Cédric Heuchenne

University of Liège | ulg · HEC Management School

Anomaly detection plays a crucial role across various domains, including healthcare, where identifying deviations from normal patterns can lead to early intervention and improved outcomes. In healthcare, such as in ECG analysis, detecting anomalous signals is essential for timely diagnosis and treatment, as it can help identify potentially life-thr...

In the field of statistical process control, the cumulative sum (CUSUM) control chart is used as a powerful tool to detect process shifts. One of the main features of the CUSUM control chart is that it takes into account the past information at each sampling time of the process. Recently, the rapid development of optimization algorithms and softwar...

In recent years, the monitoring of compositional data using control charts has been investigated in the Statistical Process Control field. In this study, we will design a Phase II Multivariate Exponentially Weighted Moving Average (MEWMA) control chart with variable sampling intervals to monitor compositional data based on isometric log-ratio trans...

The recent blooming developments of Artificial Intelligence (AI), Internet of Things (IoT), and Data Science (DS) have put Smart Manufacturing (SM) into a new context. This leads to more attractions on control charts as one of the useful tools that contribute to the success in SM by anomaly detection (AD) approach. Coefficient of variation (CV) is...

This paper proposes new tests to compare two multivariate probability distributions. Since basic ranks do not canonically exist in Rd, it is impossible to have a natural multivariate generalization of rank-based tests such as the two-sample Kolmogorov–Smirnov test. We thus rely on recent measure transportation theory to transform this d−dimensional...

In recent years, the monitoring of compositional data using control charts has been investigated in the Statistical Process Control field. In this study, we will design a Phase II Multivariate Exponentially Weighted Moving Average (MEWMA) control chart with variable sampling intervals to monitor compositional data based on isometric log-ratio trans...

In recent years, the development of digital technologies brings a lot of changes in the way of operating, leading, and working processes in companies. Accordingly, advanced technologies such as Artificial Intelligent, Big Data, Internet of things, etc., are widely applied to aggregate, transform, and analyze data, thereby inferring meaningful infor...

The last decades have witnessed the rapid growth of advanced technologies and their application which has a significant influence on industrial manufacturing, leading to smart manufacturing (SM). The recent development of information and communication technologies has engendered the concept of the smart factory that adds intelligence into the manuf...

Several commercial banks in the United States disappeared during the last decades due to failure or acquisition by another entity. From a survival analysis perspective, however, the high censoring rate suggests that some institutions are likely to be immune to failure and/or acquisition. In this study, we use a competing risks proportional-hazards...

The Lorenz regression procedure quantifies the inequality of a response explained by a set of covariates. Formally, it gives a weight to each covariate to maximize the concentration index between the response and a weighted average of the covariates. The obtained index is called the explained Gini coefficient. Unlike methods based on decompositions...

With the development of e-commerce, payment by credit card has become an essential means for the purchases of goods and services online. Especially, the Manufacturing Sector faces a high risk of fraud online payment. Its high turnover is the reason making this sector is lucrative with fraud. This gave rise to fraudulent activity on the accounts of...

We describe the penPHcure R package, which implements the semiparametric proportional-hazards (PH) cure model of Sy and Taylor (2000) extended to time-varying covariates and the variable selection technique based on its SCAD-penalized likelihood proposed by Beretta and Heuchenne (2019a). In survival analysis, cure models are a useful tool when a fr...

Online monitoring of the multivariate coefficient of variation (MCV) can be of interest in many real situations in which the dispersion of a multi-variate process is meant to remain constant with regards to its position. To this aim, several control charts have been recently proposed in the literature. In this paper, the new one-sided adaptive char...

Among the anomaly detection methods, control charts have been considered important techniques. In practice, however, even under the normal behaviour of the data, the standard deviation of the sequence is not stable. In such cases, the coefficient of variation (CV) is a more appropriate measure for assessing system stability. In this paper, we consi...

In monitoring the coefficient of variation (CV), the variable sampling interval (VSI) type charts are a useful adaptive strategy that has been recently combined with various types of charts, including exponentially weighted moving average (EWMA) and variable sample size (VSS) charts. These combinations lead to desirable control charts with an impre...

We investigate, in this paper, the effect of the measurement error (ME) on the performance of Run Rules control charts monitoring the coefficient of variation (CV) squared. The previous Run Rules CV chart in the literature is improved slightly by monitoring the CV squared using two one-sided Run Rules charts instead of monitoring the CV itself usin...

Cross-sectional sampling is often used when investigating inter-event times, resulting in left-truncated and right-censored data. In this paper, we consider a semiparametric truncation model in which the truncating variable is assumed to belong to a certain parametric family. We examine two methods of estimating both the truncation and the lifetime...

We investigate in this paper the effect of the measurement error on the performance of Run Rules control charts monitoring the coefficient of variation (CV) squared. The previous Run Rules CV chart in the literature is improved slightly by monitoring the CV squared using two one-sided Run Rules charts instead of monitoring the CV itself using a two...

In practice, there are processes where the in-control mean and standard deviation of a quality characteristic is not stable. In such cases, the coefficient of variation (CV) is a more appropriate measure for assessing process stability. In this paper, we consider the statistical design of Run Rules based control charts for monitoring the CV of mult...

This paper shows how stock market volatility regimes affect the cross-section of stock returns along quality and liquidity dimensions. We find that, during crisis periods, low quality and low liquidity stocks experience relatively higher losses than predicted in normal times, while high quality and high liquidity stocks experience rather relatively...

In this paper, we investigate the effect of the measurement error on the performance of the cumulative sum control charts monitoring the coefficient of variation. The measurement errors are supposed to follow a linear covariate error model. The obtained results show that the precision error ratio and the accuracy error have negative impact on the c...

Suppose we have a location-scale regression model where the location is the conditional mean and the scale is the conditional standard deviation; the response is possibly right-censored, the covariate is fully observed, and the error is independent of the covariate. We propose new goodness-of-fit testing procedures for the conditional mean and vari...

Due to several applications in applied statistics, there is an increasing attention to the coefficient of variation (CV) in quality control. In this paper, we propose investigating the effect of measurement errors on the performance of one-sided cumulative sum (CUSUM) control charts monitoring the CV. According to the simulated results, the precisi...

From a survival analysis perspective, bank failure data are often characterized by small default rates and heavy censoring. This empirical evidence can be explained by the existence of a subpopulation of banks likely immune from bankruptcy. In this regard, we use a mixture cure model to separate the factors with an influence on the susceptibility t...

We investigate in this paper a new type of control chart called VSI EWMA‐RZ by integrating the variable sampling interval feature (VSI) with the exponentially weighted moving average (EWMA) scheme to monitor the ratio of two normal random variables. Because the distribution of the ratio is skewed, we suggest designing two separated one‐sided charts...

In the literature, coefficient of variation control charts have been introduced under the assumption of no measurement errors. However, measurement errors always exist in practice, and they do affect the performance of control charts in the detection of an out‐of‐control situation. In this paper, we therefore study the performance of a coefficient...

We investigate in this paper a new type of control chart called VSI EWMA-RZ by integrating the variable sampling interval feature (VSI) with the exponentially weighted moving average (EWMA) scheme to monitor the ratio of two normal random variables. Because the distribution of the ratio is skewed, we suggest designing two separated one-sided charts...

In the literature, coefficient of variation control charts have been introduced under the assumption of no measurement errors. However, measurement errors always exist in practice and they do affect the performance of control charts in the detection of an out of control situation. In this paper, we therefore study the performance of a coefficient o...

We propose completely nonparametric methodology to investigate location-scale modelling of two-component mixture cure models, where the responses of interest are only indirectly observable due to the presence of censoring and the presence of so-called long-term survivors that are always censored. We use covariate-localized nonparametric estimators,...

Many data in service quality came from a nonnormal or unknown distribution, hence the commonly-used control charts are not suitable. In this paper, new Arcsine Shewhart Sign and Variable Sampling Interval EWMA (Exponentially Weighted Moving Average) distribution-free control charts are proposed. The procedure does not require the assumption of norm...

Credit card fraud causes many financial losses for customer and also for the organization. For this reason, in the past few years, many studies have been performed using machine learning techniques to detect and block fraudulent transactions. This paper introduces two real time data-driven approaches using optimal anomaly detection techniques for c...

The in-control performance of Shewhart and S² control charts with estimated in-control parameters has been evaluated by a number of authors. Results indicate that an unrealistically large amount of Phase I data is needed to have the desired in-control average run length (ARL) value in Phase II. To overcome this problem, it has been recommended that...

Suppose the random vector (X, Y) satisfies the regression model Y = m(X)+σ(X)ε, where m(·) = E(Y |·), σ²(·) = Var(Y |·) belongs to some parametric class {σθ(·): θ ε Θ} and ε is independent of X. The response Y is subject to random right censoring and the covariate X is completely observed. A new estimation procedure is proposed for σθ(·) when m(·)...

We evaluate the in-control performance of the np-control chart with estimated parameter conditional on the Phase I sample. We then apply the bootstrap method to adjust the control chart limits to guarantee the desired in-control average run length (ARL0) value in the monitoring stage. The adjusted limits ensure that the ARL0 would take a value grea...

In this article, we propose a robust statistical approach to select an appropriate error distribution, in a classical multiplicative heteroscedastic model. In a first step, unlike to the traditional approach, we don't use any GARCH-type estimation of the conditional variance. Instead, we propose to use a recently developed nonparametric procedure (...

This paper investigates how aggregate liquidity influences optimal portfolio allocations across various US characteristic portfolios. We consider short-term allocation problems, with single and multiple risky assets, and use the nonparametric approach of Brandt (1999) to directly express optimal portfolio weights as functions of aggregate liquidity...

In this paper we consider the semiparametric transformation model Λθo (Y) = m(X)+ε, where θois an unknown finite dimensional parameter, the function m(·) = ����(Λθo (Y)|X = ·) is “smooth”, but otherwise unknown, and the covariate X is independent of the error ε. An estimator of the distribution function of ε is investigated and its weak convergence...

We evaluate the in-control performance of the S2 control chart with estimated parameters conditional on the Phase I sample. Simulation results indicate no realistic amount of Phase I data is enough to have confidence that the in-control average run length (ARL) obtained will be near the desired value. To overcome this problem, we adjust the S2 char...

We model the severity distribution of operational loss data, conditionally to some covariates. Indeed, previous studies suggest that this distribution might be influenced by firm-specific factors. We introduce a conditional Generalized Pareto model for the tail of the severity distribution, where the shape parameter is an unknown function of a line...

We present an alternative sampling scheme for the Hotelling's T2 control chart with variable parameters (VP T2) which allows the sampling interval h, the sample size n and control limit k to vary between minimum and maximum values while keeping the warning line fixed over time. Our method uses only one measurement scale to overcome the difficulties...

In this paper, we present Shewhart-type and S2 control charts for monitoring individual or joint shifts in the scale and shape parameters of a Weibull distributed process. The advantage of this method is its ease of use and flexibility for the case where the process distribution is Weibull, although the method can be applied to any distribution. We...

Consider semi-competing risks data (two times to concurrent events are studied but only one of them is right-censored by the other one) where the link between the times Y and C to non-terminal and terminal events, respectively, is modeled by a family of Archimedean copulas. Moreover, both Y and C are submitted to an independent right censoring vari...

The Hotelling’s \(\textit{T}^{2 }\)control chart with variable parameters (VP \(T^{2})\) has been shown to have better statistical performance than other adaptive control schemes in detecting small to moderate process mean shifts. In this paper, we investigate the statistical performance of the VP \(T^{2}\) control chart coupled with run rules. We...

Delivery chains are concerned with the delivery of goods and services to customers within a specific time interval; this time constraint is added to the usual consumer demand for product or service quality. In this context, we address the idea of using process control tools to monitor this key variable of delivery time. In applications, there are u...

Recent studies have shown that applying the control chart by using a variable parameters (VP) scheme yields more rapid detection of assignable causes than the classical method of taking fixed sample sizes at fixed intervals of time. In this paper, the problem of economical statistical design of the VP T2 control chart is considered as a double-obje...

Recent studies have shown that a double sampling (DS) scheme yields improvements in detection times of process shifts over variable ratio sampling (VRS) methods that have been extensively studied in the literature. Additionally, a DS scheme is more practical than some of the VRS methods since the sampling interval is fixed. In this paper, we invest...

Suppose the random vector (X;Y ) satisfles the regression model Y = m(X) + æ(X)", where m(¢) and æ(¢) are unknown location and scale functions and " is independent of X. The response Y is subject to random right censoring and the covariate X is completely observed. A new test for a speciflc parametric form of any scale function æ(¢) (including the...

This paper investigates the effect of market-wide liquidity on optimal portfolio allocations across US equity portfolios sorted on size and book-to-market characteristics. In particular, we consider a single-period investor with a relative risk aversion of 5, and use the nonparametric approach of Brandt (1999) to directly express optimal portfolio...

Recent studies have shown that using variable sampling size and control limits (VSSC) schemes result in charts with more statistical power than variable sampling size (VSS) when detecting small to moderate shifts in the process mean vector. This paper presents an economic-statistical design (ESD) of the VSSC T2 control chart using the general model...

T2 control charts are used to monitor a process when more than one quality variable associated with the process is being observed. Recent studies have shown that using variable sampling size (VSS) schemes results in charts with more statistical power for detecting small to moderate shifts in the process mean vector. This paper presents an economic-...

Consider the semiparametric transformation model $\Lambda_{\theta_o}(Y)=m(X)+\epsilon$, where $\theta_o$ is an unknown finite dimensional parameter, the functions $\Lambda_{\theta_o}$ and $m$ are smooth, $\epsilon$ is independent of $X$, and $\esp(\epsilon)=0$. We propose a kernel-type estimator of the density of the error $\epsilon$, and prove its...

Consider the random vector (X, Y ), where Y represents a response variable and X an explanatory variable. The response Y is subject to random right censoring, whereas X is completely observed. Let m(x) be a conditional location function of Y given X = x. In this paper we assume that m( ⋅) belongs to some parametric class \(\mathcal{M} =\{ {m}_{\the...

Consider the regression model Y = m(X) + φ(X)ε, where m(X) = E[Y ∣X] and φ2(X) = V ar[Y ∣X] are unknown smooth functions and the error ε (with unknown distribution) is independent of X. The pair (X, Y) is subject to parametric selection bias and the response to right censoring. We construct a new estimator for the cumulative distribution function o...

Suppose the random vector (X,Y) satisfies the regression model Y=m(X)+σ(X)ε, where m(⋅) is the conditional mean, σ2(⋅) is the conditional variance, and ε is independent of X. The covariate X is d-dimensional (d≥1), the response Y is one-dimensional, and m and σ are unknown but smooth functions. Goodness-of-fit tests for the parametric form of the e...

Assume that we have two populations (X 1,Y 1) and (X 2,Y 2) satisfying two general nonparametric regression models Y j =m j (X j )+ε j , j=1,2, where m(⋅) is a smooth location function, ε j has zero location and the response Y j is possibly right-censored. In this paper, we propose to test the null hypothesis H 0:m 1=m 2 versus the one-sided...

Suppose the random vector (X, Y) satisfies the regression model Y = m(X) + σ(X)ε, where m(·) = E(Y |·) belongs to some parametric class {m θ (·) : θ ∈ Θ} of regression functions, σ 2 (·) = Var(Y |·) is unknown, and ε is independent of X. The response Y is subject to random right censoring, and the covariate X is completely observed. A new estimatio...

In this paper, we study strong uniform consistency of a weighted average of artificial data points. This is especially useful when information is incomplete (censored data, missing data …). In this case, reconstruction of the information is often achieved nonparametrically by using a local preservation of mean criterion for which the corresponding...

INTRODUCTION Since its birth in 1996, the credit derivatives market has been experiencing an exponential growth with a compound growth rate of ~46% per year. According to the British Bankers’ Association, a trend growth is likely to be sustained until at least 2008 (Barrett and Ewan, 2007). Among credit derivatives, the credit default swap (CDS) is...

Consider the polynomial regression model $$Y = \beta_0 + \beta_1 X + \cdots + \beta_p X^p + \sigma(X) \epsilon$$, where σ2(X)=Var(Y|X) is unknown, and ε is independent of X and has zero mean. Suppose that Y is subject to random right censoring. A new estimation procedure for the parameters β0,...,β p is proposed, which extends the classical least s...

Consider the heteroscedastic model Y=m(X)+σ(X)ɛ, where ɛ and X are independent, Y is subject to right censoring, m(·) is an unknown but smooth location function (like e.g. conditional mean, median, trimmed mean…) and σ(·) an unknown but smooth scale function. In this paper we consider the estimation of m(·) under this model. The estimator we propos...

Consider the random vector (X, Y), where X is completely observed and Y is subject to random right censoring. It is well known that the completely nonparametric kernel estimator of the conditional distribution F(|x){F(\cdot|x)} of Y given X =x suffers from inconsistency problems in the right tail (Beran 1981, Technical Report, University of Califor...

Recent studies have shown that the variable sampling interval (VSI) scheme helps practitioners detect process shifts more quickly than the classical scheme (FRS). In this paper, the economi-cally and statistically optimal design of the VSI T 2 control chart for monitoring the process mean vector is investigated. The cost model proposed by Lorenzen...