Interval-wise testing for functional data

Pini, Alessia; Vantini, Simone

doi:10.1080/10485252.2017.1306627

Cited by 56 publications

(62 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This adjustment enabled continuous data series to be compared between persons and groups using identical relative time points. The curves were analyzed between ATH and CTRL by applying a functional t test, based on the interval‐wise testing procedure . Such an approach enabled the identification of time intervals where ATH and CTRL differed.…”

Section: Methodsmentioning

confidence: 99%

Dynamic knee control and movement strategies in athletes and non‐athletes in side hops: Implications for knee injury

Markström

Grip

Schelin

et al. 2019

Scandinavian Med Sci Sports

View full text Add to dashboard Cite

Athletes exposed to rapid maneuvers need a high level of dynamic knee stability and robustness, while also controlling whole body movement, to decrease the risk of non‐contact knee injury. The effects of high‐level athletic training on such measures of movement control have not, however, been thoroughly evaluated. This study investigated whether elite athletes (who regularly perform knee‐specific neuromuscular training) show greater dynamic knee robustness and/or different movement strategies than non‐athletic controls, in relation to overall knee function. Thirty‐nine women (19 athletes, 20 controls) performed standardized rebound side hops (SRSH) while a motion capture system synchronized with two force plates registered three‐dimensional trunk, hip, and knee joint angles and moments. Dynamic knee robustness was evaluated using finite helical axis (FHA) inclination angles extracted from knee rotation intervals of 10°, analyzed with independent t tests. Angle and moment curves were analyzed with inferential methods for functional data. Athletes had superior knee function (less laxity, greater hop performances, and strength) but presented similar FHA inclination angles to controls. Movement strategies during the landing phase differed; athletes presented larger (a) hip flexion angles (during 9%‐29% of the phase), (b) hip adduction moments (59%‐99%), (c) hip internal rotation moments (83%‐89%), and (d) knee flexion moments (79%‐93%). Thus, elite athletes may have a greater ability than non‐athletes to keep the knee robust while performing SRSH more efficiently through increased engagement of the hip. However, dynamic knee robustness associated with lower FHA inclination angles still show room for improvement, thus possibly decreasing knee injury risk.

show abstract

Section: Methodsmentioning

confidence: 99%

Dynamic knee control and movement strategies in athletes and non‐athletes in side hops: Implications for knee injury

Markström

Grip

Schelin

et al. 2019

Scandinavian Med Sci Sports

View full text Add to dashboard Cite

show abstract

“…Furthermore, because all functional intervalwise tests are consistent (Lemma 3), the IWT procedure is also consistent (Theorem 2), due to the result of the work of Pini and Vantini (2017;theorem 3). Theorem 2 and Corollaries 2 and 3 follow immediately as special cases of Theorem 2.…”

Section: A2 Properties Of Domain Selection Iwt Proceduresmentioning

confidence: 99%

“…In this paper, we extend the domain selection IWT procedure by Pini and Vantini (2017) to functional-on-scalar linear models to control the probability of wrongly rejecting each interval characterized by only true hypotheses, that is, the control of the IWER. The result of the procedure is an adjusted p value functioñC(t) for testing (9) provided with a control of the IWER.…”

Section: Model Inferencementioning

confidence: 99%

“…In our work, we extend the IWT framework proposed by Pini and Vantini (2017) to the functional-on-scalar linear model to test various hypotheses on the functional coefficients and prove that the proposed tests are exact or asymptotically exact. We utilize tests based on permutations, and hence, the procedure does not require normality of the residual functions and knowledge about the covariance structure of the data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nonparametric inference for functional‐on‐scalar linear models applied to knee kinematic hop data after injury of the anterior cruciate ligament

Abramowicz

Häger

Pini

et al. 2018

Scandinavian J Statistics

View full text Add to dashboard Cite

Motivated by the analysis of the dependence of knee movement patterns during functional tasks on subject-specific covariates, we introduce a distribution-free procedure for testing a functional-on-scalar linear model with fixed effects. The procedure does not only test the global hypothesis on the entire domain but also selects the intervals where statistically significant effects are detected. We prove that the proposed tests are provided with an asymptotic control of the intervalwise error rate, that is, the probability of falsely rejecting any interval of true null hypotheses. The procedure is applied to one-leg hop data from a study on anterior cruciate ligament injury. We compare knee kinematics of three groups of individuals (two injured groups with different treatments and one group of healthy controls), taking individual-specific covariates into account.

show abstract

“…The approach that we propose is sound even in the absence of full prior knowledge about the process, and it is expected to yield clearer and more reliable results. We propose to select the informative parts of the functions by means of the inferential intervalwise testing procedure, which was first proposed in Pini and Vantini (), and extended here to the case of multiway functional analysis of variance (ANOVA). In detail, we test the significance of the effects of the factors on the output functions when process changes can be experimentally observed, e.g.…”

Section: Introductionmentioning

confidence: 99%

Domain-Selective Functional Analysis of Variance for Supervised Statistical Profile Monitoring of Signal Data

Pini

Vantini

Colosimo

et al. 2017

Journal of the Royal Statistical Society Series C: Applied Statistics

View full text Add to dashboard Cite

Summary. In many applications, process monitoring has to deal with functional responses, which are also known as profile data. In these scenarios, a relevant industrial problem consists of detecting faults by combining supervised learning with functional data analysis and statistical process monitoring. Supervised learning is usually applied to the whole signal domain, with the aim of discovering the features that are affected by the faults of interest. We explore a different perspective, which consists of performing supervised learning to select inferentially the parts of the signal data that are more informative in terms of underlying fault factors. The procedure is based on a non-parametric domain-selective functional analysis of variance and allows us to identify the specific subintervals where the profile is sensitive to process changes. Benefits achieved by coupling the proposed approach with profile monitoring are highlighted by using a simulation study. We show how applying profile monitoring only to the identified subintervals can reduce the time to detect the out-of-control state of the process. To illustrate its potential in industrial applications, the procedure is applied to remote laser welding, where the main aim is monitoring the gap between the welded plates through the observation of the emission spectra of the welded material.

show abstract

Interval-wise testing for functional data

Cited by 56 publications

References 39 publications

Dynamic knee control and movement strategies in athletes and non‐athletes in side hops: Implications for knee injury

Dynamic knee control and movement strategies in athletes and non‐athletes in side hops: Implications for knee injury

Nonparametric inference for functional‐on‐scalar linear models applied to knee kinematic hop data after injury of the anterior cruciate ligament

Domain-Selective Functional Analysis of Variance for Supervised Statistical Profile Monitoring of Signal Data

Contact Info

Product

Resources

About