Discrete Time Survival Analysis Model Research Articles

Investigating suicide related behaviours across sexual orientation and neighbourhood deprivation levels: A cohort study using linked health administrative data.

There have been no studies examining how neighbourhood deprivation modifies the effects of sexual minority status on suicide-related behaviours (SRB). Sexual minority individuals in deprived areas may face unique challenges and stressors that exacerbate their risk of SRB. This study aims to investigate the association between sexual minority status and clinical SRB, and examine whether the effect of neighbourhood deprivation differs across sexual orientation. A population-representative survey sample (169,090 respondents weighted to represent 8,778,120 individuals; overall participation rate 75%) was linked to administrative health data in Ontario, Canada to measure SRB-related events (emergency department visits, hospitalizations, and deaths) from 2007 to 2017. Neighbourhood-level deprivation was measured using the Ontario Marginalisation index measure of material deprivation at the dissemination area level. Discrete-time survival analysis models, stratified by sex, tested the effects of neighbourhood deprivation and sexual minority status, while controlling for individual-level covariates. Sexual minority men had 2.79 times higher odds of SRB compared to their heterosexual counterparts (95% CI 1.66 to 4.71), while sexual minority women had 2.14 times higher odds (95% CI 1.54 to 2.98). Additionally, neighbourhood deprivation was associated with higher odds of SRB: men in the most deprived neighbourhoods (Q5) had 2.01 times higher odds (95% CI 1.38 to 2.92) of SRB compared to those in the least deprived (Q1), while women had 1.75 times higher odds (95% CI 1.28 to 2.40). No significant interactions were observed between sexual minority status and neighbourhood deprivation levels. In both men and women, sexual minority status and neighbourhood deprivation are independent risk factors for SRB. Despite the lack of effect modification, sexual minorities living in the most deprived neighbourhoods have the highest chances of SRB. Future investigations should evaluate interventions and policies to improve sexual minority mental health and address neighbourhood deprivation.

Identification of optimal therapeutic window for steroid use in severe alcohol-associated hepatitis: A worldwide study

Corticosteroids are the only effective therapy for severe alcohol-associated hepatitis (AH), defined by a model for end-stage liver disease (MELD) score >20. However, there are patients who may be too sick to benefit from therapy. Herein, we aimed to identify the range of MELD scores within which steroids are effective for AH. We performed a retrospective, international multicenter cohort study across 4 continents, including 3,380 adults with a clinical and/or histological diagnosis of AH. The main outcome was mortality at 30 days. We used a discrete-time survival analysis model, and MELD cut-offs were established using the transform-the-endpoints method. In our cohort, median age was 49 (40-56) years, 76.5% were male, and 79% had underlying cirrhosis. Median MELD at admission was 24 (19-29). Survival was 88% (87-89) at 30 days, 77% (76-78) at 90 days, and 72% (72-74) at 180 days. A total of 1,225 patients received corticosteroids. In an adjusted-survival-model, corticosteroid use decreased 30-day mortality by 41% (hazard ratio [HR] 0.59; 0.47-0.74; p <0.001). Steroids only improved survival in patients with MELD scores between 21 (HR 0.61; 0.39-0.95; p= 0.027) and 51 (HR 0.72; 0.52-0.99; p= 0.041). The maximum effect of corticosteroid treatment (21-30% survival benefit) was observed with MELD scores between 25 (HR 0.58; 0.42-0.77; p <0.001) and 39 (HR 0.57; 0.41-0.79; p <0.001). No corticosteroid benefit was seen in patients with MELD >51. The type of corticosteroids used (prednisone, prednisolone, or methylprednisolone) was not associated with survival benefit (p= 0.247). Corticosteroids improve 30-day survival only among patients with severe AH, especially with MELD scores between 25 and39. Alcohol-associated hepatitis is a condition where the liver is severely inflamed as a result of excess alcohol use. It is associated with high mortality and it is not clear whether the most commonly used treatments (corticosteroids) are effective, particularly in patients with very severe liver disease. In this worldwide study, the use of corticosteroids was associated with increased 30-day, but not 90- or 180-day, survival. The maximal benefit was observed in patients with an MELD score (a marker of severity of liver disease; higher scores signify worse disease) between 25-39. However, this benefit was lost in patients with the most severe liver disease (MELD score higher than 51).

Linking changes in perceived academic control to university dropout and university grades: A longitudinal approach.

Although research shows higher levels of perceived academic control are associated with academic adjustment in the first year of university, little is known about how changes in perceived control over multiple years relate to longitudinal university dropout and grades. Thus, our 3-year study (N = 1,007) examined whether changes in perceived control predicted university dropout and whether this relationship was mediated by university grade point average (GPA). Latent change score models showed that although first-year perceived control declined on average, there were high levels of variability between students, so that perceptions of control increased for some students. Discrete time survival analysis models showed that such positive changes in perceived control were associated with reduced dropout rates. Increases in perceived control also predicted higher subsequent university grades. Finally, we confirmed that the relationship between perceived control and dropout was mediated by university grades. Findings advance the literature in highlighting longitudinal linkages between perceived academic control and university grades and their influence on subsequent dropout. Implications for instructors and institutions to support adequate control perceptions, especially in the first academic year, are discussed. (PsycInfo Database Record (c) 2020 APA, all rights reserved)

Predicting the risk of financial distress using corporate governance measures

Corporate governance is an important determinant of corporate performance. Poor corporate governance can damage the interests of shareholders, and may lead to business collapse. This paper expands the literature on credit risk management by assessing the effectiveness of aspects of corporate governance for predicting financial distress in a dynamic discrete-time survival analysis model. It is a comprehensive, up-to-date and thorough study, which uses a large range of corporate governance measures, financial ratios and macroeconomic variables in a panel data structure over a 17-year period. Furthermore, the paper addresses the relationship between government ownership and the risk of financial distress in China. The results suggest that although corporate governance alone is not sufficient to accurately predict financial distress, it can add to the predictive power of financial ratios and macroeconomic factors. In addition, the model provides insights into the role of state ownership, independent directors, institutional investors and some personal characteristics of the Chair of the board. Implications are made regarding them and the debt and bankruptcy problem in China and Asia.

How innovation impacts firms' export survival: Does export mode matter?

AbstractThe innovation‐export nexus has been extensively explored, while relatively few studies have focused on innovation's impact on firms' export survival and the role of export mode. Using a large panel dataset from China, this research empirically explores how innovation impacts firms' export survival, considering export modes. First, we employ the discrete‐time survival analysis model (cloglog) to examine this research addressing the censored issue. Second, the propensity score matching (PSM) methodology is employed to address the selection‐bias issue and select the similar firms based on which to compare their Kaplan–Meier survivor probability. Results present a positive role of innovation in the export survival of direct exporters; however, there is an inverted‐U relationship between innovation intensity and their survival probability. For indirect exporters, evidence shows an insignificant innovation‐export survival nexus. In addition, results show higher export survival for Chinese innovative exporters who are foreign‐owned, highly export‐intensive, long‐lasting in export market, in technology industries. For innovative exporters who export directly, those in medium and low‐technological industries and export capital goods are more likely to survive. Our research provides insights for Chinese exporters regarding innovation participation and suggests the government conducting prudent and deliberate design for innovation strategy.

Credit risk modelling under recessionary and financially distressed conditions

Abstract This paper provides clear cut evidence that economic recession and distressed financial conditions, as well as political instability constitute the key factors for mortgage default. Banning foreclosure procedures, often adopted by governments to mitigate the effects of the above conditions on loan defaulting, are found to positively influence the loan default probability, and thus they make efforts of banks to restructure (or refinance) mortgage loans a difficult task. Our results add support to the view that foreclosure moratorium may raise moral hazard incentives that borrowers will not maintain their payments in long run. The empirical analysis of the paper is based on an extension of the discrete-time survival analysis model which allows for a structural break in its baseline hazard function and a unique set of individual loan accounts. We also consider alternative specifications of the binary link function between default events and covariates. Asymmetric link functions are found to be more appropriate under financial distressed conditions.

Long-term effects of mental disorders on marital outcomes in the National Comorbidity Survey ten-year follow-up.

Epidemiological research has consistently shown an association between mental disorders and marital dissolution. However, this research mostly examined the association of divorce as a risk factor for mental illness. This study prospectively examined the associations of mood, anxiety, and substance use disorders with future marital dissolution and new marriages in a representative population sample. The study used data from the National Comorbidity Survey panel study-a two-wave community epidemiological survey of 5001 participants interviewed in 1990-1992 and re-interviewed in 2001-2003. Mental disorders were ascertained with the Composite International Diagnostic Interview, a fully structured instrument. Associations of baseline lifetime disorders and disorders with onset after the baseline with subsequent divorce and marriage/remarriage were examined using discrete-time survival analysis models. Mental disorders at baseline or with onset after baseline were associated with significantly greater odds of subsequent divorce among respondents who either were married at baseline or got married after baseline. Mental disorders with onset after baseline were associated with smaller odds of marriage or remarriage. Projections assuming causal effects of mental illness on marital outcomes suggest that preventing the effects of common mood, anxiety, and substance use disorders would be associated with 6.7million fewer divorces and 3.5million more marriages in the US population over an 11-year period. Individuals with common mental disorders are at greater risk of marital dissolution and are less likely to enter new marriages. These factors contribute to the diminished social engagement and social support for individuals with these disorders. Interventions aimed at improving marital and family relationships could potentially ameliorate the effect of mental disorders on these vital social ties.

A retrospective assessment of the effect of fallowing on piscirickettsiosis in Chile

Piscirickettsiosis is an endemic disease of farmed salmonids in Chile, and is the main cause of infectious disease-related losses in the Chilean aquaculture industry. Inconsistent results with the use of vaccines and antimicrobials have led producers and government to search for alternative control measures. Fallowing sites between fish production cycles has been mandated by the government authority, but the effectiveness of this practice for preventing this disease has not been assessed under field conditions. We used a discrete-time survival analysis model to evaluate the effect of the duration of the fallow period on the hazard of piscirickettsiosis during the first 24weeks of the production cycle on farms between September 2009 and August 2015. We compared the hazard of piscirickettsia for production cycles on farms that did and did not report the disease immediately before fallowing in the preceding cycle. We controlled for potential confounders, including external infectious pressure from neighboring farms. Our results showed that for both Atlantic salmon and rainbow trout there was no significant difference between the hazard of SRS for farms that reported the disease in the previous cycle and the comparison group, when these farms fallowed for more than three months. Shorter fallow periods were only assessed in rainbow trout, and findings indicate that the hazard of piscirickettsiosis is higher for farms with a recent history of the disease than for farms without a recent history of the disease prior to fallowing. These results suggest that fallowing for three months may be adequate to lower the exposure of P. salmonis from one production cycle to the next; however, our study also suggests there is a high hazard of observing SRS on farms, regardless of fallowing.

Indiana Emergent Bilingual Student Time to Reclassification

In this study, we employed a discrete-time survival analysis model to examine Indiana emergent bilingual time to reclassification as fluent English proficient. The data consisted of five years of statewide English language proficiency scores. Indiana has a large and rapidly growing Spanish-speaking emergent bilingual population, and these students are prevalent in the low socioeconomic status group. Our findings suggest that Spanish home language status, low socioeconomic status, and special education status are negatively associated with the odds to reclassification. Based on our findings, we recommend a careful investigation to inform best practices that will meet the needs of Spanish-speaking emergent bilinguals and reduce inequities in education.

Minimal disease activity and anti-tumor necrosis factor therapy in psoriatic arthritis.

A state of minimal disease activity (MDA) was defined and validated as target for treatment in psoriatic arthritis (PsA). We aimed to identify disease characteristics, outcome, and predictors of MDA in patients treated with tumor necrosis factor α (TNFα) blockers. Patients fulfilling the Classification of Psoriatic Arthritis criteria treated with TNFα blockers were followed every 3-6 months. Patients were considered in MDA when they meet at least 5 of the 7 criteria. Sustained MDA was defined as an MDA state lasting ≥12 months. Patients achieving MDA were compared to non-MDA patients. A proportional odds discrete time survival analysis model was applied, adjusting for sex, age, PsA duration, abnormal erythrocyte sedimentation rate (ESR) and clinically damaged joint count at each visit to identify predictors for MDA. Of the 306 patients treated with TNFα blockers identified from our database, 23 patients were in an MDA state when treatment was commenced; 57 were taking TNFα blockers prior to enrollment. Therefore, 226 subjects were in a non-MDA state and constituted the study population. One hundred forty-five patients of 226 patients (64%) achieved MDA within a mean ± SD duration of 1.30 ± 1.68 years. The mean ± SD duration of MDA was 3.46 ± 2.25 years. At total of 17 patients withdrew from therapy and remained in an MDA state. Male sex (odds ratio [OR] 1.65, 95% confidence interval [95% CI] 1.08-2.53; P = 0.02) and normal ESR (OR 2.27, 95% CI 1.22-4.17; P = 0.009) increased the odds for achieving MDA. MDA is achieved in 64% of patients treated with TNFα blockers in a clinical setting. Male sex and normal ESR are predictors for MDA. On withdrawal or reduction in treatment, 11.6% of patients maintained MDA state.

SAT0273 The Characteristics and Predictors of Minimal Disease Activity in Patients with Psoriatic Arthritis on TNF Blockers

BackgroundThe introduction of TNF blockers in psoriatic arthritis (PsA) has altered the disease course and was shown to reduce disease activity and radiographic progression. Clinical remission requires achieving disease quiescence...

Risk of Breastfeeding Cessation Among Low-Income Women, Infants, and Children

Women who receive services from the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) often stop breastfeeding earlier than recommended. Little is known about maternal background and intrapersonal variables that predict the timing of breastfeeding cessation over the 12-month postpartum period. The aim of this study was to identify the maternal background and intrapersonal predictors associated with the timing of breastfeeding cessation in WIC participants over the course of the 12-month postpartum period. Existing longitudinal survey and administrative data from low-income breastfeeding WIC recipients (n = 309) were analyzed using discrete time survival analysis. Risk of breastfeeding cessation was the outcome, and self-reported items were used to derive predictor variables that corresponded to the background and intrapersonal variables of the Interaction Model of Client Health Behavior. Rates of breastfeeding were low (31% at 6 months and 6% at 12 months). In the best fitting discrete time survival analysis model, women who were older and of Mexican ethnicity, who had previous breastfeeding experience, and who had breastfeeding support from family or friends were at lowest risk for breastfeeding cessation at each monthly interval. Breastfeeding duration rates were lower than Healthy People 2020 benchmarks of 61% at 6 months and 34% at 12 months. Clinicians and researchers can use the findings from this study to develop interventions that are targeted to periods of greatest risk of premature breastfeeding cessation to prolong breastfeeding duration in this vulnerable population.

Effects of Hours of Service and Driving Patterns on Motor Carrier Crashes

There is a need to explore the relationship, if any, between the probability of a crash and the hours worked by truck drivers. The need arises from the continued adjustment of federal hours of service regulations for truck drivers. This research used data logs from less-than-truckload carrier operations in 2004 to 2005 and in 2010 to estimate the probability of a crash after a certain amount of time spent driving, given no crashes until that time. Driver logs for 7 days before each crash were used and compared with a random sample (two drivers) of drivers who did not crash and were selected from the same company, terminal, and month. This study involved 686 subjects, including 224 crash-involved drivers. Discrete-time survival analysis models indicated a consistent increase in crash odds as driving time increased beyond the fourth hour. Breaks from driving reduced crash odds by as much as 50% compared with situations of drivers with no breaks. Crash odds were lowest when drivers returned to work during the day without an immediately preceding extended recovery period (but with at least minimum required off-duty time). Drivers returning to work immediately after a 34-h recovery period had crash odds 50% to 150% higher than those for drivers without the recovery immediately before a trip. Drivers had the highest crash odds immediately after returning from the extended time off; the effect then diminished with time.

Another baby? Father involvement and childbearing in fragile families.

An historic number of women in the United States have children outside of marriage, and with more than one father, yet little research has examined the association between family process and women's childbearing decisions. Using a subsample of unmarried women from the Fragile Families and Child Wellbeing Study (n = 2028), a study of primarily low-income unmarried parents, we conducted discrete-time survival analysis models to predict whether women had another child with the focal child's father (same-father birth) or with a new father (new-father birth). Father involvement was measured by engagement, indirect care, accessibility, and financial support. Overall, mothers who reported greater engagement and indirect care from the focal child's father were more likely to have a same-father birth even when he was not living in her home, and were also less likely to have a new-father birth. Further, mothers who reported greater accessibility and stable financial support from the focal child's nonresident father were also less likely to have a new-father birth. One pathway through which this may have occurred was that single mothers who perceived less indirect care and accessibility from the focal child's nonresident father were more likely to begin new romantic relationships. Indeed, whether or not the mother had a new romantic partner partially mediated the association between indirect care and a same-father birth and fully mediated the association between accessibility and a new-father birth, suggesting that one pathway linking father involvement to a new-father birth was through maternal repartnering. Clinical and policy implications are discussed.

Comparison of Methods for Measuring Crowding and Its Effects on Length of Stay in the Emergency Department

This consensus conference presentation article focuses on methods of measuring crowding. The authors compare daily versus hourly measures, static versus dynamic measures, and the use of linear or logistic regression models versus survival analysis models to estimate the effect of crowding on an outcome. Emergency department (ED) visit data were used to measure crowding and completion of waiting room time, treatment time, and boarding time for all patients treated and released or admitted to a single ED during 2010 (excluding patients who left without being seen). Crowding was characterized according to total ED census. First, total ED census on a daily and hourly basis throughout the 1-year study period was measured, and the ratios of daily and hourly census to the ED's median daily and hourly census were computed. Second, the person-based ED visit data set was transposed to person-period data. Multiple records per patient were created, whereby each record represented a consecutive 15-minute interval during each patient's ED length of stay (LOS). The variation in crowding measured statically (i.e., crowding at arrival or mean crowding throughout the shift in which the patient arrived) or dynamically (every 15 minutes throughout each patient's ED LOS) were compared. Within each phase of care, the authors divided each individual crowding value by the median crowding value of all 15-minute intervals to create a time-varying ED census ratio. For the two static measures, the ratio between each patient's ED census at arrival and the overall median ED census at arrival was computed, as well as the ratio between the mean shift ED census (based on the shift in which the patient arrived) and the study ED's overall mean shift ED census. Finally, the effect of crowding on the probability of completing different phases of emergency care was compared when estimated using a log-linear regression model versus a discrete time survival analysis model. During the 1-year study period, for 9% of the hours, total ED census was at least 50% greater than the median hourly census (median, 36). In contrast, on none of the days was total ED census at least 50% greater than the median daily census (median, 161). ED census at arrival and time-varying ED census yielded greater variation in crowding exposure compared to mean shift census for all three phases of emergency care. When estimating the effect of crowding on the completion of care, the discrete time survival analysis model fit the observed data better than the log-linear regression models. The discrete time survival analysis model also determined that the effect of crowding on care completion varied during patients' ED LOS. Crowding measured at the daily level will mask much of the variation in crowding that occurs within a 24-hour period. ED census at arrival demonstrated similar variation in crowding exposure as time-varying ED census. Discrete time survival analysis is a more appropriate approach for estimating the effect of crowding on an outcome.

Fraudulent Statements Disclosure And Financial Distress: A Discrete-Time Survival Analysis

&lt;p class="MsoNormal" style="text-justify: inter-ideograph; text-align: justify; line-height: 12pt; margin: 0in 36.1pt 0pt 0.5in; mso-layout-grid-align: none; mso-line-height-rule: exactly;"&gt;&lt;span style="font-family: Times New Roman;"&gt;&lt;span style="font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt;"&gt;This study &lt;/span&gt;&lt;span style="font-size: 10pt;"&gt;uses discrete-time survival analysis (DTSA) to&lt;/span&gt;&lt;span style="font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt;"&gt; examine the &lt;/span&gt;&lt;span style="font-size: 10pt;"&gt;influence of fraudulent statements disclosure on the probability of financial distress not only in the initial period subsequent to disclosure, but future periods as well. Evidence indicates DTSA is superior to logistic regression and extends a richer depiction of the probability after a first-time fraudulent statement disclosure. After &lt;/span&gt;&lt;span style="font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt; mso-bidi-font-weight: bold;"&gt;fraudulent statements disclosure,&lt;/span&gt;&lt;span style="color: black; font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt;"&gt; 24% of the reporting firms &lt;/span&gt;&lt;span style="font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt; mso-bidi-font-weight: bold;"&gt;experienced financial distress in Year 1, with the hazard function declines progressively in subsequent years. &lt;/span&gt;&lt;span style="font-size: 10pt;"&gt;We find total liability to total assets, &lt;/span&gt;&lt;span style="font-size: 10pt; mso-font-kerning: 0pt; mso-bidi-font-weight: bold;"&gt;directors and supervisors&amp;rsquo; stock pledged ratio, and CPA (Certified Public Accountant) change are definitely linked to financial distress probability (p-value &amp;lt;0.05). A DTSA model not only includes financial ratios, but also considers corporate governance variables to produce more accurate classification than those of alternative models. &lt;/span&gt;&lt;/span&gt;&lt;span style="font-size: 10pt; mso-fareast-font-family: DFKai-SB; mso-font-kerning: 0pt;"&gt;&lt;/span&gt;&lt;/p&gt;

The Effect of Season on Somatic Cell Count and the Incidence of Clinical Mastitis

Bulk milk somatic cell count (BMSCC), individual cow somatic cell count (ICSCC), and incidence rate of clinical mastitis (IRCM) are all udder health parameters. So far, no studies have been reported on the effect of season on BMSCC, IRCM, and ICSCC in the same herds and period over multiple years. The objectives of this study were to determine the seasonal pattern over a 4-yr period of 1) BMSCC, 2) elevated ICSCC, 3) IRCM, and 4) pathogen-specific IRCM. Bulk milk somatic cell count, ICSCC, and pathogen-specific clinical mastitis data were recorded in 300 Dutch dairy farms. For the analyses of BMSCC, ICSCC, and IRCM, a mixed, a transitional, and a discrete time survival analysis model were used, respectively. Sine and cosine were included in the models to investigate seasonal patterns in the data. For all parameters, a seasonal effect was present. Bulk milk somatic cell count peaked in August to September in all 4 years. The probability of cows getting or maintaining a high ICSCC was highest in August and May, respectively. Older and late-lactation cows were more likely to develop or maintain a high ICSCC. Incidence rate of clinical mastitis was highest in December to January, except for Streptococcus uberis IRCM, which was highest in August. Totally confined herds had a higher Escherichia coli IRCM in summer than in winter. Compared with the major mastitis pathogens, the seasonal differences in IRCM were smaller for the minor pathogens. Distinguishing between Strep. uberis, Streptococcus dysgalactiae, Streptococcus agalactiae, and other streptococci is essential when identifying Streptococcus spp. because each of them has a unique epidemiology. Streptococcus uberis IRCM seemed to be associated with being on pasture, whereas E. coli IRCM was more housing-related.

Exposure opportunity as a mechanism linking youth marijuana use to hallucinogen use

The aim of this study is to shed light upon an observed association between the use of marijuana and hallucinogens (e.g. LSD), with a specific focus on the idea that two separate mechanisms might link marijuana use to hallucinogen use: (1) greater hallucinogen exposure opportunity for marijuana users versus nonusers; (2) increased probability of hallucinogen use for marijuana users versus nonusers, once the opportunity to use hallucinogens has occurred. This work is based on a novel analysis of retrospective, self-report data from more than 40 000 young participants in the 1991–1994 National Household Surveys on Drug Abuse (NHSDA), with discrete time survival analysis models. Youths who had used marijuana were substantially more likely than nonusers to have the opportunity to use hallucinogens (estimated unadjusted relative risk, uRR=16.3; 95%. Confidence interval (CI)=14.3–18.6). Once an opportunity to use hallucinogens occurred, marijuana users were more likely than nonusers to initiate hallucinogen use (uRR=12.6; 95% CI=9.0–17.6). This evidence provides a more complete view of interconnections between marijuana use and hallucinogen use, and helps to clarify the pivotal role for drug exposure opportunities. Important next steps will be to understand what accounts for variation in the exposure opportunities experienced by marijuana users, and to understand why some marijuana users do not progress even when they have a chance to do so.