Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 65.184
BMJ Open ; 13(2): e065576, 2023 Feb 01.
Article in English | MEDLINE | ID: mdl-36725096


INTRODUCTION: Observational studies in health-related research often aim to answer causal questions. Missing data are common in these studies and often occur in multiple variables, such as the exposure, outcome and/or variables used to control for confounding. The standard classification of missing data as missing completely at random, missing at random (MAR) or missing not at random does not allow for a clear assessment of missingness assumptions when missingness arises in more than one variable. This presents challenges for selecting an analytic approach and determining when a sensitivity analysis under plausible alternative missing data assumptions is required. This is particularly pertinent with multiple imputation (MI), which is often justified by assuming data are MAR. The objective of this scoping review is to examine the use of MI in observational studies that address causal questions, with a focus on if and how (a) missingness assumptions are expressed and assessed, (b) missingness assumptions are used to justify the choice of a complete case analysis and/or MI for handling missing data and (c) sensitivity analyses under alternative plausible assumptions about the missingness mechanism are conducted. METHODS AND ANALYSIS: We will review observational studies that aim to answer causal questions and use MI, published between January 2019 and December 2021 in five top general epidemiology journals. Studies will be identified using a full text search for the term 'multiple imputation' and then assessed for eligibility. Information extracted will include details about the study characteristics, missing data, missingness assumptions and MI implementation. Data will be summarised using descriptive statistics. ETHICS AND DISSEMINATION: Ethics approval is not required for this review because data will be collected only from published studies. The results will be disseminated through a peer reviewed publication and conference presentations. TRIAL REGISTRATION NUMBER: This protocol is registered on figshare (

Models, Statistical , Research Design , Humans , Data Interpretation, Statistical , Observational Studies as Topic , Review Literature as Topic
Methods Mol Biol ; 2624: 7-18, 2023.
Article in English | MEDLINE | ID: mdl-36723806


Arrays provide a cost-effective platform for the analysis of human DNA methylation. ShinyÉPICo is an interactive, web-based, and graphical tool that allows the user to analyze Illumina DNA methylation arrays (450 k and EPIC), from the user's own computer or from a server. This tool covers the analysis entirely, from the raw data input to the final list of differentially methylated positions or regions. Here, we describe the steps of the analysis, the different parameters available, and useful information to understand and select the best options in each step.

DNA Methylation , Software , Humans , Data Interpretation, Statistical , CpG Islands
Sci Rep ; 13(1): 644, 2023 Jan 12.
Article in English | MEDLINE | ID: mdl-36635443


Fully conditional specification (FCS) is a convenient and flexible multiple imputation approach. It specifies a sequence of simple regression models instead of a potential complex joint density for missing variables. However, FCS may not converge to a stationary distribution. Many authors have studied the convergence properties of FCS when priors of conditional models are non-informative. We extend to the case of informative priors. This paper evaluates the convergence properties of the normal linear model with normal-inverse gamma priors. The theoretical and simulation results prove the convergence of FCS and show the equivalence of prior specification under the joint model and a set of conditional models when the analysis model is a linear regression with normal inverse-gamma priors.

Models, Statistical , Linear Models , Data Interpretation, Statistical , Computer Simulation , Bayes Theorem
Neuroimage ; 266: 119807, 2023 02 01.
Article in English | MEDLINE | ID: mdl-36513290


Analysis and interpretation of neuroimaging datasets has become a multidisciplinary endeavor, relying not only on statistical methods, but increasingly on associations with respect to other brain-derived features such as gene expression, histological data, and functional as well as cognitive architectures. Here, we introduce BrainStat - a toolbox for (i) univariate and multivariate linear models in volumetric and surface-based brain imaging datasets, and (ii) multidomain feature association of results with respect to spatial maps of post-mortem gene expression and histology, task-based fMRI meta-analysis, as well as resting-state fMRI motifs across several common surface templates. The combination of statistics and feature associations into a turnkey toolbox streamlines analytical processes and accelerates cross-modal research. The toolbox is implemented in both Python and MATLAB, two widely used programming languages in the neuroimaging and neuroinformatics communities. BrainStat is openly available and complemented by an expandable documentation.

Brain , Software , Humans , Brain/diagnostic imaging , Data Interpretation, Statistical , Datasets as Topic , Linear Models , Magnetic Resonance Imaging , Neuroimaging , Meta-Analysis as Topic
J Speech Lang Hear Res ; 66(1): 347-364, 2023 Jan 12.
Article in English | MEDLINE | ID: mdl-36542850


PURPOSE: This article provides a tutorial introduction to ordinal pattern analysis, a statistical analysis method designed to quantify the extent to which hypotheses of relative change across experimental conditions match observed data at the level of individuals. This method may be a useful addition to familiar parametric statistical methods including repeated measures analysis of variance and generalized linear mixed-effects models, particularly when analyzing inherently individual characteristics, such as perceptual processes, and where experimental effects are usefully modeled in relative rather than absolute terms. METHOD: Three analyses of increasing complexity are demonstrated using ordinal pattern analysis. An initial analysis of a very small data set is designed to explicate the simple mathematical calculations that make up ordinal pattern analysis, which can be performed without the aid of a computer. Analyses of slightly larger data sets are used to demonstrate familiar concepts, including comparison of competing hypotheses, handling missing data, group comparisons, and pairwise tests. All analyses can be reproduced using provided code and data. RESULTS: Ordinal pattern analysis results are presented, along with an analogous linear mixed-effects analysis, to illustrate the similarities and differences in information provided by ordinal pattern analysis in comparison to familiar parametric methods. CONCLUSION: Although ordinal pattern analysis does not produce familiar numerical effect sizes, it does provide highly interpretable results in terms of the proportion of individuals whose results are consistent with a hypothesis, along with individual and group-level statistics, which quantify hypothesis performance.

Research Design , Humans , Linear Models , Data Interpretation, Statistical
Article in English, Portuguese | LILACS, BDENF - Nursing | ID: biblio-1413336


Objetivo: analisar a incidência de neoplasias malignas em 2020. Métodos: estudo ecológico com análise comparativa entre as populações de Porto Alegre e Salvador. Foram extraídos dados do DATASUS, analisados em tabelas e apresentados em gráficos. Resultados: A incidência de neoplasias malignas em mulheres entre 30 a 34 anos é maior em Porto Alegre que em Salvador, sendo quase o dobro de casos de mulheres em relação aos homens. Entre 65 a 69 anos, mulheres representaram 20 casos a mais em Porto Alegre, e, em Salvador, o sexo masculino apresentou 28 casos a mais. As mulheres realizaram mais quimioterapias e os homens mais cirurgias. Conclusão: Houve diferença entre a incidência de neoplasias nas cidades podendo associar variáveis determinantes como sexo biológico feminino ao tipo de câncer e idade avançada. A maior incidência de casos na região sul pode estar associada aos hábitos de vida como alimentação e cultura desta região.

Objective: to analyze the incidence of malignant neoplasms in 2020 in two Brazilian cities. Methods: this is an ecological study with comparative analysis between the populations of the cities of Porto Alegre, and Salvador. Data were extracted from the DATASUS, analyzed in tables and presented in descriptive. Results: The incidence of malignant neoplasms in women aged 30 to 34 years is higher of Porto Alegre than in Salvador, with almost double the number of cases in women compared to men in both cities. In the age 65 to 69, women accounted for 20 more cases in Porto Alegre, and in Salvador, males had 28 more cases. Women underwent more chemotherapy and men more surgical in both cities. Conclusion: Differences were observed between the incidence of neoplasms for the cities compared, which could associate determinant variables such as female biological sex with the type of cancer and advanced age. In addition, there is evidence that the southern region of Brazil has a higher incidence than the northeast region, which may be associated with lifestyle habits such as food and culture in the region.

Objetivo: analizar la incidencia de neoplasias malignas en 2020 en dos ciudades brasileñas. Métodos: se trata de un estudio ecológico con análisis comparativo entre las poblaciones de Porto Alegre y Salvador. Los datos fueron extraídos del DATASUS, analizados en tablas y presentados en gráficos. Resultados: La incidencia de neoplasias malignas en mujeres de 30 a 34 años es mayor en Porto Alegre que en Salvador, con casi el doble de casos en mujeres que en hombres. Entre 65 a 69 años, las mujeres representaron 20 casos más en Porto Alegre, y en Salvador, los hombres tuvieron 28 casos más. Las mujeres se sometieron más a quimioterapia y los hombres más a quirúrgias. Conclusión: Se observaron diferencias entre la incidencia de neoplasias, que podrían asociar variables determinantes como el sexo biológico femenino con el tipo de cáncer y la edad avanzada. Existe evidencia de que la región sur de Brasil tiene una mayor incidencia que la región noreste, lo que puede estar asociado con hábitos de estilo de vida como la alimentación y la cultura en la región.

Humans , Male , Female , Adult , Middle Aged , Aged , Incidence , Health Information Systems , Neoplasms/epidemiology , Epidemiologic Studies , Data Interpretation, Statistical
Rev. esp. cardiol. (Ed. impr.) ; 75(12): 1011-1019, dic. 2022. ilus, tab, graf
Article in Spanish | IBECS | ID: ibc-212934


Introducción y objetivos: La insuficiencia cardiaca (IC) es prevalente en edades avanzadas. Nuestro objetivo es conocer el impacto de la fragilidad en la mortalidad a 1 año en pacientes mayores con IC ambulatorios. Métodos: El estudio «Impacto de la fragilidad y otros síndromes geriátricos en el manejo clínico y pronóstico del paciente anciano ambulatorio con insuficiencia cardiaca» (FRAGIC) es un registro prospectivo multicéntrico, realizado en 16 centros españoles, que incluyó pacientes con IC ambulatorios de edad ≥ 75 años seguidos por cardiología en España. Resultados: Se incluyó a 499 pacientes (media de edad, 81,4±4,3 años; 193 [38%] mujeres); 268 (54%) tenían una fracción de eyección del ventrículo izquierdo <40% y el 84,6% estaba en clase funcional II de la NYHA. La escala FRAIL identificó a 244 pacientes prefrágiles (49%) y 111 frágiles (22%). Los pacientes frágiles tenían una media de edad significativamente mayor, eran más frecuentemente mujeres (ambos, p <0,001) y presentaban mayores comorbilidad según el índice de Charlson (p=0,017) y prevalencia de síndromes geriátricos (p <0,001). Tras una mediana de seguimiento de 371 [361-387] días, fallecieron 58 pacientes (11,6%). En el análisis multivariado (modelo de regresión de Cox), la fragilidad mediante la escala FRAIL se asoció marginalmente con la mortalidad (HR=2,35; IC95%, 0,96-5,71; p=0,059); la identificada mediante la escala visual de movilidad (HR=2,26; IC95%, 1,16-4,38; p=0,015) fue predictor independiente de mortalidad, cuya asociación se mantuvo tras ajustar por variables confusoras (HR=2,13; IC95%, 1,08-4,20; p=0,02). Conclusiones: En pacientes mayores ambulatorios con IC, la fragilidad es predictor independiente de mortalidad a 1 año de seguimiento. Debe identificarse como parte del abordaje integral de estos pacientes.(AU)

Introduction and objectives: Heart failure (HF) is prevalent in advanced ages. Our objective was to assess the impact of frailty on 1-year mortality in older patients with ambulatory HF. Methods: Our data come from the FRAGIC study (Spanish acronym for “Study of the impact of frailty and other geriatric syndromes on the clinical management and prognosis of elderly outpatients with heart failure”), a multicenter prospective registry conducted in 16 Spanish hospitals including outpatients ≥ 75 years with HF followed up by cardiology services in Spain. Results: We included 499 patients with a mean age of 81.4±4.3 years, of whom 193 (38%) were women. A total of 268 (54%) had left ventricular ejection fraction <40%, and 84.6% was in NYHA II functional class. The FRAIL scale identified 244 (49%) pre-frail and 111 (22%) frail patients. Frail patients were significantly older, were more frequently female (both, P <.001), and had higher comorbidity according to the Charlson index (P=.017) and a higher prevalence of geriatric syndromes (P <.001). During a median follow-up of 371 [361-387] days, 58 patients (11.6%) died. On multivariate analysis (Cox regression model), frailty detected with the FRAIL scale was marginally associated with mortality (HR=2.35; 95%CI, 0.96-5.71; P=.059), while frailty identified by the visual mobility scale was an independent predictor of mortality (HR=2.26; 95%CI, 1.16-4.38; P=.015); this association was maintained after adjustment for confounding variables (HR=2.13; 95%CI, 1.08-4.20; P=.02). Conclusions: In elderly outpatients with HF, frailty is independently associated with mortality at 1 year of follow-up. It is essential to identify frailty as part of the comprehensive approach to elderly patients with HF.(AU)

Humans , Male , Female , Aged , Heart Failure , Frailty , Frail Elderly , Prognosis , Mortality , Data Interpretation, Statistical , Cardiology , Heart Diseases
Nutr. clín. diet. hosp ; 42(4): 23-34, Dic 4, 2022. tab, graf
Article in Spanish | IBECS | ID: ibc-212965


Introducción: El porcentaje de grasa es determinante enla evaluación de la atención primaria.Objetivo: Comparar ecuaciones antropométricas regio-nales que predicen el porcentaje de grasa corporal (%GC)con ecuaciones extranjeras y, proponer percentiles para va-lorar el % GC de niños y adolescentes de la región delMaule, Chile. Metodología: Se efectuó un estudio transversal (correla-cional) en escolares de la región del Maule (Chile). Se estudióa 1,126 escolares (588 hombres y 538 mujeres) con un rangode edad desde los 6,0 hasta los 17,9 años. Se evaluó la edad,el peso, estatura, circunferencia del abdomen, dos plieguescutáneos (tricipital y subescapular). Se calculó el índice demasa corporal (IMC), Índice Ponderal (IP, Índice Cintura-Talla(ICT), %GC por dos ecuaciones regionales y tres ecuacionesextranjeras (Boileau, Slaughter y Deuremberg). Resultados: Las ecuaciones regionales de chile presentaronvalores de 26,2±7,1%GC (ecuación 1) y 26,2±7,05%GC (ecua-ción 2) en varones, mientras que en mujeres reflejaron 33,6±4,72%GC (ecuación 1) y 33,6±4,70%GC (ecuación 2).Las ecuaciones extranjeras reflejaron valores similares en varo-nes, por ejemplo, de 19,3%±6,9%GC (Boileau), 20,1±8,7%GC(Slaughter) y 20,6±5,3%GC (Deuremberg), mientras que, enlas mujeres fue de 25,9±6,1%GC (Boileau), 25,2±8,8%GC(Slaughter) y 25,0±5,3%GC (Deuremberg). Hubo diferenciassignificativas entre las ecuaciones regionales con las ecuacio-nes extranjeras en ambos sexos (p<0,05). Los percentiles cal-culados fueron: (P3, P5, P10, P15, P25, P50, P75, P85, P90,P95 y P97). Los valores de %GC en las mujeres a edades avan-zadas (próximas a la adultez) oscilan entre 32 a 34%, y en loshombres entre 19 a 20%. Conclusión: Se evidenció que las tres ecuaciones extran-jeras de Boileau, Slaughter y Deuremberg no son aplicables amuestra de escolares chilenos, además, se desarrolló percen-tiles utilizando ecuaciones antropométricas para estimar el%GC desde los 6 hasta los 17,9 años.(AU)

Introduction: Fat percentage is determinant in primarycare evaluation. Objective: To compare regional anthropometric equationsthat predict body fat percentage (%BF) with foreign equa-tions and to propose percentiles to assess %BF in childrenand adolescents in the Maule region, Chile. Methodology: A cross-sectional (correlational) study wascarried out in schoolchildren from the Maule region (Chile). We studied 1,126 schoolchildren (588 males and 538 fe-males) with an age range from 6.0 to 17.9 years. Age, weight,height, abdomen circumference, and two skinfolds (tricipitaland subscapular) were evaluated. Body mass index (BMI),Ponderal Index (PI), Height-Waist Index (WHI), %GC werecalculated by two regional equations and three foreign equa-tions (Boileau, Slaughter and Deuremberg). Results: The Chilean regional equations presented valuesof 26.2±7.1% WC in males, while in females they reflected33.6±4.7% WC (p<0.05). The foreign equations reflectedsimilar values in males, i.e., 19.3%±6.9%GC (Boileau),20.1±8.7%GC (Slaughter) and 20.6±5.3%GC (Deuremberg),whereas, in females it was 25.9±6.1%GC (Boileau), 25.2±8.8%GC (Slaughter) and 25.0±5.3%GC (Deuremberg).There were significant differences between regional equa-tions with foreign equations in both sexes (p<0.05). The cal-culated percentiles were: (P3, P5, P10, P15, P25, P50, P75,P85, P90, P95 and P97). The %GC values in women at ad-vanced ages (close to adulthood) ranged from 32 to 34%,and in men from 19 to 20%. Conclusion: It was shown that the three foreign equationsof Boileau, Slaughter and Deuremberg are not applicable to asample of Chilean schoolchildren. In addition, percentileswere developed using anthropometric equations to estimate%BF from 6 to 17.9 years of age.(AU)

Humans , Male , Female , Child , Adolescent , Forecasting , Abdominal Fat , Dietary Fats , Anthropometry , Data Interpretation, Statistical , Child Nutrition , Adolescent Nutrition , Chile , Cross-Sectional Studies , 52503 , Dietetics
Sci Data ; 9(1): 776, 2022 12 21.
Article in English | MEDLINE | ID: mdl-36543828


Anonymization has the potential to foster the sharing of medical data. State-of-the-art methods use mathematical models to modify data to reduce privacy risks. However, the degree of protection must be balanced against the impact on statistical properties. We studied an extreme case of this trade-off: the statistical validity of an open medical dataset based on the German National Pandemic Cohort Network (NAPKON), which was prepared for publication using a strong anonymization procedure. Descriptive statistics and results of regression analyses were compared before and after anonymization of multiple variants of the original dataset. Despite significant differences in value distributions, the statistical bias was found to be small in all cases. In the regression analyses, the median absolute deviations of the estimated adjusted odds ratios for different sample sizes ranged from 0.01 [minimum = 0, maximum = 0.58] to 0.52 [minimum = 0.25, maximum = 0.91]. Disproportionate impact on the statistical properties of data is a common argument against the use of anonymization. Our analysis demonstrates that anonymization can actually preserve validity of statistical results in relatively low-dimensional data.

COVID-19 , Humans , Bias , Data Anonymization , Models, Theoretical , Privacy , Data Interpretation, Statistical , Datasets as Topic
PeerJ ; 10: e14551, 2022.
Article in English | MEDLINE | ID: mdl-36530395


Water shortage could play an imperative role in the future due to an influx of water demand when compared to water supplies. Inadequate water could damage human life and other aspects related to living. This serious issue can be prevented by estimating the demand for water to bridge the small gap between demand and supplies for water. Some water consumption data recorded daily may be missing and could affect the estimated value of water demand. In this article, new ratio estimators for estimating population total are proposed under unequal probability sampling without replacement when data are missing. Two situations are considered: known or unknown mean of an auxiliary variable and missing data are missing at random for both study and auxiliary variables. The variance and associated estimators of the proposed estimators are investigated under a reverse framework. The proposed estimators are applied to data from simulation studies and empirical data on water demand in Thailand which contain some missing values, to assess the efficacies of the estimators.

Replantation , Humans , Thailand , Probability , Computer Simulation , Data Interpretation, Statistical
BMC Med Res Methodol ; 22(1): 297, 2022 11 19.
Article in English | MEDLINE | ID: mdl-36402979


BACKGROUND: The occurrence and timing of mycobacterial culture conversion is used as a proxy for tuberculosis treatment response. When researchers serially sample sputum during tuberculosis studies, contamination or missed visits leads to missing data points. Traditionally, this is managed by ignoring missing data or simple carry-forward techniques. Statistically advanced multiple imputation methods potentially decrease bias and retain sample size and statistical power. METHODS: We analyzed data from 261 participants who provided weekly sputa for the first 12 weeks of tuberculosis treatment. We compared methods for handling missing data points in a longitudinal study with a time-to-event outcome. Our primary outcome was time to culture conversion, defined as two consecutive weeks with no Mycobacterium tuberculosis growth. Methods used to address missing data included: 1) available case analysis, 2) last observation carried forward, and 3) multiple imputation by fully conditional specification. For each method, we calculated the proportion culture converted and used survival analysis to estimate Kaplan-Meier curves, hazard ratios, and restricted mean survival times. We compared methods based on point estimates, confidence intervals, and conclusions to specific research questions. RESULTS: The three missing data methods lead to differences in the number of participants achieving conversion; 78 (32.8%) participants converted with available case analysis, 154 (64.7%) converted with last observation carried forward, and 184 (77.1%) converted with multiple imputation. Multiple imputation resulted in smaller point estimates than simple approaches with narrower confidence intervals. The adjusted hazard ratio for smear negative participants was 3.4 (95% CI 2.3, 5.1) using multiple imputation compared to 5.2 (95% CI 3.1, 8.7) using last observation carried forward and 5.0 (95% CI 2.4, 10.6) using available case analysis. CONCLUSION: We showed that accounting for missing sputum data through multiple imputation, a statistically valid approach under certain conditions, can lead to different conclusions than naïve methods. Careful consideration for how to handle missing data must be taken and be pre-specified prior to analysis. We used data from a TB study to demonstrate these concepts, however, the methods we described are broadly applicable to longitudinal missing data. We provide valuable statistical guidance and code for researchers to appropriately handle missing data in longitudinal studies.

Research Design , Sputum , Humans , Longitudinal Studies , Data Interpretation, Statistical , Bias
J Neurosci ; 42(45): 8432-8438, 2022 11 09.
Article in English | MEDLINE | ID: mdl-36351823


Experimental neuroscience typically uses "p-valued" statistical testing procedures (null hypothesis significance testing; NHST) in evaluating its results. The rote, often misguided, application of NHST (Gigerenzer, 2008) has led to errors and "questionable research practices." Although the problems could be avoided with better statistics training (Lakens, 2021), there have been calls to abandon NHST altogether. One suggestion is to replace NHST with "estimation statistics" (Cumming and Calin-Jageman, 2017; Calin-Jageman and Cumming, 2019). Estimation statistics emphasizes the uncertainty inherent in scientific investigations and uses metrics, e.g., confidence intervals (CIs), that draw attention to uncertainty. Besides procedural steps and methods, the Estimation Approach prefers expressing "quantitative," rather than "qualitative" conclusions and making generalizations, rather than testing scientific hypotheses. The Estimation Approach embodies a philosophy of science-its ultimate goals, experimental mindset, and specific aims-that diverges unhelpfully from what laboratory-based neuroscience needs. The Estimation Approach meshes naturally with, e.g., clinical neuroscience, drug development, human psychology, and social sciences. It fits less well with much of the neuroscience published in the Journal of Neuroscience, for example. In contrast, the philosophy behind NHST fits naturally with traditional, evaluative testing of scientific hypotheses. Finally, some Estimation Approach remedies, e.g., replication, ideally with "preregistration," are incompatible with much experimental neuroscience. This Dual Perspective essay argues that, while neuroscience can benefit from practical aspects of estimation statistics, entirely replacing conventional methods with the Estimation Approach would be a mistake. NHST testing should be retained and improved.SIGNIFICANCE STATEMENT Experimental neuroscience relies on statistical procedures to assess the meaning and importance of its research findings. Optimal scientific communication demands a common set of assumptions for expressing and evaluating results. Problems arising from misuse of conventional significance testing methods have led to a proposal to replace significance testing with an Estimation Statistics Approach. Practical elements of the Estimation Approach can usefully be incorporated into conventional methods. However, the prevailing philosophy of the Estimation Approach does not address certain important needs of much experimental neuroscience. Neuroscience should adopt beneficial elements of the Estimation Approach without giving up the advantages of significance testing.

Neurosciences , Research Design , Humans , Data Interpretation, Statistical