Repeated Confidence Intervals Under Fractional Brownian Motion in Long-Term Clinical Trials

Repeated confidence interval (RCI) is an important tool for design and monitoring of group sequential trials according to which we do not need to stop the trial with planned statistical stopping rules. In this article, we derive RCIs when data from each stage of the trial are not independent thus it is no longer a Brownian motion (BM) process. Under this assumption, a larger class of stochastic processes fractional Brownian motion (FBM) is considered. Comparisons of RCI width and sample size requirement are made to those under Brownian motion for different analysis times, Type I error rates and number of interim analysis. Power family spending functions including Pocock, O'Brien-Fleming design types are considered for these simulations. Interim data from BHAT and oncology trials is used to illustrate how to derive RCIs under FBM for efficacy and futility monitoring.     

Operating Characteristics for Group Sequential Trials Monitored Under Fractional Brownian Motion

Brownian motion has been used to derive stopping boundaries for group sequential trials, however, when we observe dependent increment in the data, fractional Brownian motion is an alternative to be considered to model such data. In this article we compared expected sample sizes and stopping times for different stopping boundaries based on the power family alpha spending function under various values of Hurst coefficient. Results showed that the expected sample sizes and stopping times will decrease and power increases when the Hurst coefficient increases. With same Hurst coefficient, the closer the boundaries are to that of O'Brien-Fleming, the higher the expected sample sizes and stopping times are; however, power has a decreasing trend for values start from H = 0.6 (early analysis), 0.7 (equal space), 0.8 (late analysis). We also illustrate study design changes using results from the BHAT study.     

Repeated confidence intervals and prediction intervals using stochastic curtailment under fractional Brownian motion

ABSTRACT

Repeated confidence intervals (RCIs) and prediction intervals (PIs) can be used for the design and monitoring of group sequential trials. Stochastically curtailed tests (SCTs) under fractional Brownian motion (FBM) have been studied for the interim analysis of clinical trials (Zhang et al., 2015 Zhang, Q., Lai, D.J., Davis, B.R. (2015). Stochastically curtailed tests under fractional Brownian motion. Commun. Stat. Theory Methods. 44(5):1053–1064.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]). In this article, we derive RCIs and PIs based on SCTs under FBM for one-sided derived tests (Jennison and Turnbull, 2000 Jennison, C., Turnbull, B.W. (2000). Group Sequential Methods with Applications to Clinical Trials. Boca Raton, London: Chapman and Hall. [Google Scholar]). Comparisons of RCI width and sample size requirement are made to those under Brownian motion (BM) and to those of Pocock and O'Brien-Fleming design types for various type I, type II error rates, and number of interim analyses. Interim data from Beta-Blocker Heart Attack Trial are used to illustrate how to design and monitor clinical trials using these RCIs and PIs under FBM. Results show that these one-sided derived tests based on SCTs have narrower final confidence intervals and require smaller sample sizes than those using classical group sequential designs. The Hurst parameter has more impact on the RCI width than on the sample size requirements for the proposed designs.     

Fractional Brownian motion and long term clinical trial recruitment

Prediction of recruitment in clinical trials has been a challenging task. Many methods have been studied, including models based on Poisson process and its large sample approximation by Brownian motion (BM); however, when the independent incremental structure is violated for BM model, we could use fractional Brownian motion to model and approximate the underlying Poisson processes with random rates. In this paper, fractional Brownian motion (FBM) is considered for such conditions and compared to BM model with illustrated examples from different trials and simulations.     

Group sequential tests under fractional Brownian motion in monitoring clinical trials

Group sequential tests have been effective tools in monitoring long term clinical trials. There have been several popular discrete sequential boundaries proposed for modeling interim analysis of clinical trials under the assumption of Brownian motion for the stochastic processes generated from test statistics. In this paper, we study the five sequential boundaries in Lan and DeMets (Biometrika 70:659–663, 1983) under the fractional Brownian motion. The fractional Brownian includes the classic Brownian motion as a special case. An example from a real data set is used to illustrate the applications of the boundaries.     

Conditional moving linear regression: Modeling the recruitment process for ALLHAT

Effective recruitment is a prerequisite for successful execution of a clinical trial. ALLHAT, a large hypertension treatment trial (N = 42,418), provided an opportunity to evaluate adaptive modeling of recruitment processes using conditional moving linear regression. Our statistical modeling of recruitment, comparing Brownian and fractional Brownian motion, indicates that fractional Brownian motion combined with moving linear regression is better than classic Brownian motion in terms of higher conditional probability of achieving a global recruitment goal in 4-week ahead projections. Further research is needed to evaluate how recruitment modeling can assist clinical trialists in planning and executing clinical trials.     

Is a Brownian Motion Skew?

We study the asymptotic behaviour of the maximum likelihood estimator corresponding to the observation of a trajectory of a skew Brownian motion, through a uniform time discretization. We characterize the speed of convergence and the limiting distribution when the step size goes to zero, which in this case are non‐classical, under the null hypothesis of the skew Brownian motion being an usual Brownian motion. This allows to design a test on the skewness parameter. We show that numerical simulations can be easily performed to estimate the skewness parameter and provide an application in Biology.     

Highs and lows: Some properties of the extremes of a diffusion and applications in finance

Observations on security prices, currency exchange rates, interest rates, and other financial time series usually include not only an open and close, but also a high and low price for the period. For Brown‐ian motion and certain diffusion processes, the information on high and low prices is of considerable value, particularly for estimating volatility, correlations between processes, and in the pricing of look‐back and barrier options. For pricing more general derivatives, this information is useful to the extent that change in volatility is an important ingredient in the price. The author gives a simple geometric device for generating the extremes of Brownian motion, and geometric Brownian motion; he then uses these extremes in the estimation of the volatility of the processes and to study survivorship bias.     

Approximation to two independent Gaussian processes from a unique Lévy process and applications

Abstract

In this article, we construct two families of processes, from a unique Lévy process, the finite dimensional distributions of which converge in law towards the finite dimensional distributions of the two independent Gaussian processes. As applications of this result, we obtain families of processes that converge in law towards fractional Brownian motion, sub-fractional Brownian motion and bifractional Brownian motion, respectively.     

A quadratically convergent algorithm for first passage time distributions in the Markov-modulated Brownian motion

A Markov-modulated Brownian motion (MMBM) is a substantial generalization of the classical Brownian Motion and is obtained by allowing the Brownian parameters to be modulated by an underlying Markov chain of environments. As with Brownian Motion, the time-dependent analysis of the MMBM becomes easy once the first passage times between levels are determined. However, in the MMBM those distributions cannot be obtained explicitly, and we need efficient algorithms to compute them. In this article, we provide a powerful approach based on approximating the MMBM with a sequence of scaled Markov-modulated fluid flows without Brownian components that weakly converge to the MMBM. Our main result is a Riccati equation for an associated matrix of transforms that satisfies conditions for the Newton scheme to have quadratic convergence and thus yields a very practical tool. The solution of that Riccati equation determines needed first passage times in the MMBM without much additional work. The success of our approach, which is based essentially on first-order fluid flows and a stochastic limit process, is argued to be due to the way we have isolated certain terms involving the quadratic variation effects of the Brownian. As an illustration of our algorithm, we present a numerical example of time-dependent results for a MMBM considered by Asmussen for which he determined (only) the eventual first return probabilities which we use here as an accuracy check.     

Fisher Information for Fractional Brownian Motion Under High-Frequency Discrete Sampling

We investigate the issue of the validation of the local asymptotic normality property of three characterizing parameters of the fractional Brownian motion under high-frequency discrete sampling. We prove that the local asymptotic normality property holds true for the likelihood only when at least one of the volatility parameter and the Hurst exponent is known. We provide optimal rates of convergence of the three parameters and Fisher information matrix in closed form.     

On drift parameter estimation in models with fractional Brownian motion

We consider a stochastic differential equation involving standard and fractional Brownian motion with unknown drift parameter to be estimated. We investigate the standard maximum likelihood estimate of the drift parameter, two non-standard estimates and three estimates for the sequential estimation. Model strong consistency and some other properties are proved. The linear model and Ornstein–Uhlenbeck model are studied in detail. As an auxiliary result, an asymptotic behaviour of the fractional derivative of the fractional Brownian motion is established.     

Heuristic approach to some laws for Brownian motion

Csàki and Vincze have shown that for an elementary tied-down random walk, the pair (maximum, instant of maximum) has the same law as (time spent in (0, 1/2), time spent above 1/2). Formal passage to the limit indicates that the former pair has for a Brownian bridge the same law as (local time at 0, duration of positivity). A quadrivariate density of Karatzas and Shreve and an equivalence for Brownian motion with drift follow.     

A Generalization of Geometric Brownian Motion with Applications

Although geometric Brownian motion has a great variety of applications, it can not cover all the random phenomena. The purpose of this article is to propose a model that generalizes geometric Brownian motion. We present some interesting applications of this model in financial engineering and statistical inferences for the unknown parameters.     

Ruin problem of a two-dimensional fractional Brownian motion risk process

This paper investigates ruin probability and ruin time of a two-dimensional fractional Brownian motion risk process. The net loss process of an insurance company is modeled by a fractional Brownian motion. The two-dimensional fractional Brownian motion risk process models the surplus processes of an insurance and a reinsurance company, where the net loss is divided between them in some specified proportions. The ruin problem considered is that of the two-dimensional risk process first entering the negative quadrant, that is, the simultaneous ruin problem. We derive both asymptotics of the ruin probability and approximations of the scaled conditional ruin time as the initial capital tends to infinity.     

Variance Estimation for Fractional Brownian Motions with Fixed Hurst Parameters

Some real-world phenomena in geo-science, micro-economy, and turbulence, to name a few, can be effectively modeled by a fractional Brownian motion indexed by a Hurst parameter, a regularity level, and a scaling parameter σ², an energy level. This article discusses estimation of a scaling parameter σ² when a Hurst parameter is known. To estimate σ², we propose three approaches based on maximum likelihood estimation, moment-matching, and concentration inequalities, respectively, and discuss the theoretical characteristics of the estimators and optimal-filtering guidelines. We also justify the improvement of the estimation of σ² when a Hurst parameter is known. Using the three approaches and a parametric bootstrap methodology in a simulation study, we compare the confidence intervals of σ² in terms of their lengths, coverage rates, and computational complexity and discuss empirical attributes of the tested approaches. We found that the approach based on maximum likelihood estimation was optimal in terms of efficiency and accuracy, but computationally expensive. The moment-matching approach was found to be not only comparably efficient and accurate but also computationally fast and robust to deviations from the fractional Brownian motion model.     

The local fractional bootstrap

We introduce a bootstrap procedure for high‐frequency statistics of Brownian semistationary processes. More specifically, we focus on a hypothesis test on the roughness of sample paths of Brownian semistationary processes, which uses an estimator based on a ratio of realized power variations. Our new resampling method, the local fractional bootstrap, relies on simulating an auxiliary fractional Brownian motion that mimics the fine properties of high‐frequency differences of the Brownian semistationary process under the null hypothesis. We prove the first‐order validity of the bootstrap method, and in simulations, we observe that the bootstrap‐based hypothesis test provides considerable finite‐sample improvements over an existing test that is based on a central limit theorem. This is important when studying the roughness properties of time series data. We illustrate this by applying the bootstrap method to two empirical data sets: We assess the roughness of a time series of high‐frequency asset prices and we test the validity of Kolmogorov's scaling law in atmospheric turbulence data.     

Estimators for the Drift of Subfractional Brownian Motion

In this paper, we consider, using technique based on Girsanov theorem, the problem of efficient estimation for the drift of subfractional Brownian motion S^H ? (S^H_t)_{t ∈ [0, T]}. We also construct a class of biased estimators of James-Stein type which dominate, under the usual quadratic risk, the natural maximum likelihood estimator.     

A strong convergence to the tempered fractional Brownian motion

In this paper, we give a strong approximation of the tempered fractional Brownian motion via transport processes and derive the rate of convergence.     

Optimality of equidistant sampling designs for the Brownian motion with a quadratic drift

In the paper we show that the equidistant sampling designs are optimal for the model of Brownian motion with a quadratic drift and for any of its submodels. This result holds for all Loewner isotonic criteria of parametric optimality continuous on the set of regular information matrices, as well as for the mean squared error of the best linear unbiased predictor.