Tests for a change-point

James, Barry R.; James, Kang Ling; Siegmund, David

doi:10.1093/biomet/74.1.71

Cited by 197 publications

(73 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If the sequence is indeed random, 2ND JS typically follows a x 2 distribution, and the tail area under this distribution is the corresponding significance level [17]. Numerical simulation and studies on the change-point problem in statistics have shown that the distribution may not be a x 2 , but an N-dependent "extreme value" distribution [18]. The dependence of Eq.…”

mentioning

confidence: 99%

New Stopping Criteria for Segmenting DNA Sequences

2001

Phys. Rev. Lett.

View full text Add to dashboard Cite

We propose a solution on the stopping criterion in segmenting inhomogeneous DNA sequences with complex statistical patterns. This new stopping criterion is based on Bayesian information criterion in the model selection framework. When this criterion is applied to telomere of S. cerevisiae and the complete sequence of E. coli, borders of biologically meaningful units were identified, and a more reasonable number of domains was obtained. We also introduce a measure called segmentation strength which can be used to control the delineation of large domains. The relationship between the average domain size and the threshold of segmentation strength is determined for several genome sequences.

show abstract

mentioning

confidence: 99%

New Stopping Criteria for Segmenting DNA Sequences

2001

Phys. Rev. Lett.

View full text Add to dashboard Cite

show abstract

“…the power output. The above model is a form of what has been described in the literature as a change point (CP) problem (Brown et al 1975;James et al 1987;Antoch and HusÏ kova 1989, and the references quoted therein). Standard procedures for testing constancy of regression relationships, described in the references given above, fail to detect CP in our model, however.…”

Section: Detection Of the Change Point In Omentioning

confidence: 99%

Detection of the change point in oxygen uptake during an incremental exercise test using recursive residuals: relationship to the plasma lactate accumulation and blood acid base balance

Zoladz¹,

Szkutnik

Majerczak³

et al. 1998

European Journal of Applied Physiology

View full text Add to dashboard Cite

The purpose of this study was to develop a method to determine the power output at which oxygen uptake (VO2) during an incremental exercise test begins to rise non-linearly. A group of 26 healthy non-smoking men [mean age 22.1 (SD 1.4) years, body mass 73.6 (SD 7.4) kg, height 179.4 (SD 7.5) cm, maximal oxygen uptake (VO2max) 3.726 (SD 0.363) l x min(-1)], experienced in laboratory tests, were the subjects in this study. They performed an incremental exercise test on a cycle ergometer at a pedalling rate of 70 rev x min(-1). The test started at a power output of 30 W, followed by increases amounting to 30 W every 3 min. At 5 min prior to the first exercise intensity, at the end of each stage of exercise protocol, blood samples (1 ml each) were taken from an antecubital vein. The samples were analysed for plasma lactate concentration [La]pl, partial pressure of O2 and CO2 and hydrogen ion concentration [H+]b. The lactate threshold (LT) in this study was defined as the highest power output above which [La-]pl showed a sustained increase of more than 0.5 mmol x l(-1) x step(-1). The VO2 was measured breath-by-breath. In the analysis of the change point (CP) of VO2 during the incremental exercise test, a two-phase model was assumed for the 3rd-min-data of each step of the test: Xi = at(i) + b + epsilon(i) for i = 1,2, ..., T, and E(Xi) > at(i) + b for i = T + 1, ..., n, where X1, ..., Xn are independent and epsilon(i) approximately N(0, sigma2). In the first phase, a linear relationship between VO2 and power output was assumed, whereas in the second phase an additional increase in VO2 above the values expected from the linear model was allowed. The power output at which the first phase ended was called the change point in oxygen uptake (CP-VO2). The identification of the model consisted of two steps: testing for the existence of CP and estimating its location. Both procedures were based on suitably normalised recursive residuals. We showed that in 25 out of 26 subjects it was possible to determine the CP-VO2 as described in our model. The power output at CP-VO2 amounted to 136.8 (SD 31.3) W. It was only 11 W -- non significantly -- higher than the power output corresponding to LT. The VO2 at CP-VO2 amounted to 1.828 (SD 0.356) l x min(-1) was [48.9 (SD 7.9)% VO2max]. The [La-]pl at CP-VO2, amounting to 2.57 (SD 0.69) mmol x l(-1) was significantly elevated (P < 0.01) above the resting level [1.85 (SD 0.46) mmol x l(-1)], however the [H+]b at CP-VO2 amounting to 45.1 (SD 3.0) nmol x l(-1), was not significantly different from the values at rest which amounted to 44.14 (SD 2.79) nmol x l(-1). An increase of power output of 30 W above CP-VO2 was accompanied by a significant increase in [H+]b above the resting level (P = 0.03).

show abstract

“…Models that accommodate a change-point in the hazard function have been considered by a number of authors [7, 8, 10, 13, 15, 19, 21–23, 25, 29, 34]. However, these models do not accommodate populations that have a cure fraction.…”

Section: Introductionmentioning

confidence: 99%

Change-point cure models with application to estimating the change-point effect of age of diagnosis among prostate cancer patients

Othus

Tiwari

2012

Journal of Applied Statistics

View full text Add to dashboard Cite

Previous research on prostate cancer survival trends in the United States National Cancer Institute’s Surveillance Epidemiology and End Results database has indicated a potential change-point in the age of diagnosis of prostate cancer around age 50. Identifying a change-point value in prostate cancer survival and cure could have important policy and health care management implications. Statistical analysis of this data has to address two complicating features: (1) change-point models are not smooth functions and so present computational and theoretical difficulties; and (2) models for prostate cancer survival need to account for the fact that many men diagnosed with prostate cancer can be effectively cured of their disease with early treatment. We develop a cure survival model that allows for change-point effects in covariates to investigate a potential change-point in the age of diagnosis of prostate cancer. Our results do not indicate that age under 50 is associated with increased hazard of death from prostate cancer.

show abstract

Tests for a change-point

Cited by 197 publications

References 33 publications

New Stopping Criteria for Segmenting DNA Sequences

New Stopping Criteria for Segmenting DNA Sequences

Detection of the change point in oxygen uptake during an incremental exercise test using recursive residuals: relationship to the plasma lactate accumulation and blood acid base balance

Change-point cure models with application to estimating the change-point effect of age of diagnosis among prostate cancer patients

Contact Info

Product

Resources

About