Nonlinear Time Trends Research Articles

Harnessing Available Evidence in Single-Case Experimental Studies: The Use of Multilevel Meta-Analysis.

The use of multilevel models to combine and compare the results of multiple single-case experimental design (SCED) studies has been proposed about two decades ago. Since then, the number of multilevel meta-analyses of SCED studies steadily increased, together with the complexity of multilevel models used. At the same time, many studies were done to empirically evaluate the approach in a variety of situations, and to study how the flexibility of multilevel models can be employed to account for many complexities that often are encountered in SCED research, such as autocorrelation, linear and nonlinear time trends, specific designs, external event effects, multiple outcomes, and heterogeneity. In this paper, we give a state-of-the-art of the multilevel approach, by making an overview of basic and more extended models, summarizing simulation results, and discussing some remaining issues.

Evidence for differences in patterns of temporal trends in meta-analyses of diagnostic accuracy studies in the Cochrane database of systematic reviews

ObjectivesTemporal trends in comparative meta-analyses of interventions are well-recognized in the medical literature. For studies of diagnostic test accuracy (DTA), evidence of temporal trends is growing and the importance of assessing and reporting them has been highlighted in recent guidelines on postmarket surveillance in several jurisdictions. In this study, we evaluate the prevalence and patterns of time trends using a larger and more up-to-date set of DTA systematic reviews than has previously been examined, from the Cochrane Database of Systematic Reviews. Study Design and SettingCumulative meta-analysis was conducted on bivariate random effects meta-analysis estimates of sensitivity and specificity, after ranking studies by publication date. Trends for all studies were assessed graphically using plots of summary estimates by study rank, and using receiver operating characteristic plots of sensitivity vs specificity. Linear trends were also described using weighted linear regression with autocorrelated errors of summary estimates against study rank. Various patterns of nonlinear trends were characterized descriptively. ResultsThe analysis included 46 reviews (92 meta-analyses) conducted between 2017 and 2022. The total number of studies within all reviews was 1486, with a median (IQR) 7134 (2782–16,406) participants per review. Reviews had a median (IQR) time span of 19 (15-25) publication years. Time trends in at least 1 DTA measure were observed in 40 (87%) reviews, and statistically significant linear trends in 32 (70%) reviews. Nonlinear time trends were observed in 14 (30%) reviews. There was no evidence for a trend in either DTA measure in 6 (13%) reviews. ConclusionThe study contributes evidence on the variety in patterns of linear and nonlinear temporal DTA trends which has not previously been described. We recommended researchers check statistical assumptions of trend analysis methods, eg, using graphical methods. Further research into potential reasons for time trends could contribute to the robustness of future meta-analyses.

National, regional, and global estimates of low birthweight in 2020, with trends from 2000: a systematic analysis

Low birthweight (LBW; <2500 g) is an important predictor of health outcomes throughout the life course. We aimed to update country, regional, and global estimates of LBW prevalence for 2020, with trends from 2000, to assess progress towards global targets to reduce LBW by 30% by 2030. For this systematic analysis, we searched population-based, nationally representative data on LBW from Jan 1, 2000, to Dec 31, 2020. Using 2042 administrative and survey datapoints from 158 countries and areas, we developed a Bayesian hierarchical regression model incorporating country-specific intercepts, time-varying covariates, non-linear time trends, and bias adjustments based on data quality. We also provided novel estimates by birthweight subgroups. An estimated 19·8 million (95% credible interval 18·4-21·7 million) or 14·7% (13·7-16·1) of liveborn newborns were LBW worldwide in 2020, compared with 22·1 million (20·7-23·9 million) and 16·6% (15·5-17·9) in 2000-an absolute reduction of 1·9 percentage points between 2000 and 2020. Using 2012 as the baseline, as this is when the Global Nutrition Target began, the estimated average annual rate of reduction from 2012 to 2020 was 0·3% worldwide, 0·85% in southern Asia, and 0·59% in sub-Saharan Africa. Nearly three-quarters of LBW births in 2020 occurred in these two regions: of 19 833 900 estimated LBW births worldwide, 8 817 000 (44·5%) were in southern Asia and 5 381 300 (27·1%) were in sub-Saharan Africa. Of 945 300 estimated LBW births in northern America, Australia and New Zealand, central Asia, and Europe, approximately 35·0% (323 700) weighed less than 2000 g: 5·8% (95% CI 5·2-6·4; 54 800 [95% CI 49 400-60 800]) weighed less than 1000 g, 9·0% (8·7-9·4; 85 400 [82 000-88 900]) weighed between 1000 g and 1499 g, and 19·4% (19·0-19·8; 183 500 [180 000-187 000]) weighed between 1500 g and 1999 g. Insufficient progress has occurred over the past two decades to meet the Global Nutrition Target of a 30% reduction in LBW between 2012 and 2030. Accelerating progress requires investments throughout the lifecycle focused on primary prevention, especially for adolescent girls and women living in the most affected countries. With increasing numbers of births in facilities and advancing electronic information systems, improvements in the quality and availability of administrative LBW data are also achievable. The Children's Investment Fund Foundation; the UNDP-UNFPA-UNICEF-WHO World Bank Special Programme of Research, Development and Research Training in Human Reproduction; and the Bill & Melinda Gates Foundation.

National, regional, and global estimates of preterm birth in 2020, with trends from 2010: a systematic analysis

Preterm birth is the leading cause of neonatal mortality and is associated with long-term physical, neurodevelopmental, and socioeconomic effects. This study updated national preterm birth rates and trends, plus novel estimates by gestational age subgroups, to inform progress towards global health goals and targets, and aimed to update country, regional, and global estimates of preterm birth for 2020 in addition to trends between 2010 and 2020. We systematically searched population-based, nationally representative data on preterm birth from Jan 1, 2010, to Dec 31, 2020 and study data (26 March-14 April, 2021) for countries and areas with no national-level data. The analysis included 679 data points (86% nationally representative administrative data [582 of 679 data points]) from 103 countries and areas (62% of countries and areas having nationally representative administrative data [64 of 103 data points]). A Bayesian hierarchical regression was used for estimating country-level preterm rates, which incoporated country-specific intercepts, low birthweight as a covariate, non-linear time trends, and bias adjustments based on a data quality categorisation, and other indicators such as method of gestational age estimation. An estimated 13·4 million (95% credible interval [CrI] 12·3-15·2 million) newborn babies were born preterm (<37 weeks) in 2020 (9·9% of all births [95% CrI 9·1-11·2]) compared with 13·8 million (12·7-15·5 million) in 2010 (9·8% of all births [9·0-11·0]) worldwide. The global annual rate of reduction was estimated at -0·14% from 2010 to 2020. In total, 55·6% of total livebirths are in southern Asia (26·8% [36 099 000 of 134 767 000]) and sub-Saharan Africa (28·7% [38 819 300 of 134 767 000]), yet these two regions accounted for approximately 65% (8 692 000 of 13 376 200) of all preterm births globally in 2020. Of the 33 countries and areas in the highest data quality category, none were in southern Asia or sub-Saharan Africa compared with 94% (30 of 32 countries) in high-income countries and areas. Worldwide from 2010 to 2020, approximately 15% of all preterm births occurred at less than 32 weeks of gestation, requiring more neonatal care (<28 weeks: 4·2%, 95% CI 3·1-5·0, 567 800 [410 200-663 200 newborn babies]); 28-32 weeks: 10·4% [9·5-10·6], 1 392 500 [1 274 800-1 422 600 newborn babies]). There has been no measurable change in preterm birth rates over the last decade at global level. Despite increasing facility birth rates and substantial focus on routine health data systems, there remain many missed opportunities to improve preterm birth data. Gaps in national routine data for preterm birth are most marked in regions of southern Asia and sub-Saharan Africa, which also have the highest estimated burden of preterm births. Countries need to prioritise programmatic investments to prevent preterm birth and to ensure evidence-based quality care when preterm birth occurs. Investments in improving data quality are crucial so that preterm birth data can be improved and used for action and accountability processes. The Children's Investment Fund Foundation and the UNDP, United Nations Population Fund-UNICEF-WHO-World Bank Special Programme of Research, Development and Research Training in Human Reproduction.

Accounting for time dependency in meta-analyses of concordance probability estimates.

Recent years have seen the development of many novel scoring tools for disease prognosis and prediction. To become accepted for use in clinical applications, these tools have to be validated on external data. In practice, validation is often hampered by logistical issues, resulting in multiple small-sized validation studies. It is therefore necessary to synthesize the results of these studies using techniques for meta-analysis. Here we consider strategies for meta analyzing the concordance probability for time-to-event data ("C-index"), which has become a popular tool to evaluate the discriminatory power of prediction models with a right-censored outcome. We show that standard meta-analysis of the C-index may lead to biased results, as the magnitude of the concordance probability depends on the length of the time interval used for evaluation (defined e.g., by the follow-up time, which might differ considerably between studies). To address this issue, we propose a set of methods for random-effects meta-regression that incorporate time directly as covariate in the model equation. In addition to analyzing nonlinear time trends via fractional polynomial, spline, and exponential decay models, we provide recommendations on suitable transformations of the C-index before meta-regression. Our results suggest that the C-index is best meta-analyzed using fractional polynomial meta-regression with logit-transformed C-index values. Classical random-effects meta-analysis (not considering time as covariate) is demonstrated to be a suitable alternative when follow-up times are small. Our findings have implications for the reporting of C-index values in future studies, which should include information on the length of the time interval underlying the calculations.

Comparison of alcohol consumption and tobacco use among Korean adolescents before and during the COVID-19 pandemic.

The COVID-19 pandemic has brought significant changes worldwide, and due to the strict "Social Distancing Plan" including school closures, Korean adolescents have experienced unprecedented changes in their lives. Considering the peer effect on adolescents' health behavior impacted due to the changes brought about by the pandemic, it would be interesting to explore differences in substance use in Korean adolescents. This study examines how these risk behaviors among Korean adolescents have changed before and during the COVID-19 pandemic. Korea Youth Risk Behavior Web-based Survey of 87,532 adolescents was used to collect the data for the period 2019, 2020, and 2021. The KYRBWS is conducted by a national institution which uses a stratified two-stage cluster sampling, and the data is statistically reliable and representative of the population. The Cochran-Armitage and Chi-squared test for linear and non-linear time trends, respectively, were calculated to assess the difference across the period (2019, 2020, 2021). Also, the odds ratios (ORs) with 95% CIs for current smoking status and current alcohol use status among 2020 and 2021 participants were compared with those of the 2019 participants using multiple logistic regression analysis. The degree of current smoking status was lower in 2020 and 2021 participants than in the 2019 participants (2020: OR = 0.66, 95% CI = 0.61-0.71; 2021: OR = 0.66, 95% CI = 0.61-0.71). On the same token, current alcohol use status was also lower in the participants during the pandemic than those before the pandemic (2020: OR = 0.70, 95% CI = 0.66-0.73; 2021: OR = 0.70, 95% CI = 0.66-0.73). This study found that alcohol and tobacco use were reduced among Korean adolescents during the COVID-19 pandemic. Despite the decrease, future research on the potential effects of the COVID-19 pandemic on adolescents is warranted.

Multiple sclerosis incidence temporal trend in the Northeast of Iran: Using the Empirical Bayesian method.

In recent years dramatic changes in multiple sclerosis (MS) incidence have been reported in different provinces in Iran. This study was conducted to assess MS incidence temporal trends from March 21, 2005, to March 20, 2020, and provide a forecast until the end of 2025 in Shahroud county. This longitudinal study was carried out based on the data obtained from the MS registration system in Shahroud county. First, the annual incidence rates were calculated based on the year of diagnosis and smoothed using the Empirical Bayesian Method. Then temporal trends and annual percent change (APC) of MS incidence were analyzed using Joinpoint (JP) regression. Finally, the univariate time series model analysis was used to estimate the MS incidence trend until the end of 2025. A total of 234 newly diagnosed cases (60 [25.64%] males and 174 [74.36.4%] females) were examined in this study. The mean age of patients at the time of diagnosis was 31.40±3.78. It was 32.01±6.35 and 30.66±4.27 years for males and females, respectively (P<0.22). The mean annual MS incidence was 5.99±1.46, 3.03±0.21, and 8.98±2.79 per 100,000 in overall, males and females respectively. The MS incidence increased significantly from 5.67 (95% CI: 3.63-7.99) in 2005 to 7.58 (95% CI: 5.17-10.28) in 2020 with an APC of 4.5 (2.8 - 6.1). The MS incidence had a non-linear time trend in the study period and the best time trend fitted to the annual MS incidence trend was the non-linear quadratic curve. Based on this model, the annual MS incidence is expected to increase until the end of 2025. Shahroud county is one of the high-risk areas for MS and the increasing trend of MS incidence in it is similar to regional and global changes. This study, also, showed that MS incidence in Shahroud county will be increasing in the coming years.

Comparing Corrosion Control Treatments for Drinking Water Using a Robust Bayesian Generalized Additive Model

Pipe loop studies are used to evaluate corrosion control treatment, and updated regulatory guidance will ensure that they remain important for drinking water quality management. But the data they generate are difficult to analyze: nonlinear time trends, nondetects, extreme values, and autocorrelation are common attributes that make popular methods, such as the t- or rank-sum tests, poor descriptive models. Here, we propose a framework for describing pipe loop data that accommodates all of these challenging attributes: a robust Bayesian generalized additive model with continuous-time autoregressive errors. Our approach facilitates corrosion control treatment comparisons without the need for imputing nondetects or special handling of outliers. It is well suited to describing nonlinear trends without overfitting, and it accounts for the reduced information content in autocorrelated time series. We demonstrate it using a 4-year pipe loop study, with multiple pipe configurations and orthophosphate dosing protocols, finding that an initially high dose of orthophosphate (2 mg P L–1) that is subsequently lowered (0.75 mg P L–1) can yield lower lead release than an intermediate dose (1 mg P L–1) in the long term. Water utilities face difficult trade-offs in applying orthophosphate for corrosion control, and better models of pipe loop data can help inform the decision-making process.

The association between unemployment and suicide among employed and unemployed people in Hong Kong: A time-series analysis

BackgroundUnemployment is associated with suicide. However, it is unclear whether the influence of unemployment is consistent on suicide across subgroups with different employment status. This study aimed to explore the immediate and delayed association between unemployment and suicide among unemployed and employed people in Hong Kong. MethodsQuarterly statistics on labor force, unemployment rate and suicide count by employment status in Hong Kong (2003–2019) were obtained from the Hong Kong Census and Statistics Department and the Coroner's Court suicide reports. Separate negative binomial autoregressive regressions were used to investigate associations between unemployment and suicide among employed and unemployed people. The models controlled for linear and non-linear time trends, seasonal variations, the number of suicide cases, Consumer Price Index, and gender ratios of the labor force in the previous quarter. ResultsAfter controlling for all covariates, every 1% increase in the present unemployment rate was associated with a 15% increase in the suicide rate among the employed people in the current quarter (Incidence Rate Ratio (IRR) = 1.14, 95% CI = 1.01–1.28), and a 13% decrease in the suicide rate among the unemployed in the next quarter (IRR = 0.87, 95% CI = 0.78–0.98). LimitationsMost recent data on suicide cannot be obtained due to processing time of death investigation. ConclusionsThe influence of unemployment differed on suicide by employment status in different time periods. Employed and unemployed people have different needs in different economic conditions. Hence, it is important to provide timely, targeted and effective measures for suicide prevention to the specific group.

Thoracoscopic ablation for symptomatic atrial fibrillation improves quality of life

Abstract Background Rhythm control has become an essential part of adequate management in atrial fibrillation (AF) to reduce symptoms and ultimately to improve health related quality of life (HRQoL). Totally thoracoscopic ablation has been established over the last years as an effective and safe rhythm control strategy, especially for persistent AF, but quality of life data are lacking. Purpose To assess the impact of totally thoracoscopic ablation on HRQoL in patients with symptomatic AF. Methods Consecutive patients with symptomatic AF undergoing totally thoracoscopic ablation at a referral centre in the Netherlands (July 2016 – October 2019) were included. The primary outcome was quality of life. Short Form 36 and Atrial Fibrillation Effect on Quality-of-Life (AFEQT) health surveys were collected at baseline, 1, 3, 6 and 12 months. Clinical improvement was measured as the relative increase of the QoL-score at 1 year compared to the baseline score (in %). Multilevel regression modelling was used, coupled with fractional polynomials for adjustment of age differences and nonlinear time trends, to investigate the one-year clinical trajectories of sex differences in QoL subscales. Secondary outcomes included rhythm success (freedom from any recurrence of atrial tachyarrhythmia&amp;gt;30 sec), mortality and stroke. Results 191 patients were included (63.9±8.6 years, 68% male, 22.5% paroxysmal AF, 69.6% persistent AF and 7.9% long-term persistent AF, 66.5% having at least one previous failed catheter ablation, with median Cha2ds2 Vasc score of 2 [IQR 1–3]). AFEQT sum scores (52.6 points at baseline) substantially improved after three months (49.8%; p&amp;lt;0.001) and remained stable up to 1-year (54.2%; p&amp;lt;0.001) despite adverse events. Patients with recurrent AF also showed significant improvement at 3 months which remained stable up to 1-year, but patients who remained in sinus rhythm had significantly more increase (61.3% vs 26.9%, p&amp;lt;.001). The SF36 physical and mental summary composite scores significantly improved after 3 months (12.3% and 11.9% respectively; p&amp;lt;.001) and remained stable up to 1-year (16.9% and 16.4% respectively; P&amp;lt;.001). Although female patients had significantly lower AFEQT and physical subscales at baseline, similar improvement in scores were observed over time compared to men, adjusted for age and sex interactions (P&amp;lt;.001). One-year stroke rate was 1.6 per 100 patient-years with an oral anticoagulation rate of 63%. One-year survival was 99.5%. Conclusions This study reveals significant improvement of HRQoL three months after thoracoscopic ablation that persisted up to 1-year, also when adjusted for sex and age differences. Despite AF recurrence or adverse events AF related QoL still improved. Trials are necessary to confirm these data. Funding Acknowledgement Type of funding sources: None.

Abstract P110: Intravenous Hydralazine Effect On Blood Pressure Following Severe Inpatient Hypertension Development

Background: BP elevations in the hospital are commonly treated with intravenous medications, specifically hydralazine. However, treatment guidelines are lacking. Our goal is to assess the effect of intravenous hydralazine on BP following severe inpatient HTN development. Methods: This is a cohort study of adults admitted for reasons other than HTN and developed severe HTN within a single healthcare system. We defined severe inpatient HTN as the first documentation of BP elevation (&gt;180 systolic or &gt;110 diastolic) at least 1 hour after admission. Pregnant women were excluded. Mixed-effects models with nonlinear time trend were used to assess and visualize the time-dependent effect of intravenous hydralazine on BP within 6 hours of BP elevation. Results: Of the 23,147 inpatients who developed severe HTN, 13,753 were untreated and 9,166 were treated of which 12% received intravenous hydralazine. Of the treated and untreated patients, 57 and 46% had a severe MAP reduction (drop ≥30%) (p-value&lt;0.01). Risk factors for severe MAP drop include older age, history of drug and alcohol abuse, and higher BP on admission. Compared to inpatients with severe HTN who did not receive antihypertensives, those treated with intravenous hydralazine had a -12 [-14, -10], -19 [-22, -17], -8[-10, -7] mmHg greater reduction in MAP, SBP, and DBP after adjustment for demographic and clinical characteristics. Moreover, intravenous hydralazine resulted in acute BP reduction ( Figure 1 ). Conclusion: Severe MAP reduction is observed in both treated and untreated inpatients with severe HTN, however adjusted absolute decrease in MAP is greater in inpatients treated with intravenous hydralazine.

Study of the trend pattern of COVID-19 using spline-based time series model: a Bayesian paradigm.

A vast majority of the countries are under economic and health crises due to the current epidemic of coronavirus disease 2019 (COVID-19). The present study analyzes the COVID-19 using time series, an essential gizmo for knowing the enlargement of infection and its changing behavior, especially the trending model. We consider an autoregressive model with a non-linear time trend component that approximately converts into the linear trend using the spline function. The spline function splits the series of COVID-19 into different piecewise segments between respective knots in the form of various growth stages and fits the linear time trend. First, we obtain the number of knots with their locations in the COVID-19 series to identify the transmission stages of COVID-19 infection. Then, the estimation of the model parameters is obtained under the Bayesian setup for the best-fitted model. The results advocate that the proposed model appropriately determines the location of knots based on different transmission stages and know the current transmission situation of the COVID-19 pandemic in a country.

Fine Particle Exposure and Clinical Aggravation in Neurodegenerative Diseases in New York State.

Background:Adult-onset neurodegenerative diseases affect millions and negatively impact health care systems worldwide. Evidence suggests that air pollution may contribute to aggravation of neurodegeneration, but studies have been limited.Objective:We examined the potential association between long-term exposure to particulate matter in aerodynamic diameter [fine particulate matter ()] and disease aggravation in Alzheimer’s (AD) and Parkinson’s (PD) diseases and amyotrophic lateral sclerosis (ALS), using first hospitalization as a surrogate of clinical aggravation.Methods:We used data from the New York Department of Health Statewide Planning and Research Cooperative System (SPARCS 2000–2014) to construct annual county counts of first hospitalizations with a diagnosis of AD, PD, or ALS (total, urbanicity-, sex-, and age-stratified). We used annual concentrations estimated by a prediction model at a resolution, which we aggregated to population-weighted county averages to assign exposure to cases based on county of residence. We used outcome-specific mixed quasi-Poisson models with county-specific random intercepts to estimate rate ratios (RRs) for a 1-y exposure. We allowed for nonlinear exposure–outcome relationships using penalized splines and accounted for potential confounders.Results:We found a positive nonlinear association that plateaued above (, 95% CI: 1.04, 1.14 for a increase from 8.1 to ). We also found a linear positive association (, 95% CI: 1.01, 1.09 per increase), and suggestive evidence of an association with AD. We found effect modification by age for PD and ALS with a stronger positive association in patients of age but found insufficient evidence of effect modification by sex or urbanization level for any of the outcomes.Conclusion:Our findings suggest that annual increase in county-level concentrations may contribute to clinical aggravation of PD and ALS. Importantly, the average annual concentration in our study was , below the current American national standards, suggesting the standards may not adequately protect the aging population. https://doi.org/10.1289/EHP7425

Sex-specific temporal trends in the incidence of atrial fibrillation in a large Norwegian population-based study 1986–2014

Abstract Background Due to population aging, increasing prevalence of obesity and enhanced detection, the prevalence of atrial fibrillation (AF) worldwide is increasing steadily. Considerable sex differences in the epidemiology of AF such as lower prevalence and later onset in women compared to men have been reported. However, little is known about sex-specific temporal trends in AF incidence within the general population. Purpose To explore sex-specific age-adjusted secular trends in the incidence of AF in a general population from Norway between 1986 and 2014. Methods A total of 16,865 men and 15,413 women aged 20 years or older and without AF were enrolled in a longitudinal population study between 1986 and 2008 and followed up for incident AF to the end of 2014. Follow-up was from the date of attendance to the date of AF, emigration or death, whichever came first. All AF cases were validated by an independent endpoint committee using hospital and death records. AF incidence rates were calculated for each calendar year by dividing the number of AF cases per year by the corresponding person-time at risk. To allow for non-linear time trends, calendar year was fitted using fractional polynomials. Poisson regression was used to estimate calendar year-specific AF incidence rates adjusted for age. All analyses were stratified by sex. Results A total of 911 AF events in women and 1,139 AF events in men occurred over 324,090 person-years and 294,531 person-years of follow-up, respectively. During the study period AF incidence rates in men were at least double that in women (Figure). Age-adjusted AF incidence rates in women increased from 1986, peaked at 0.87 per 1000 person-years in 1998 and then decreased slightly towards 2014. In men AF incidence rates increased up to 2.18 per 1000 person-years in 2005 and then steeply decreased. Conclusion(s) AF incidence rates decreased in both women and men towards the end of the study period. The decrease was more profound in men compared to that in women. One possible explanation is more pronounced reduction in incidence and better treatment of myocardial infarction in men compared to women given that the aetiology of AF in men is mainly ischemic heart disease-related. However, further epidemiological analyses should be undertaken to identify explanatory factors. Funding Acknowledgement Type of funding source: Public hospital(s). Main funding source(s): University Hospital of North Norway, Northern Norway Regional Health Authority

Reference chart for knee flexion following total knee arthroplasty: a novel tool for monitoring postoperative recovery

BackgroundClinicians and patients lack an evidence-based framework by which to judge individual-level recovery following total knee arthroplasty (TKA) surgery, thus impeding personalized treatment approaches for this elective surgery. Our study aimed to develop and validate a reference chart for monitoring recovery of knee flexion following TKA surgery.MethodsRetrospective analysis of data collected in routine rehabilitation practice for patients following TKA surgery. Reference charts were constructed using Generalized Additive Models for Location Scale and Shape. Various models were compared using the Schwarz Bayesian Criterion, Mean Squared Error in 5-fold cross validation, and centile coverage (i.e. the percent of observed data represented below specified centiles). The performance of the reference chart was then validated against a test set of patients with later surgical dates, by examining the centile coverage and average bias (i.e. difference between observed and predicted values) in the test dataset.ResultsA total of 1173 observations from 327 patients were used to develop a reference chart for knee flexion over the first 120 days following TKA. The best fitting model utilized a non-linear time trend, with smoothing splines for median and variance parameters. Additionally, optimization of the number of knots in smoothing splines and power transformation of time improved model fit. The reference chart performed adequately in a test set of 171 patients (377 observations), with accurate centile coverage and minimal average bias (< 3 degrees).ConclusionA reference chart developed with clinically collected data offers a new approach to monitoring knee flexion following TKA.

Artificial neural network regression models in a panel setting: Predicting economic growth

Economic time series often feature non-linear structures such as non-linear time trends, non-linear autoregressive effects, and non-linear interaction effects. In this paper, it is shown that artificial neural network regression models are suitable tools for the analysis of economic panel data because they allow for a compromise between the ability to model these features and the model size. As model specification is a concern in artificial neural network models, previous approaches are discussed critically. It is shown that the growth rates of the gross domestic product of 24 industrialized economies in the period 1992–2016 follow a non-linear time trend which cannot be explained by autoregressive features or polynomial time variables. The unrestricted functional form of the time trend in the artificial neural network model is also the main reason for the superior statistical performance compared to conventional panel models. This is confirmed by out-of-sample predictions for 2017.

Placebo Effects in Antidepressant Trials Across Four Decades: A Comparison of Binary and Continuous Outcomes

Background: Previous work suggested placebo response rate in antidepressant trials to be stable since the 1970s. The present analysis aimed to compare placebo response with placebo remission (both binary outcomes) and placebo efficacy (continuous outcome, based on the Hamilton Depression Scale), thereby considering previously suggested (but not assessed) nonlinear time trends and accounting for previously suggested (but not properly adjusted for) small-study effects (SSE). Methods: Random-effects meta-regression was conducted to estimate the effects of study year. Potential nonlinear effects of study year were modeled using restricted cubic splines (RCS). Relative importance of SSE compared to other trial-level covariates (study centers, dosing schedule, study length) was assessed using multimodel averaging. Findings: Multimodel averaging suggested any nonlinear time trends in placebo response (0·07 [-0·05-0·18] 95% CI) and remission (0·00 [-0·01-0·02] 95% CI) to be sufficiently explained by SSE and other trial-level covariates, with between-trial heterogeneity being reduced to I2 =55%/672%, respectively. This suggested stable rates across years, in line with previous work. By contrast, efficacy (continuous) showed an increasing trend from 1979 to 2914 (0·11 [0·02-0·21] 95% CI) with substantial between-trial heterogeneity being unexplained (I2 =85%). Interpretation: The present analysis reports differences in the time trends between binary and continuous placebo outcomes across decades. The findings are discussed regarding their clinical relevance because increasing placebo effects have been suspected of contributing to so-called failed antidepressant trials. Funding Statement: The authors stated: No funding. Declaration of Interests: The author declares no competing interests. Ethics Approval Statement: The authors declared: Not applicable.

CPI INFLATION IN AFRICA: FRACTIONAL PERSISTENCE, MEAN REVERSION AND NONLINEARITY

Abstract Price stability has been one of the key mandates that apex monetary authorities strive to achieve globally. While most developed economies have achieved single digit inflation rates, most developing economies, especially African countries still experience alarming double-digit inflation rates. This paper therefore examined the dynamics of inflation in sixteen African countries. We employed the fractional persistence framework with linear trend and non-linear specifications based on Chebyshev’s polynomial in time. The results indicated nonlinear time trend in inflation for most of the countries. With the exception of Burkina Faso, which exhibited plausibility of naturally reverting to its mean level, the majority of the selected African countries would require stronger interventions to revert their observed inflationary levels to their mean levels.

Random scaling factors in Bayesian distributional regression models with an application to real estate data

Distributional structured additive regression provides a flexible framework for modelling each parameter of a potentially complex response distribution in dependence of covariates. Structured additive predictors allow for an additive decomposition of covariate effects with non-linear effects and time trends, unit- or cluster-specific heterogeneity, spatial heterogeneity and complex interactions between covariates of different type. Within this framework, we present a simultaneous estimation approach for multiplicative random effects that allow for cluster-specific heterogeneity with respect to the scaling of a covariate′s effect. More specifically, a possibly non-linear function f( z) of a covariate z may be scaled by a multiplicative and possibly spatially correlated cluster-specific random effect (1+αc). Inference is fully Bayesian and is based on highly efficient Markov Chain Monte Carlo (MCMC) algorithms. We investigate the statistical properties of our approach within extensive simulation experiments for different response distributions. Furthermore, we apply the methodology to German real estate data where we identify significant district-specific scaling factors. According to the deviance information criterion, the models incorporating these factors perform significantly better than standard models without (spatially correlated) random scaling factors.

Environmental consequences of dread behavior: A note on 2005 London bombings

The aim of this paper is to identify the environmental impact induced by behavioral responses to terrorist attacks occurred in London on July 7th, 2005. By relying on the “dread hypothesis” and on the evidence of an increase in private transport subsequent attacks, we have estimated econometric models of pollution concentration. Our results point at a substantial environmental impact in terms of PM10 and NO2, possibly driven by an increase in the perception of higher safety of private transport with respect to public transit. Results are robust to several robustness checks, including nonlinear time trends and heterogeneity across types of monitoring stations.