Maximum Likelihood Regression Research Articles

Stress and land‐use legacies alter the relationship between invasive‐ and native‐ plant richness

AbstractQuestionsDoes the driver of native richness impact invasion–diversity relationships? In high stress systems, do negative invasion–diversity relationships emerge from biotic resistance (as predicted by the diversity–resistance hypothesis) or from stress acting as a selective driver of native richness? Do invasion–diversity relationships change when abiotic and biotic legacies, rather than stress, act as non‐selective drivers of richness?LocationCalcareous fens, Wisconsin, USA.MethodsWe compared plot‐level relationships between native and invasive species richness in 220 plots in 11 calcareous fens, six of which had stress alleviation and community impoverishment due to historic ploughing. We measured nutrient availability (resource stress) and saturation stress (non‐resource stress), native richness and invasive richness in each plot.ResultsResidual maximum likelihood (REML) regression found a negative correlation between native and invasive richness in never ploughed plots, but no relationship was found in ploughed plots. REML multiple regression found that after accounting for saturation and nutrients, there was no relationship between native and invasive richness in ploughed or never ploughed plots. Saturation stress predicted low invasive richness and high native richness in never ploughed plots. Time since abandonment did not predict invasive richness. Non‐metric multidimensional scaling (NMDS) found most invasive species present only in areas with the least saturation stress.ConclusionsNegative relationships between native and invasive richness can result when the main driver of native richness favour native species (such as stress), and therefore may not support the diversity–resistance hypothesis. When the main driver of native richness does not select between native and invasive richness, there may be no relationship between native and invasive richness, even at very small spatial scales.

The supermatrix technique: A simple framework for hypothesis testing with missing data

We present a new paradigm that allows simplified testing of multiparameter hypotheses in the presence of incomplete data. The proposed technique is a straight-forward procedure that combines the benefits of two powerful data analytic tools: multiple imputation and nested-model difference testing. A Monte Carlo simulation study was conducted to assess the performance of the proposed technique. Full information maximum likelihood (FIML) and single regression imputation were included as comparison conditions against which the performance of the suggested technique was judged. The imputation-based conditions demonstrated much higher convergence rates than the FIML conditions. statistics derived from the proposed technique were more accurate than such statistics derived from both the FIML conditions and the regression imputation conditions. Limitations of the current work and suggestions for future directions are also addressed.

Access to Care for Patients With Time-Sensitive Conditions in Pennsylvania

Collective knowledge and coordination of vital interventions for time-sensitive conditions (ST-segment elevation myocardial infarction [STEMI], stroke, cardiac arrest, and septic shock) could contribute to a comprehensive statewide emergency care system, but little is known about population access to the resources required. We seek to describe existing clinical management strategies for time-sensitive conditions in Pennsylvania hospitals. All Pennsylvania emergency departments (EDs) open in 2009 were surveyed about resource availability and practice patterns for time-sensitive conditions. The frequency with which EDs provided essential clinical bundles for each condition was assessed. Penalized maximum likelihood regressions were used to evaluate associations between ED characteristics and the presence of the 4 clinical bundles of care. We used geographic information science to calculate 60-minute ambulance access to the nearest facility with these clinical bundles. The percentage of EDs providing each of the 4 clinical bundles in 2009 ranged from 20% to 57% (stroke 20%, STEMI 32%, cardiac arrest 34%, sepsis 57%). For STEMI and stroke, presence of a board-certified/board-eligible emergency physician was significantly associated with presence of a clinical bundle. Only 8% of hospitals provided all 4 care bundles. However, 53% of the population was able to reach this minority of hospitals within 60 minutes. Reliably matching patient needs to ED resources in time-dependent illness is a critical component of a coordinated emergency care system. Population access to critical interventions for the time-dependent diseases discussed here is limited. A population-based planning approach and improved coordination of care could improve access to interventions for patients with time-sensitive conditions.

A graphical evaluation of logistic ridge estimator in mixture experiments

In comparison to other experimental studies, multicollinearity appears frequently in mixture experiments, a special study area of response surface methodology, due to the constraints on the components composing the mixture. In the analysis of mixture experiments by using a special generalized linear model, logistic regression model, multicollinearity causes precision problems in the maximum-likelihood logistic regression estimate. Therefore, effects due to multicollinearity can be reduced to a certain extent by using alternative approaches. One of these approaches is to use biased estimators for the estimation of the coefficients. In this paper, we suggest the use of logistic ridge regression (RR) estimator in the cases where there is multicollinearity during the analysis of mixture experiments using logistic regression. Also, for the selection of the biasing parameter, we use fraction of design space plots for evaluating the effect of the logistic RR estimator with respect to the scaled mean squared error of prediction. The suggested graphical approaches are illustrated on the tumor incidence data set.

Bowel Function After Tapentadol and Oxycodone Immediate Release (IR) Treatment in Patients With Low Back or Osteoarthritis Pain

Constipation is a common side effect of opioid therapy. Tapentadol immediate release (IR) was better tolerated than oxycodone IR in 2 clinical trials involving patients with low back or osteoarthritis pain. The objective of this study was to examine patient-reported bowel function during those trials. Bowel function was assessed during secondary post hoc analyses using: the bowel movement questionnaire (BMQ; 10-d trial); the Patient Assessment of Constipation Symptoms questionnaire (PAC-SYM; 90-day trial); and laxative use (both trials). Random effects maximum likelihood regressions were run to examine PAC-SYM data. BMQ data were analyzed using 1-way analyses of variance and a multinomial logistic regression. Rates of laxative use were compared using χ(2) statistics. The 10- and 90-day trials consistently showed that tapentadol IR caused less impairment of bowel function than oxycodone IR. BMQ data were comparable between patients receiving tapentadol IR and placebo, and better versus oxycodone IR including: lower proportion of days where bowel movement was absent (P<0.05); lower risks of reporting hard stools (P<0.001); and moderate or severe straining (P<0.001). All PAC-SYM summary scores (abdominal, rectal, stool, overall) indicated fewer symptoms among patients receiving tapentadol IR versus oxycodone IR (P<0.001). In both trials, rates of laxative use was lower for tapentadol IR treatment groups versus oxycodone IR (P<0.001). Patient-reported bowel function associated with tapentadol IR treatment was similar to that associated with placebo (10-d trial) and significantly better than that associated with oxycodone IR treatment (10- and 90-d trials).

Estimating the postmortem interval (PMI) using accumulated degree-days (ADD) in a temperate region of South Africa

The validity of the method in which total body score (TBS) and accumulated degree-days (ADD) are used to estimate the postmortem interval (PMI) is examined. TBS and ADD were recorded for 232 days in northern South Africa, which has temperatures between 17 and 28°C in summer and 6 and 20°C in winter. Winter temperatures rarely go below 0°C. Thirty pig carcasses, which weighed between 38 and 91kg, were used. TBS was scored using the modified method of Megyesi et al. [1]. Temperature was acquired from an on site data logger and the weather station bureau; differences between these two sources were not statistically significant. Using loglinear random-effects maximum likelihood regression, an r2 value for ADD (0.6227) was produced and linear regression formulae to estimate PMI from ADD with a 95% prediction interval were developed. The data of 16 additional pigs that were placed a year later were then used to validate the accuracy of this method. The actual PMI and ADD were compared to the estimated PMI and ADD produced by the developed formulae as well as the estimated PMIs within the 95% prediction interval. A validation of the study produced poor results as only one pig of 16 fell within the 95% interval when using the formulae, showing that ADD has limited use in the prediction of PMI in a South African setting.

Stochastic time‐concentration activity models for cytotoxicity in 3D brain cell cultures

BackgroundIn vitro aggregating brain cell cultures containing all types of brain cells have been shown to be useful for neurotoxicological investigations. The cultures are used for the detection of nervous system‐specific effects of compounds by measuring multiple endpoints, including changes in enzyme activities. Concentration‐dependent neurotoxicity is determined at several time points.MethodsA Markov model was set up to describe the dynamics of brain cell populations exposed to potentially neurotoxic compounds. Brain cells were assumed to be either in a healthy or stressed state, with only stressed cells being susceptible to cell death. Cells may have switched between these states or died with concentration‐dependent transition rates. Since cell numbers were not directly measurable, intracellular lactate dehydrogenase (LDH) activity was used as a surrogate. Assuming that changes in cell numbers are proportional to changes in intracellular LDH activity, stochastic enzyme activity models were derived. Maximum likelihood and least squares regression techniques were applied for estimation of the transition rates. Likelihood ratio tests were performed to test hypotheses about the transition rates. Simulation studies were used to investigate the performance of the transition rate estimators and to analyze the error rates of the likelihood ratio tests. The stochastic time‐concentration activity model was applied to intracellular LDH activity measurements after 7 and 14 days of continuous exposure to propofol. The model describes transitions from healthy to stressed cells and from stressed cells to death.ResultsThe model predicted that propofol would affect stressed cells more than healthy cells. Increasing propofol concentration from 10 to 100 μM reduced the mean waiting time for transition to the stressed state by 50%, from 14 to 7 days, whereas the mean duration to cellular death reduced more dramatically from 2.7 days to 6.5 hours.ConclusionThe proposed stochastic modeling approach can be used to discriminate between different biological hypotheses regarding the effect of a compound on the transition rates. The effects of different compounds on the transition rate estimates can be quantitatively compared. Data can be extrapolated at late measurement time points to investigate whether costs and time‐consuming long‐term experiments could possibly be eliminated.

Abstract P6-09-05: Women's perceptions of lymphedema risk management: Psychological factors do matter

Abstract Introduction: Lymphedema arising from breast cancer surgery and treatment is characterized by arm impairment, physical disfigurement, emotional distress and diminished quality of life. Given no specific lymphedema cure, early detection and risk management strategies are recommended. The American Cancer Society (ACS) identifies simple behavioral strategies to minimize lymphedema risk; however, little is known about women's adherence to these recommendations over time. Even less is known about how women perceive lymphedema risk and the psychological factors that promote long-term adherence. Guided by the Cognitive-Social Health Information Processing model we assessed adherence to risk management strategies and identified psychological factors associated with adherence. Methods: Women (N = 103) diagnosed with primary breast cancer and scheduled for breast surgery initially completed the baseline questionnaire prior to surgery, and then received the ACS publication “Lymphedema: What Every Woman With Breast Cancer Should Know” as part of usual care. Follow-up questionnaires were completed by participants 6- and 12-months later. Baseline data collected included demographic and medical history variables, lymphedema-related knowledge and cognitive and affective factors (perceived risk, beliefs and expectancies, self-regulatory competencies, negative affect), and adherence to risk management strategies. Adherence was also assessed at 6- and 12-months. A mixed-model maximum-likelihood logistic regression was employed in data analyses. Results: Adherence to risk minimization strategies increased over time (p &amp;lt; .001) and varied with the specific strategy (p &amp;lt; .001). Risk minimization strategies fell into three broad groupings: 1) High levels of consistent adherence across time - wearing loose clothing, avoiding tight jewelry, avoiding blood pressure readings and avoiding trauma to the arm; 2) Moderate levels of adherence and greater variability across time - avoiding cutting cuticles, extreme sun exposure, carrying heavy bags, and temperature extremes, and consulting with a doctor when symptoms appear; 3) Low level of adherence - wearing protective gloves and using an electric razor. Baseline knowledge was associated with adherence to all strategies. In addition, increased self-efficacy to enact the strategies (OR = 1.82, p = 0.0001), greater beliefs in one's self-regulatory ability to manage distress (OR = 1.25, p = 0.0017), and decreased risk-related negative affect (OR = 0.96, p = 0.03) were associated with increased adherence to the recommendations. Conclusions: During the 12 months following breast cancer diagnosis, women demonstrated increased awareness of lymphedema risk management and adherence to the recommended strategies, although adherence to individual strategies varied. Psychological factors were associated with adherence to recommendations. Specifically, women with greater knowledge, self-efficacy to enact recommended strategies and ability to self-regulate negative emotions, and lower negative affect were more likely to be adherent. These findings suggest that for lymphedema education approaches to be maximally effective, they should incorporate psychological interventions designed to enhance self-efficacy and coping in women at risk to ensure long-term adherence. Citation Information: Cancer Res 2012;72(24 Suppl):Abstract nr P6-09-05.

The Relationship of California’s Medicaid Reimbursement System to Nurse Staffing Levels

Policy initiatives at the Federal and state level are aimed at increasing staffing in nursing homes. These include direct staffing standards, public reporting, and financial incentives. To examine the impact of California's Medicaid reimbursement for nursing homes which includes incentives directed at staffing. Two-stage limited-information maximum-likelihood regressions were used to model the relationship between staffing [registered nurses (RNs), licensed practical nurses, and certified nursing assistants hours per resident day] and the Medicaid payment rate, accounting for the specific structure of the payment system, endogeneity of payment and case-mix, and controlling for facility and market characteristics. A total of 927 California free-standing nursing homes in 2006. The model included facility characteristics (case-mix, size, ownership, and chain affiliation), market competition and excess demand, labor supply and wages, unemployment, and female employment. The instrumental variable for Medicaid reimbursement was the peer group payment rate for 7 geographical market areas, and the instrumental variables for resident case-mix were the average county revenues for professional therapy establishments and the percent of county population aged 65 and over. Consistent with the rate incentives and rational expectation behavior, expected nursing home reimbursement rates in 2008 were associated with increased RN staffing levels in 2006 but had no relationship with licensed practical nurse and certified nursing assistant staffing. The effect was estimated at 2 minutes per $10 increase in rate. The incentives in the Medicaid system impacted only RN staffing suggesting the need to improve the state's rate setting methodology.

Unbiased Weibull Modulus Estimation Using Differential Cumulative Entropy

Recently, Liu (2007) defined a new entropy which measures the distance between a prescribed and an empirical survival function. In this article, we use this measure called Differential Cumulative Entropy (DCE) for Weibull parameters estimation. We show that the DCE method provides biased estimations of the Weibull modulus, but utilizing unbiasing factors derived here we enhance the results. A simulation study shows the higher performance of the new method over commonly used maximum likelihood and linear regression methods in Weibull parameters estimation especially in small sample sizes.

The influence of societal values on attitudes towards immigration

This paper examines the influence of societal values on individual attitudes towards immigration and immigrants. We argue that conflict between individual and societal values leads individuals to be exposed to frames and opinions that are contrary to their values, evokes competing considerations and creates attitudinal ambivalence and volatility. To evade ambivalence, individuals whose values are in conflict with those of their society rely less on their core values to construct their attitudes. Using data from the first wave of European Social Surveys and relying on Heteroskedastic Maximum Likelihood Regression, we test our argument simultaneously for 18 European countries and show that deviations from society’s conservation and self-transcendence values lead to greater ambivalence in attitudes towards immigration and immigrants. Our results provide evidence of the importance of the social context and society’s shared values in influencing personal political attitudes and judgments.

Do Alzheimer-specific microstructural changes in mild cognitive impairment predict conversion?

Diffusion tensor imaging (DTI) is a magnetic resonance imaging (MRI) technique that provides information on the fiber architecture of the brain by measuring water diffusion. Prior work has shown that neuronal degeneration in Alzheimer's disease (AD) and mild cognitive impairment (MCI) alters this architecture. Since the conversion rate to AD is much higher for MCI patients than for normal healthy people, it is important to identify biomarkers with a predictive value on this conversion. In this study, we applied tract-based spatial statistics (TBSS) on datasets of 15 healthy controls, 15 AD patients, and 17 MCI patients. Of these MCI patients eight remained stable, whereas nine developed AD within the first 12–18months of follow-up investigations. Analysis using TBSS combined with a maximum likelihood regression with random effects of the fornix, the corpus callosum, and the cingulum identified significant differences between these two types of MCI patients in fractional anisotropy (FA) and radial diffusivity (DR). Thus, DTI reveals Alzheimer-specific changes in those MCI subjects that later convert, although they were clinically identical to the other MCI-patients at the time the data were acquired. This finding could lead to early identification of AD and thereby aid early clinical intervention.

Statistical modeling approach for detecting generalized synchronization

Detecting nonlinear correlations between time series presents a hard problem for data analysis. We present a generative statistical modeling method for detecting nonlinear generalized synchronization. Truncated Volterra series are used to approximate functional interactions. The Volterra kernels are modeled as linear combinations of basis splines, whose coefficients are estimated via l(1) and l(2) regularized maximum likelihood regression. The regularization manages the high number of kernel coefficients and allows feature selection strategies yielding sparse models. The method's performance is evaluated on different coupled chaotic systems in various synchronization regimes and analytical results for detecting m : n phase synchrony are presented. Experimental applicability is demonstrated by detecting nonlinear interactions between neuronal local field potentials recorded in different parts of macaque visual cortex.

Estimating Response Modeling Methodology models

AbstractAn advanced review of Response Modeling Methodology (RMM) has recently summarized RMM core philosophy, modeling approach, and allied statistical expressions. This focus article complements the earlier review by presenting a step‐by‐step guide to estimating RMM models. The estimation procedure comprises two stages: first the median is estimated and then the rest of the RMM parameters are estimated. Three estimation procedures are presented for the latter stage: maximum likelihood, two‐moment matching, and nonlinear quantile regression. The three estimation methods, as applied to RMM, are first expounded and then demonstrated via a numerical example, using Monte‐Carlo simulated data from a γ distribution and an L4 orthogonal array design. Comparisons with generalized linear modeling and estimation, assuming γ distribution (correctly) and inverse Gaussian distribution (incorrectly), are given. A brief introduction to RMM is also provided. WIREs Comput Stat 2012, 4:323–333. doi: 10.1002/wics.1199This article is categorized under: Statistical and Graphical Methods of Data Analysis &gt; Density Estimation Statistical Learning and Exploratory Methods of the Data Sciences &gt; Modeling Methods Statistical Models &gt; Simulation Models

Do rainfall conditions push or pull rural migrants: evidence from Malawi

AbstractThis article uses nationally representative data from Malawi's 2004/05 Integrated Household Survey (IHS2) to examine whether rainfall conditions influence a rural worker's decision to make a long‐term move to an urban or another rural area. Results of a Full Information Maximum Likelihood regression model reveal that (1) rainfall shocks have a negative association with rural out‐migration, (2) migrants choose to move to communities where rainfall variability and drought probability are lower, and (3) rainfall shocks have larger negative effects on the consumption of recent migrants than on the consumption of long‐time residents.

Darknet-Based Inference of Internet Worm Temporal Characteristics

Internet worm attacks pose a significant threat to network security and management. In this work, we coin the term Internet worm tomography as inferring the characteristics of Internet worms from the observations of Darknet or network telescopes that monitor a routable but unused IP address space. Under the framework of Internet worm tomography, we attempt to infer Internet worm temporal behaviors, i.e., the host infection time and the worm infection sequence, and thus pinpoint patient zero or initially infected hosts. Specifically, we apply statistical estimation techniques and propose method of moments, maximum likelihood, and linear regression estimators. We show analytically and empirically that our proposed estimators can better infer worm temporal characteristics than a naive estimator that has been used in the previous work. We also demonstrate that our estimators can be applied to worms using different scanning strategies such as random scanning and localized scanning.

Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach

Society is rapidly accepting the use of video cameras in many new and varied locations, but effective methods to utilize and manage the massive resulting amounts of visual data are only slowly developing. This paper presents a framework for live video analysis in which the behaviors of surveillance subjects are described using a vocabulary learned from recurrent motion patterns, for real-time characterization and prediction of future activities, as well as the detection of abnormalities. The repetitive nature of object trajectories is utilized to automatically build activity models in a 3-stage hierarchical learning process. Interesting nodes are learned through Gaussian mixture modeling, connecting routes formed through trajectory clustering, and spatio-temporal dynamics of activities probabilistically encoded using hidden Markov models. Activity models are adapted to small temporal variations in an online fashion using maximum likelihood regression and new behaviors are discovered from a periodic retraining for long-term monitoring. Extensive evaluation on various data sets, typically missing from other work, demonstrates the efficacy and generality of the proposed framework for surveillance-based activity analysis.

A 274-lake calibration data-set and inference model for chironomid-based summer air temperature reconstruction in Europe

A 274-lake calibration data-set for chironomid-based temperature reconstruction is presented which is based on the taxonomic amalgamation of a 117-lake data-set from Switzerland and a 157-lake data-set from Norway and Svalbard. Taxonomic consistency of the two data-sets was ensured by joint microscope sessions by the two involved analysts, re-identifying chironomid assemblages in the Swiss data-set to reach an identical taxonomic resolution as in the Norwegian data, and by double-checking selected samples of the Norwegian calibration data-set. The combined Swiss-Norwegian calibration data-set contains information on the distribution of 154 chironomid taxa over a July air temperature range of 3.5–18.4 °C, a pH range of 4.7–8.8, and an altitudinal range of 5–2815 m asl from lakes in temperate, subarctic, arctic, and alpine environments. Inference models developed based on this data-set using weighted averaging-partial least squares (WA-PLS) regression outperformed inference models based on maximum likelihood regression. After outlier deletion WA-PLS regression predicted July air temperature with a bootstrapped (cross-validated) root mean squared error of prediction (RMSEP) of 1.40 °C. Inference models developed from the separate regional data-sets have an RMSEP of 1.16 and 1.43 °C for the Norwegian and the Swiss calibration data-set, respectively. The WA-PLS inference model based on the Norwegian data-set adequately predicted July air temperature based on chironomid assemblages in the Swiss data-set (RMSEP 2.05 °C; r 2 0.74). In contrast, the WA-PLS model based on the Swiss chironomid assemblages performed poorly in inferring July air temperatures based on the Norwegian chironomid assemblages (RMSEP 2.70 °C; r 2 0.39). We attribute this discrepancy to the large proportion of chironomid taxa in Norwegian samples not represented in the Swiss data-set, the larger range of both pH and lake types included in the Norwegian calibration data-set, and the lack of some chironomid taxa with an arctic and boreal distribution in the Swiss data-set. The WA-PLS inference model based on the combined Swiss-Norwegian calibration data-set is the largest taxonomically consistent chironomid-based inference model available to date and outperforms other existing models if the r 2 and RMSEP relative to the overall temperature gradient are examined. We demonstrate that the combined model can reconstruct a larger range of temperatures when applied to fossil assemblages than models based on the Norwegian or Swiss calibration data-sets only. The combined data-set includes the majority of chironomid taxa expected in late Pleistocene and Holocene sediments of lakes from Northern, Eastern, and Central Europe as well as from southern European mountain lakes. The newly developed WA-PLS inference model is therefore well suited for developing continental-scale reconstructions of late Quaternary temperature change based on chironomid records from different parts of Europe.

Kinematic Motion Patterns of the Cranial and Caudal Canine Cervical Spine

To define the kinematic motion patterns of the canine cervical spine, with a particular emphasis on identifying differences between the cranial (C(2)-C(4)) and caudal (C(5)-C(7)) segments, and to determine the significance of coupled motions (CM) in the canine cervical spine. Cadaveric biomechanical study. Cervical spines of 8 Foxhounds. Spinal specimens were considered free of pathology based on radiographic, computed tomography, and magnetic resonance imaging examinations. All musculature was removed without damaging ligaments or joint capsules. Spines were mounted in a customized pure-moment spine testing jig, and data were collected using an optoelectronic motion capture system. Range of motion, neutral zone and CM in flexion/extension, left/right lateral bending and left/right axial rotation were established. Data were analyzed using mixed-effects maximum likelihood regression models. Total flexion/extension did not change across the 4 levels. There was no difference between flexion and extension, and no CM was identified. Lateral bending was not different across levels, but tended to be greater in the cranial spine. Axial rotation was ∼2.6 times greater in the caudal segments. Lateral bending and axial rotation were coupled. Kinematics of the cranial and caudal cervical spine differed markedly with greater mobility in the caudal cervical spine.

Rosca Participation in Benin: A Commitment Issue*

AbstractIn the light of first‐hand data from a Beninese urban household survey in Cotonou, we investigate several motives aiming to explain participation in Rotating Savings and Credit Associations. We provide anecdotal pieces of evidence, descriptive statistics, Full Information Maximum Likelihood (FIML) regressions and matching estimates which tend to indicate that most individuals use their participation in a rosca as a device to commit themselves to save money and to deal with self‐control problems.