chngpt: threshold regression model estimation and inference

Fong, Youyi; Huang, Ying; Gilbert, Peter B.; Permar, Sallie R.

doi:10.1186/s12859-017-1863-x

Cited by 165 publications

(149 citation statements)

References 15 publications

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…With these data, we evaluated two models, a step arrangement evaluating whether there was a demonstrable change in status (i.e., mean abundance) during the time period and a segmented model examining whether there was a change in the trend; we specifically tested for a reversal of trend from a period of decline to one of growth. We fit these models in R (R Core Team 2018) with the changepoint (Killick et al 2016) and chngpt (Fong and Gilbert 2017) packages. Assumptions of independent, normally distributed data (on a log e scale) with constant variance pre- and post-change were evaluated with Shapiro and Kolmogorov-Smirnov tests and inspection of quantile-quantile and autocorrelation plots.…”

Section: Methodsmentioning

confidence: 99%

Evidence for a growing population of eastern migratory monarch butterflies is currently insufficient

Thogmartin

Szymanski

Weiser

2020

Preprint

View full text Add to dashboard Cite

The eastern migratory population of monarch butterflies has experienced a multi-10 decadal decline, but a recent increase in abundance (to 6.05 ha in winter 2018) has led some 11 observers to question whether the population has reversed its long-standing decline and 12 embarked on a trajectory of increasing abundance. We examined this possibility through 13 changepoint analyses, first assessing whether a change in trajectory existed and whether that 14 change was sufficient to alter our estimated risk for the population. We found evidence of a 15 change in trajectory in 2014, but insufficient statistical support for a significantly increasing 16 population since that time (β = 0.285, 95% CI = -0.127, 0.697). If the population estimate for 17 winter 2019 is ≥4.0 ha, we will then be able to credibly assert the population has been increasing 18 since 2014. However, given estimated levels of time series variability, presumed habitat capacity 19 and no recent change in status or trend, there was a 13.5% probability of observing a population 20 estimate as large or larger than was reported for winter 2018. Despite insufficient evidence for an 21 increasing population, near-term risk of quasi-extinction by 2023 has declined (mean risk 22 23 highlight the incredible difficulty in drawing robust conclusions from annual changes in 24 abundance over a short time series, especially for an insect that commonly exhibits considerable 25 year-to-year variation. Thus, we urge caution when drawing conclusions regarding species status 26 and trends for any species for which limited data are available. 27 28 Shapiro 32 Populations vary over time in their abundance, and this variability can impart uncertainty to the 33 status and trend of a species. As population dynamics approach extinction, dynamics become 34 more variable (Holmes and Fagan 2006), which means short-term highs might become higher, 35 even while abundance is declining on average. In addition to the stochastic variation in 36 abundance imposed by the environment, uncertainty in species status and trend arises from 37 population sizes most often being estimated rather than counted; trends being inferred from 38 limited duration time series; and latent characteristics of a population, such as its relation to 39 carrying capacity or quasi-extinction thresholds, generally being inferred properties rather than 40 an observable quantity. Thus, given these various sources of uncertainty, it is difficult enough to 41 determine the trajectory for a population, let alone any change that may occur in that trajectory, 42 especially one that may occur near the terminus of a time series based on limited data.43 3 Estimates of the population size of the eastern North American migratory population of 44 monarch butterflies (Danaus plexippus, hereafter monarchs) in their overwintering locations in 45 high-elevation oyamel fir (Abies religiosa) forests of central Mexico suggest a long-term decline 46 in abundance. Using a model allowing separation of observation-induced error from n...

show abstract

Section: Methodsmentioning

confidence: 99%

Evidence for a growing population of eastern migratory monarch butterflies is currently insufficient

Thogmartin

Szymanski

Weiser

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, the variance of the change‐point by Muggeo's method is obtained as an approximation to the variance of the ratio of two random variables based on the delta method and is sensitive to the difference in slopes and the sample size . This method may not adequately account for the uncertainty involved in the estimate of the change‐point . Our method on the other hand uses Equation and the asymptotic variance formula for θ I in Section 3 for the estimation of the model parameters and associated variances.…”

Section: Applicationsmentioning

confidence: 99%

“…12 This method may not adequately account for the uncertainty involved in the estimate of the change-point. 23 Our method on the other hand uses Equation (4) and the asymptotic variance formula for I in Section 3 for the estimation of the model parameters and associated variances. Another reason could be that the estimated location of the change-point for age by the proposed and Muggeo's method is around 50, which lies far away from the median (29) of the distribution of the age variable as observed in Figure S3 of the Supplementary Materials.…”

Section: Pima Indians Diabetes Studymentioning

confidence: 99%

Methods for generalized change‐point models: with applications to human immunodeficiency virus surveillance and diabetes data

Tapsoba

Wang

Zangeneh

et al. 2020

Statistics in Medicine

View full text Add to dashboard Cite

In many epidemiological and biomedical studies, the association between a response variable and some covariates of interest may change at one or several thresholds of the covariates. Change‐point models are suitable for investigating the relationship between the response and covariates in such situations. We present change‐point models, with at least one unknown change‐point occurring with respect to some covariates of a generalized linear model for independent or correlated data. We develop methods for the estimation of the model parameters and investigate their finite‐sample performances in simulations. We apply the proposed methods to examine the trends in the reported estimates of the annual percentage of new human immunodeficiency virus (HIV) diagnoses linked to HIV‐related medical care within 3 months after diagnosis using HIV surveillance data from the HIV prevention trial network 065 study. We also apply our methods to a dataset from the Pima Indian diabetes study to examine the effects of age and body mass index on the risk of being diagnosed with type 2 diabetes.

show abstract

“…Theory predicts that thresholds might demarcate changes in dispersal behavior (Lookingbill et al 2010, Hovestadt et al 2014, and in this system, the number of offspring occupying the maternal web might reach a threshold level triggering dispersal. We therefore tested for the presence of threshold effects in population parameters (number of juveniles emerging from the sac and the number of older siblings remaining in the web) using the 'chngpt.test' function in the 'chngpt' package in R (Fong et al 2017). We tested for a 'segmented' threshold (whether slopes change before and after the change point) using a maximum likelihood ratio statistic (Fong et al 2017).…”

Section: Analysesmentioning

confidence: 99%

“…We therefore tested for the presence of threshold effects in population parameters (number of juveniles emerging from the sac and the number of older siblings remaining in the web) using the 'chngpt.test' function in the 'chngpt' package in R (Fong et al 2017). We tested for a 'segmented' threshold (whether slopes change before and after the change point) using a maximum likelihood ratio statistic (Fong et al 2017). We included the same explanatory variables tested as fixed effects above as covariates for the threshold analysis.…”

Section: Analysesmentioning

confidence: 99%

Interacting maternal and spatial cues influence natal – dispersal out of social groups

Yip

Rao

Smith

et al. 2019

Oikos

View full text Add to dashboard Cite

Proximate cues for animal dispersal are complex and varied. Multiple cues may provide information about different aspects of habitat quality, and these aspects may interact with each other, as well as with population density in different ways. We examined how individuals incorporate multiple cues in their decisions to emigrate and immigrate in the colonial orb‐weaving spider, Cyrtophora citricola. We manipulated maternal feeding as a cue for prey abundance and measured the size of the maternal web, which provides a limited space for philopatric offspring and a second potential dispersal cue. In addition, we recorded all immigration events to determine dispersal distances and the cues juveniles may use in settlement. Dispersal increased when mothers were poorly fed, web sizes were small and clutch sizes were large. In addition to these overall effects, maternal feeding also interacted with web size, indicating that offspring from well‐fed mothers were more tolerant of high sibling densities. We also detected a threshold for the effect of clutch size on dispersal for the first egg sac: below 20 offspring, there was no effect of clutch size, but dispersal increased with clutch size for larger clutches. Dispersal distances were often short, and immigrants preferred sheltered trees and those occupied by adult females. Dispersal not only depended on multiple cues, but these cues interacted, and the importance of web size suggested that saturation of the natal web might force dispersal, at least for spiders with poorly‐fed mothers. How one aspect of habitat quality influences dispersal can therefore depend on the state of other aspects of habitat quality. In particular, some natal resources, such as a nest or territory, may become saturated and limit group size, but this limit will also depend on other factors, such as prey availability.

show abstract

chngpt: threshold regression model estimation and inference

Cited by 165 publications

References 15 publications

Evidence for a growing population of eastern migratory monarch butterflies is currently insufficient

Evidence for a growing population of eastern migratory monarch butterflies is currently insufficient

Methods for generalized change‐point models: with applications to human immunodeficiency virus surveillance and diabetes data

Interacting maternal and spatial cues influence natal – dispersal out of social groups

Contact Info

Product

Resources

About