–18), confirming the development of IVS during GFC. However, findings of the in-sample test for cases 19–36 reveal the positive return from simultaneous trading of OTMP and ATMC because of the lower value of OTMPIV compared to ATMCIV, ensuring no occurrence of IVS in the post-GFC period. Finally, only 13 out of 63 cases (from cases 37–99) under the out-of-sample test show the IVS can forecast negative returns in an abnormal stock market. Further, the predictability of IVS for the US stock market crash depends on the maturity of options, forecast horizon, and options trading period

Data-Driven Chance-Constrained Planning for Distributed Generation: A Partial Sampling Approach

The planning of distributed energy resources has been challenged by the significant uncertainties and complexities of distribution systems. To ensure system reliability, one often employs chance-constrained programs to seek a highly likely feasible solution while minimizing certain costs. The traditional sample average approximation (SAA) is commonly used to represent uncertainties and reformulate a chance-constrained program into a deterministic optimization problem. However, the SAA introduces additional binary variables to indicate whether a scenario sample is satisfied and thus brings great computational complexity to the already challenging distributed energy resource planning problems. In this paper, we introduce a new paradigm, i.e., the partial sample average approximation (PSAA) using real data, to improve computational tractability. The innovation is that we sample only a part of the random parameters and introduce only continuous variables corresponding to the samples in the reformulation, which is a mixed-integer convex quadratic program. Our extensive experiments on the IEEE 33-Bus and 123-Bus systems show that the PSAA approach performs better than the SAA because the former provides better solutions in a shorter time in in-sample tests and provides better guaranteed probability for system reliability in out-of-sample tests. All the data used in the experiments are real data acquired from Pecan Street Inc. and ERCOT. More importantly, our proposed chance-constrained model and PSAA approach are general enough and can be applied to solve other valuable problems in power system planning and operations. Thus, this paper fits one of the journal scopes: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Distribution System Planning in Power System Planning and Implementation</i> .

Multi-Asset Option Pricing Using Normal Tempered Stable Processes with Stochastic Correlation

In this article, the authors develop a new multi-asset option pricing model where underlying dynamics are assumed to follow the normal tempered stable (NTS) process and its correlation structure evolves over time. The model is constructed by extending the constant correlation term in the previous NTS framework to the stochastic correlation making use of the Ornstein-Uhlenbeck process. We then derive its closed-form solution under the risk-neutral measure and apply it to an empirical study of a quanto option. The in-sample tests and calibration practices justify our model specification reflecting the empirical stylized facts on asset returns such as heavy tails, skewness, kurtosis, and stochastic correlation. Building on the empirical results, we can also identify the presence of stochastic correlation in the risk-neutral world.

A closer look at the regime-switching evidence of bull and bear markets

Studies that use Markov-switching models to identify bull and bear markets indicate that conditional expected market returns display substantial variation over time. However, I find that in-sample tests fail to produce any evidence that these models predict market returns. To explain this finding, I show that the estimated expected return for the bull regime must differ from the estimated expected return for the bear regime in order to capture skewness. Because market returns display negative skewness, the Markov-switching estimates of conditional expected returns will typically vary over time, regardless of whether there is any actual variation in conditional expected returns.

Prediction of corporate financial distress based on digital signal processing and multiple regression analysis

Abstract In order to reduce the default rate of corporate bond market, the author proposes to use digital signal processing and multiple regression analysis to study the prediction system of financial distressed companies. First, design the research method, Logistic regression model is the most commonly used multivariate statistical method when modeling binary dependent variables, it can solve the problem of nonlinear classification, it has no specific requirements for the distribution of variables, and the accuracy of judgment is high. The author selects 32 financial ratios from the perspectives of solvency, operating ability, profitability, development ability, per share index, and risk level. Taking special treatment (ST) due to abnormal financial status as a sign of financial distress in listed companies, when selecting samples, the matching principle is adopted to select non-ST companies as matching samples. Two methods of logistic regression and support vector machine are used for empirical testing, and both in-sample testing and out-of-sample prediction are performed. The results show that when using the logistic regression method, the propensity to default indicator (TTD) reflected in the text content, it can indeed improve the out-of-sample prediction accuracy of the financial distress prediction model, and it is consistent with the in-sample test, this is mainly reflected in the reduction of the first type of error, that is, the probability of misjudging a financially distressed company as a normal company. Changes in the proportions have little effect on the relative importance of financial ratio variables when modeling with support vector machines, the propensity to default indicator (TTD) entered the top ten important variables in both ratios, and ranked fourth among all indicators when the ratio was 1:2, importance has increased significantly. From this it can be seen that, when using support vector machine to build a financial distress prediction model, the propensity to default indicator (TTD) has played an important role. In the case of using the support vector machine method, adding the default tendency indicator (TTD) reflected by the text information can also improve the accuracy of the financial distress prediction model.

Modelling the dynamics of stock market in the gulf cooperation council countries: evidence on persistence to shocks

This study examines the statistical properties required to model the dynamics of both the returns and volatility series of the daily stock market returns in six Gulf Cooperation Council countries, namely Bahrain, Oman, Kuwait, Qatar, Saudi Arabia, and the United Arab Emirates, under different financial and economic circumstances. The empirical investigation is conducted using daily data from June 1, 2005 to July 1, 2019. The analysis is conducted using a set of double long-memory specifications with some significant features such as long-range dependencies, asymmetries in conditional variances, non-linearity, and multiple seasonality or time-varying correlations. Our study indicates that the joint dual long-memory process can adequately estimate long-memory dynamics in returns and volatility. The in-sample diagnostic tests as well as out-of-sample forecasting results demonstrate the prevalence of the Autoregressive Fractionally Integrated Moving Average and Hyperbolic Asymmetric Power Autoregressive Conditional Heteroskedasticity modeling process over other competing models in fitting the first and the second conditional moments of the market returns. Moreover, the empirical results show that the proposed model offers an interesting framework to describe the long-range dependence in returns and seasonal persistence to shocks in conditional volatility and strongly support the estimation of dynamic returns that allow for time-varying correlations. A noteworthy finding is that the long-memory dependencies in the conditional variance processes of stock market returns appear important, asymmetric, and differ in their volatility responses to unexpected shocks. Our evidence suggests that these markets are not completely efficient in processing regional news, thus providing a sound alternative for regional portfolio diversification.

Exchange rate return predictability in times of geopolitical risk

We develop the hypothesis that geopolitical risk predicts exchange rate returns. Using data on 17 countries, we demonstrate that the information content embedded in geopolitical risk is economically useful and can improve the forecast accuracy of exchange rate returns. We show that geopolitical risk predicts 10 out of 17 (59%) exchange rate returns in in-sample tests while in out-of-sample tests predictability is found for 88% of currencies. Buy and sell signals generated from our model lead to higher returns compared to the historical average model. Our model delivers excess profits relative to the benchmark model in 11 out of 17 (65%) currencies.

Market efficiency in the age of big data

Modern investors face a high-dimensional prediction problem: thousands of observable variables are potentially relevant for forecasting. We reassess the conventional wisdom on market efficiency in light of this fact. In our equilibrium model, N assets have cash flows that are linear in J characteristics, with unknown coefficients. Risk-neutral Bayesian investors learn these coefficients and determine market prices. If J and N are comparable in size, returns are cross-sectionally predictable ex post. In-sample tests of market efficiency reject the no-predictability null with high probability, even though investors use information optimally in real time. In contrast, out-of-sample tests retain their economic meaning.

Do oil-price shocks predict the realized variance of U.S. REITs?

We examine, using aggregate and sectoral U.S. data for the period 2008–2020, the predictive power of disentangled oil-price shocks for Real Estate Investment Trusts (REITs) realized market variance via the heterogeneous auto-regressive realized variance (HAR-RV) model. In-sample tests show that demand and financial-market-risk shocks contribute to a larger extent to the overall fit of the model than supply shocks, where the in-sample transmission of the impact of the shocks mainly operates through their significant effects on realized upward (“good”) variance. Out-of-sample tests corroborate the significant predictive value of demand and financial-market-risk shocks for realized variance and its upward counterpart at a short, medium, and long forecast horizon, for various recursive-estimation windows, for realized volatility (that is, the square root of realized variance), for a shorter sub-sample period that excludes the recent phase of exceptionally intense oil-market turbulence, and for an extended benchmark model that features realized higher-order moments, realized jumps, and a leverage effect as control variables. We also study a quantiles-based extension of the HAR-RV model, and we analyze the economic benefits of using shocks for realized-variance forecasting.

Image classification of marine-terminating outlet glaciers in Greenland using deep learning methods

Abstract. A wealth of research has focused on elucidating the key controls on mass loss from the Greenland and Antarctic ice sheets in response to climate forcing, specifically in relation to the drivers of marine-terminating outlet glacier change. The manual methods traditionally used to monitor change in satellite imagery of marine-terminating outlet glaciers are time-consuming and can be subjective, especially where mélange exists at the terminus. Recent advances in deep learning applied to image processing have created a new frontier in the field of automated delineation of glacier calving fronts. However, there remains a paucity of research on the use of deep learning for pixel-level semantic image classification of outlet glacier environments. Here, we apply and test a two-phase deep learning approach based on a well-established convolutional neural network (CNN) for automated classification of Sentinel-2 satellite imagery. The novel workflow, termed CNN-Supervised Classification (CSC) is adapted to produce multi-class outputs for unseen test imagery of glacial environments containing marine-terminating outlet glaciers in Greenland. Different CNN input parameters and training techniques are tested, with overall F1 scores for resulting classifications reaching up to 94 % for in-sample test data (Helheim Glacier) and 96 % for out-of-sample test data (Jakobshavn Isbrae and Store Glacier), establishing a state of the art in classification of marine-terminating glaciers in Greenland. Predicted calving fronts derived using optimal CSC input parameters have a mean deviation of 56.17 m (5.6 px) and median deviation of 24.7 m (2.5 px) from manually digitised fronts. This demonstrates the transferability and robustness of the deep learning workflow despite complex and seasonally variable imagery. Future research could focus on the integration of deep learning classification workflows with free cloud-based platforms, to efficiently classify imagery and produce datasets for a range of glacial applications without the need for substantial prior experience in coding or deep learning.

Language Commonality and Sell-Side Information Production

I study the effects of language commonality (i.e., sharing a native language) on information production in financial markets. Using a hand-collected data set on the prevalent dialects for 2,091 cities (counties) in China, I identify the effects of language commonality separately from those of shared hometown and geographic proximity. In in-sample tests, language commonality between analysts and CEOs increases the return of trading on analysts’ recommendations by 5.5%. The results mainly stem from less intelligible dialects. Broadly speaking, language commonality can alleviate communication frictions when nonnative languages are used in professional settings. This paper was accepted by Gustavo Manso, finance.

In-sample tests of predictability are superior to pseudo-out-of-sample tests, even when data mining

This paper analyses straightforward Bonferroni adjustments to critical values of in-sample tests of predictability, when data mining is used to search across models. Unlike conventional pseudo-out-of-sample tests, these in-sample tests have stable family-wise error rates (FWERs) when searching for models that predict well. Furthermore, when data mining, these in-sample tests have more power than pseudo-out-of-sample tests for identifying true predictability.

Forecasting Bitcoin returns: is there a role for the US–China trade war?

Previous studies have provided evidence that trade-related uncertainty tends to predict an increase in Bitcoin returns. In this paper, we extend the related literature by examining whether the information on the US–China trade war can be used to forecast the future path of Bitcoin returns, controlling for various explanatory variables. We apply ordinary least square (OLS) regression, support vector regression (SVR) and least absolute shrinkage and selection operator (LASSO) techniques that stem from the field of machine learning, and we find weak evidence of the role of the trade war in forecasting Bitcoin returns. Given that out-of-sample tests are more reliable than in-sample tests, our results tend to suggest that future Bitcoin returns are unaffected by trade-related uncertainties, and investors can use Bitcoin as a safe haven in this context.

Forecasting the U.S. stock volatility: An aligned jump index from G7 stock markets

We propose new jump indexes that are aligned with the jump information on the G7 stock markets to predict the U.S. stock market volatility. We present several noteworthy findings. First, in-sample tests indicate that the impacts of the aligned jump indexes on one-step-ahead U.S. stock market volatility are significantly negative. Second, the aligned jump index based on the Partial Least Squares (PLS) approach remarkably exhibits a higher predictive power, showing that this new jump index can contain much more predictive information than jump itself or jump index based on the Principal Component Analysis (PCA). Third, the results are consistent across the direction-of-change test and a variety of robustness tests. Consequently, this research provides a new insight and constructs a powerful predictive variable for the U.S. stock market volatility forecasting.

Using the area under an estimated ROC curve to test the adequacy of binary predictors

ABSTRACTWe consider using the area under an empirical receiver operating characteristic curve to test the hypothesis that a predictive index combined with a range of cutoffs performs no better than pure chance in forecasting a binary outcome. This corresponds to the null hypothesis that the area in question, denoted as AUC, is 1/2. We show that if the predictive index comes from a first-stage regression model estimated over the same data set, then testing the null based on the standard asymptotic normality results leads to severe size distortion in general settings. We then analytically derive the proper asymptotic null distribution of the empirical AUC in a special case; namely, when the first-stage regressors are Bernoulli random variables. This distribution can be utilised to construct a fully in-sample test of with correct size and more power than out-of-sample tests based on sample splitting, though practical application becomes cumbersome with more than two regressors.

Short term prediction of extreme returns based on the recurrence interval analysis

Being able to predict the occurrence of extreme returns is important in financial risk management. Using the distribution of recurrence intervals—the waiting time between consecutive extremes—we show that these extreme returns are predictable in the short term. Examining a range of different types of returns and thresholds we find that recurrence intervals follow a q-exponential distribution, which we then use to theoretically derive the hazard probability . Maximizing the usefulness of extreme forecasts to define an optimized hazard threshold, we indicate a financial extreme occurring within the next day when the hazard probability is greater than the optimized threshold. Both in-sample tests and out-of-sample predictions indicate that these forecasts are more accurate than a benchmark that ignores the predictive signals. This recurrence interval finding deepens our understanding of reoccurring extreme returns and can be applied to forecast extremes in risk management.

Monitoring Structural Stability of Dynamic Factor Models

This paper aims to test the out-of-sample structural changes of the factor augmented regression (FAR) model as compared to the in-sample structural stability tests considered in Breitung and Eickmeier (2011), and Chen, Dolado, and Gonzalo (2011). We extends the fluctuation monitoring test of Chu, Stinchcombe, and White (1996) by proposing a rescaled monitoring test to deal with the scenario where there is a large number of cross-section series, N, each with T observations, and each series has some predictive ability for the variable of interest as in the study of Bai and Ng (2006). We recognize the difficulties of monitoring the predictive ability of the estimated factors by pointing out the randomness nature of estimated factor from principle component analysis (PCA) when new observation arrives sequentially. Nevertheless, under the null hypothesis of no structural change, a new rescaled monitoring test is proposed and proved to behave as a Brownian bridge asymptotically. Thus, the critical values suggested in Chu et al. (1996) can be applied to the dynamce factor model along with our method. Furthermore, the finite sample of performance of the proposed test is promising. We also apply the new test to the data of Ludvigson and Ng (2009) for monitoring the stability of the factor factor for forecasting U.S. industrial production (IP).

Dynamic robust portfolio selection with copulas

This paper considers two dynamic robust portfolio optimization models based on the framework of Kakouris and Rustem(2014). We use copula-GARCH and DCC copulas approaches to capture the dynamics of the distribution of the returns. We compare our proposed methods with the static robust and nonrobust portfolio optimization models based on the CSI300 data. The experimental study shows that the dynamic WCVaR models perform better in out-of-sample tests when considering the uncertainty in the estimated model. The static nonrobust method produces higher returns in the in-sample tests, since there is no room to capture model uncertainty.