Imputing Risk Tolerance From Survey Responses.
Ontology highlight
ABSTRACT:
SUBMITTER: Kimball MS
PROVIDER: S-EPMC2856097 | biostudies-literature | 2008 Sep
REPOSITORIES: biostudies-literature
Publications
Imputing Risk Tolerance From Survey Responses.
Kimball Miles S MS Sahm Claudia R CR Shapiro Matthew D MD
Journal of the American Statistical Association 20080901 483
Economic theory assigns a central role to risk preferences. This article develops a measure of relative risk tolerance using responses to hypothetical income gambles in the Health and Retirement Study. In contrast to most survey measures that produce an ordinal metric, this article shows how to construct a cardinal proxy for the risk tolerance of each survey respondent. The article also shows how to account for measurement error in estimating this proxy and how to obtain consistent regression es ...[more]
Similar Datasets
Project description:We develop a method of imputing ego network characteristics for respondents in probability samples of individuals. This imputed network uses the homophily principle to estimate certain properties of a respondent's core discussion network in the absence of actual network data. These properties measure the potential exposure of respondents to the attitudes, values, beliefs, etc. of their (likely) network alters. We use American National Election Survey data (2016 ANES) to demonstrate that the imputed network features show substantial effects on individual level measures, such as political attitudes and beliefs. In some cases, the imputed network variable substantially reduces the effects of standard socio-demographic variables like age and education. We argue that the imputed network variable captures many of the aspects of social context that have been at the core of sociological analysis for decades.
| S-EPMC6720115 | biostudies-literature
Project description:ObjectiveTo determine tolerance to various risk scenarios associated with current multiple sclerosis (MS) therapies.MethodsPeople with MS from the North American Research Committee on Multiple Sclerosis Registry's online cohort and the National Multiple Sclerosis Society were invited to complete a questionnaire on tolerance to real-world risks associated with a hypothetical therapy. Multiple risks levels were presented, including skin rash, infection, kidney injury, thyroid injury, liver injury, and progressive multifocal leukoencephalopathy (PML).ResultsBoth PML and kidney injury had the lowest risk tolerance (RT) at 1:1,000,000, and thyroid and infection risks had the highest tolerance at 1:1,000. Men, younger individuals, and participants with greater disability reported a higher tolerance to all risk scenarios. Those who were currently taking an MS therapy reported higher tolerance than those not taking any therapy. Participants taking infusion therapies reported high tolerance to all risks, and those taking injectables reported a lower tolerance.ConclusionPeople with MS displayed a wide range of RT for MS therapies. Our study identified sex, age, disability, and current disease-modifying therapy use to be associated with RT.
| S-EPMC6448448 | biostudies-literature
Project description:Missing data are frequently encountered in molecular phylogenetics, but there has been no accurate distance imputation method available for distance-based phylogenetic reconstruction. The general framework for distance imputation is to explore tree space and distance values to find an optimal combination of output tree and imputed distances. Here I develop a least-square method coupled with multivariate optimization to impute multiple missing distance in a distance matrix or from a set of aligned sequences with missing genes so that some sequences share no homologous sites (whose distances therefore need to be imputed). I show that phylogenetic trees can be inferred from distance matrices with about 10% of distances missing, and the accuracy of the resulting phylogenetic tree is almost as good as the tree from full information. The new method has the advantage over a recently published one in that it does not assume a molecular clock and is more accurate (comparable to maximum likelihood method based on simulated sequences). I have implemented the function in DAMBE software, which is freely available at http://dambe.bio.uottawa.ca.
| S-EPMC6063210 | biostudies-literature
Project description:Background and objectivesIt is widely recognized that survey satisficing, inattentive, or careless responding in questionnaires reduce the quality of self-report data. In this study, we propose that such low-quality responding (LQR) can carry substantive meaning at older ages. Completing questionnaires is a cognitively demanding task and LQR among older adults may reflect early signals of cognitive deficits and pathological aging. We hypothesized that older people displaying greater LQR would show faster cognitive decline and greater mortality risk.Research design and methodsWe analyzed data from 9, 288 adults 65 years or older in the Health and Retirement Study. Indicators of LQR were derived from participants' response patterns in 102 psychosocial questionnaire items administered in 2006-2008. Latent growth models examined whether LQR predicted initial status and change in cognitive functioning, assessed with the modified Telephone Interview for Cognitive Status, over the subsequent 10 years. Discrete-time survival models examined whether LQR was associated with mortality risk over the 10 years. We also examined evidence for indirect (mediated) effects in which LQR predicts mortality via cognitive trajectories.ResultsAfter adjusting for age, gender, race, marital status, education, health conditions, smoking status, physical activity, and depressive symptoms, greater LQR was cross-sectionally associated with poorer cognitive functioning, and prospectively associated with faster cognitive decline over the follow-up period. Furthermore, greater LQR was associated with increased mortality risk during follow-up, and this effect was partially accounted for by the associations between LQR and cognitive functioning.Discussion and implicationsSelf-report questionnaires are not formally designed as cognitive tasks, but this study shows that LQR indicators derived from self-report measures provide objective, performance-based information about individuals' cognitive functioning and survival. Self-report surveys are ubiquitous in social science, and indicators of LQR may be of broad relevance as predictors of cognitive and health trajectories in older people.
| S-EPMC9155162 | biostudies-literature
Project description:We describe a new method to combine propensity-score matching with regression adjustment in treatment-control studies when outcomes are binary by multiply imputing potential outcomes under control for the matched treated subjects. This enables the estimation of clinically meaningful measures of effect such as the risk difference. We used Monte Carlo simulation to explore the effect of the number of imputed potential outcomes under control for the matched treated subjects on inferences about the risk difference. We found that imputing potential outcomes under control (either single imputation or multiple imputation) resulted in a substantial reduction in bias compared with what was achieved using conventional nearest neighbor matching alone. Increasing the number of imputed potential outcomes under control resulted in more efficient estimation, with more efficient estimation of the estimated risk difference when increasing the number of the imputed potential outcomes. The greatest relative increase in efficiency was achieved by imputing five potential outcomes; once 20 outcomes under control were imputed for each matched treated subject, further improvements in efficiency were negligible. We also examined the effect of the number of these imputed potential outcomes on: (i) estimated standard errors; (ii) mean squared error; (iii) coverage of estimated confidence intervals. We illustrate the application of the method by estimating the effect on the risk of death within 1 year of prescribing beta-blockers to patients discharged from hospital with a diagnosis of heart failure.
| S-EPMC8596520 | biostudies-literature
Project description:High-pressure processing is a nonthermal method of food preservation that uses pressure to inactivate microorganisms. To ensure the effective validation of process parameters, it is important that the design of challenge protocols consider the potential for resistance in a particular species. Herein, the responses of 99 diverse Salmonella enterica strains to high pressure are reported. Members of this population belonged to 24 serovars and were isolated from various Canadian sources over a period of 26 years. When cells were exposed to 600 MPa for 3 min, the average reduction in cell numbers for this population was 5.6 log10 CFU/ml, with a range of 0.9 log10 CFU/ml to 6 log10 CFU/ml. Eleven strains, from 5 serovars, with variable levels of pressure resistance were selected for further study. The membrane characteristics (propidium iodide uptake during and after pressure treatment, sensitivity to membrane-active agents, and membrane fatty acid composition) and responses to stressors (heat, nutrient deprivation, desiccation, and acid) for this panel suggested potential roles for the cell membrane and the RpoS regulon in mediating pressure resistance in S. enterica The data indicate heterogeneous and multifactorial responses to high pressure that cannot be predicted for individual S. enterica strains.IMPORTANCE The responses of foodborne pathogens to increasingly popular minimal food decontamination methods are not understood and therefore are difficult to predict. This report shows that the responses of Salmonella enterica strains to high-pressure processing are diverse. The magnitude of inactivation does not depend on how closely related the strains are or where they were isolated. Moreover, strains that are resistant to high pressure do not behave similarly to other stresses, suggesting that more than one mechanism might be responsible for resistance to high pressure and the mechanisms used may vary from one strain to another.
| S-EPMC5752854 | biostudies-literature
Project description:BackgroundChronic hepatitis C virus infection is prevalent and often causes hepatic fibrosis, which can progress to cirrhosis and cause liver cancer or liver failure. Study of fibrosis progression often relies on imputing the time of infection, often as the reported age of first injection drug use. We sought to examine the accuracy of such imputation and implications for modeling factors that influence progression rates.MethodsWe analyzed cross-sectional data on hepatitis C antibody status and reported risk factor histories from two large studies, the Women's Interagency HIV Study and the Urban Health Study, using modern survival analysis methods for current status data to model past infection risk year by year. We compared fitted distributions of past infection risk to reported age of first injection drug use.ResultsAlthough injection drug use appeared to be a very strong risk factor, models for both studies showed that many subjects had considerable probability of having been infected substantially before or after their reported age of first injection drug use. Persons reporting younger age of first injection drug use were more likely to have been infected after, and persons reporting older age of first injection drug use were more likely to have been infected before.ConclusionIn cross-sectional studies of fibrosis progression where date of HCV infection is estimated from risk factor histories, modern methods such as multiple imputation should be used to account for the substantial uncertainty about when infection occurred. The models presented here can provide the inputs needed by such methods. Using reported age of first injection drug use as the time of infection in studies of fibrosis progression is likely to produce a spuriously strong association of younger age of infection with slower rate of progression.
| S-EPMC2238758 | biostudies-literature
Project description:BackgroundEffective risk communication is one of the critical strategies in the response to COVID-19. This study examined risk perceptions and attitudinal responses to COVID-19 among the educated section of the society in Ethiopia.MethodsAn internet-based survey was conducted from April 22 to May 04, 2020, in Ethiopia. A questionnaire addressing the perception of health threat-combination of perceived vulnerability (PV) and perceived seriousness (PS), and perceived efficacy-combinations of perceived response efficacy (PRE), perceived self-efficacy (PSE), and perceived collective efficacy (PCE). The data were analyzed using SPSS 21.0. Descriptive statistics were computed after the standardization of the scores. The scores for overall efficacy and threat were split by median value and response classifications were generated through threat by efficacy interactions. For statistical significance, 95% CI and p-value < 0.05 were used.ResultsA total of 929 respondents submitted their responses. Eight hundred and twenty-eight (89.1%) of the respondents were male and 753 (81.1%) were Christian. The perceived threat to COVID-19 was generally low (median = 58.3). The median score for overall efficacy, PRE, and PSE were 79.8, 87.5, and 80.0, respectively. However, the median value (66.7) for PCE was relatively low. Perceived threat significantly varied by age, education, occupation, and place of residence (p < 0.05). Perceived efficacy significantly differed by gender, residence, and use of some sources of information (p < 0.05). In terms of response to COVID-19, 290 (31.2%), 239 (25.7%), 175 (18.8%) and 225 (24.2%) of the respondents were in the responsive, pro-active, avoidant, and indifferent attitudinal categories, respectively. The avoidant and indifferent groups constituted a fear control response (mal-adaptive motivation towards COVID-19 protective behavior) whereas responsive and pro-active categories formed a danger control response (self-protective motivation). These responses varied significantly by residence, region, religion, and sources of information (p < 0.05).ConclusionsUnderstanding people's perceived health threat and efficacy is a critical step toward creating risk communication campaigns. Hence, this study provided an insight that has the potential to inform the COVID-19 risk communication campaigns targeting the educated section of the society, by ensuring a balanced combination of threat appeals and efficacy messages for improved self-protective responses.
| S-EPMC8148408 | biostudies-literature
Project description:Microarray measurements of gene expression constitute a large fraction of publicly shared biological data, and are available in the Gene Expression Omnibus (GEO). Many studies use GEO data to shape hypotheses and improve statistical power. Within GEO, the Affymetrix HG-U133A and HG-U133 Plus 2.0 are the two most commonly used microarray platforms for human samples; the HG-U133 Plus 2.0 platform contains 54 220 probes and the HG-U133A array contains a proper subset (21 722 probes). When different platforms are involved, the subset of common genes is most easily compared. This approach results in the exclusion of substantial measured data and can limit downstream analysis. To predict the expression values for the genes unique to the HG-U133 Plus 2.0 platform, we constructed a series of gene expression inference models based on genes common to both platforms. Our model predicts gene expression values that are within the variability observed in controlled replicate studies and are highly correlated with measured data. Using six previously published studies, we also demonstrate the improved performance of the enlarged feature space generated by our model in downstream analysis. Availability and Implementation:The gene inference model described in this paper is available as a R package (affyImpute), which can be downloaded at http://simtk.org/home/affyimpute. Contact:rbaltman@stanford.edu. Supplementary information:Supplementary data are available at Bioinformatics online.
| S-EPMC5408923 | biostudies-literature
Project description:Genome-wide association studies (GWASs) have been successful in detecting variants correlated with phenotypes of clinical interest. However, the power to detect these variants depends on the number of individuals whose phenotypes are collected, and for phenotypes that are difficult to collect, the sample size might be insufficient to achieve the desired statistical power. The phenotype of interest is often difficult to collect, whereas surrogate phenotypes or related phenotypes are easier to collect and have already been collected in very large samples. This paper demonstrates how we take advantage of these additional related phenotypes to impute the phenotype of interest or target phenotype and then perform association analysis. Our approach leverages the correlation structure between phenotypes to perform the imputation. The correlation structure can be estimated from a smaller complete dataset for which both the target and related phenotypes have been collected. Under some assumptions, the statistical power can be computed analytically given the correlation structure of the phenotypes used in imputation. In addition, our method can impute the summary statistic of the target phenotype as a weighted linear combination of the summary statistics of related phenotypes. Thus, our method is applicable to datasets for which we have access only to summary statistics and not to the raw genotypes. We illustrate our approach by analyzing associated loci to triglycerides (TGs), body mass index (BMI), and systolic blood pressure (SBP) in the Northern Finland Birth Cohort dataset.
| S-EPMC5005435 | biostudies-literature