Analysis Of Repeated Measures Data Research Articles

Association between total body muscle percentage and prevalence of non-alcoholic fatty liver disease in Korean adults findings from an 18-year follow-up: a prospective cohort study.

This study aimed to elucidate the association between total lean muscle mass and the incidence of non-alcoholic fatty liver disease (NAFLD) in the adult Korean population. Utilizing data derived from the 18-year prospective cohort of the Korean Genome and Epidemiology Study, NAFLD was diagnosed via the hepatic steatosis index with an established cutoff value of 36. Lean muscle mass was assessed via bioelectrical impedance analysis and subsequently divided into tertiles. A generalized mixed model with a logit link was employed for repeated measures data analysis, accounting for potential confounders. Analysis encompassed 7,794 participants yielding 49,177 measurements. The findings revealed a markedly increased incidence of NAFLD in the lower tertiles of muscle mass, specifically, tertile 1 (odds ratio [OR], 20.65; 95% confidence interval [CI], 9.66-44.11) and tertile 2 (OR, 4.57; 95% CI, 2.11-9.91), in comparison to tertile 3. Age-dependent decreases in the OR were observed within the tertile 1 group, with ORs of 10.12 at age of 40 years and 4.96 at age of 80 years. Moreover, each 1%-point increment in total muscle mass corresponded with an estimated OR of 0.87 (95% CI, 0.82-0.93) for NAFLD resolution. The study demonstrates a significant association between total muscle mass and NAFLD prevalence among Korean adults. Given the potential endocrine role of muscle mass in NAFLD pathogenesis, interventions aimed at enhancing muscle mass might serve as an effective public health strategy for mitigating NAFLD prevalence.

Area under the Curve as an Alternative to Latent Growth Curve Modeling When Assessing the Effects of Predictor Variables on Repeated Measures of a Continuous Dependent Variable

Researchers conducting longitudinal data analysis in psychology and the behavioral sciences have several statistical methods to choose from, most of which either require specialized software to conduct or advanced knowledge of statistical methods to inform the selection of the correct model options (e.g., correlation structure). One simple alternative to conventional longitudinal data analysis methods is to calculate the area under the curve (AUC) from repeated measures and then use this new variable in one’s model. The present study assessed the relative efficacy of two AUC measures: the AUC with respect to the ground (AUC-g) and the AUC with respect to the increase (AUC-i) in comparison to latent growth curve modeling (LGCM), a popular repeated measures data analysis method. Using data from the ongoing Panel Study of Income Dynamics (PSID), we assessed the effects of four predictor variables on repeated measures of social anxiety, using both the AUC and LGCM. We used the full information maximum likelihood (FIML) method to account for missing data in LGCM and multiple imputation to account for missing data in the calculation of both AUC measures. Extracting parameter estimates from these models, we next conducted Monte Carlo simulations to assess the parameter bias and power (two estimates of performance) of both methods in the same models, with sample sizes ranging from 741 to 50. The results using both AUC measures in the initial models paralleled those of LGCM, particularly with respect to the LGCM baseline. With respect to the simulations, both AUC measures preformed as well or even better than LGCM in all sample sizes assessed. These results suggest that the AUC may be a viable alternative to LGCM, especially for researchers with less access to the specialized software necessary to conduct LGCM.

Use of Repeated Measures Data Analysis for Field Trials with Annual and Perennial Crops.

Field studies conducted over time to collect any type of plant response to a set of treatments are often not treated as repeated measures data. The most used approaches for statistical analyses of this type of longitudinal data are based on separate analyses such as ANOVA, regression, or time contrasts. In many instances, during the review of manuscripts, reviewers have asked researchers to treat year, for example, as a random effect and ignore the interactions between year and other main effects. One drawback of this approach is that the correlation between measurements taken on the same subject over time is ignored. Here, we show that avoiding the covariance between measurements can induce erroneous (e.g., no differences reported when they exist, or differences reported when they actually do not exist) inference of treatment effects. Another issue that has received little attention for statistical inference of multi-year field experiments is the combination of fixed, random, and repeated measurement effects in the same statistical model. This type of analysis requires a more in-depth understanding of modeling error terms and how the statistical software used translates the statistical language of the given command into mathematical computations. Ignoring possible significant interactions among repeated, fixed, and random effects might lead to an erroneous interpretation of the data set. In this manuscript, we use data from two field experiments that were repeated during two and three consecutive years on the same plots to illustrate different modeling strategies and graphical tools with an emphasis on the use of mixed modeling techniques with repeated measures.

Different preoperative fluids do not affect the hemodynamic status but gastric volume: results of a randomized crossover pilot study

Background and objectiveInferior vena cava (IVC) examination has been reported as a noninvasive method for evaluating the hemodynamic state. We conducted this crossover pilot study to investigate the effects of the administration of water and high-carbohydrate-containing fluids on the hemodynamic status of volunteers through collapsibility index of IVC (IVCCI) measurement.MethodsTwenty volunteers were randomly assigned to a water or high-carbohydrate group according to computer-generated random numbers in a 1:1 ratio. In the water group, volunteers received water (5 mL/kg), and in the high-carbohydrate group, patients received carbohydrate drinks (5 mL/kg). Respiratory variations in the IVC diameter, gastric volume, and blood pressure and heart rates in erect and supine positions were measured at admission (T1), 1 h (T2), 2 h (T3), 3 h (T4), and 4 h (T5).ResultsWhen considering participants with an IVCCI of more than 42%, there were no significant differences between the water and carbohydrate drink groups at each time point (all p > 0.05). At T2, more participants had an empty stomach in water group than in carbohydrate drink group (p < 0.001). At T3, 30% of the participants could not empty their stomachs in carbohydrate drink group. However, with regard to the number of volunteers with empty stomach at T3, there was no significant difference between water and carbohydrate drink group. Repeated measures data analysis demonstrated that IVCCI showed no significant differences over time (p = 0.063 for T1-T5). There were no differences between water and carbohydrate drinks (p = 0.867).ConclusionOur results suggested that neither water nor carbohydrate drinking affected the hemodynamic status through IVCCI measurement over time, up to 4 h after drinking. Furthermore, carbohydrate drinking might delay gastric emptying at 1 h, but not 2 h after drinking, in comparison with water.

Differences in Rates of Low Birth Weight among Prefectures in Japan: An Ecological Study Using Government Statistics Data.

The differences in the rates and trends of the overall low birth weight and term low birth weight in recent years are unknown for the Japanese prefectures. In this ecological study, we revealed the rates for each prefecture and investigated the factors affecting the regional differences in these outcomes. Aggregated vital statistics data from 2007 to 2019 were obtained from the Ministry of Health, Labour, and Welfare in Japan. The association between the outcomes and the variables, including the infants’ birth characteristics, medical characteristics, and socioeconomic characteristics of the prefectures, were analyzed. An analysis of repeated-measures data was conducted using the data from 2013 and 2018 for each prefecture. The trend for the rates of overall low birth weight and term low birth weight over the years differed among the prefectures. Moreover, the proportions of multiple births and lean (body mass index <18.5 kg/m2) and obese (body mass index ≥25.0 kg/m2) women had a statistically significant positive association with both the overall low birth weight rate and the term low birth weight rate among the prefectures. It was suggested that to resolve the difference in these outcomes among the prefectures, being obese or underweight needs to be addressed in mothers.

A primer on distributional assumptions and model linearity in repeated measures data analysis

A primer on distributional assumptions and model linearity in repeated measures data analysis

Effect of Preconception Care Education by Health Volunteers on Knowledge and Attitudes of Women: Application of the Health Belief Model

Preconception care identifies and modifies the risk factors for pregnancy and childbirth. The present study aimed to determine the effects a preconception care education program, which was based on the Health Belief Model (HBM) and implemented by health volunteers, on knowledge and attitudes of women. A semi-experimental study was conducted using 22 health volunteers and 110 women aged 15-49 years selected from two comprehensive health centers of Mashhad, Iran, in 2016. The convenience sampling method was employed for selecting the volunteers and the regular random sampling method for choosing the women. For data collection, we applied a researcher-made tool with verified validity and reliability. HBM-based education was implemented by the volunteers during three sessions. Data analysis was performed in SPSS using Mann-Whitney test, Friedman, and Spearman's rank correlation coefficient; repeated measures data analysis was carried out at the significance level of 0.05. The mean age of the women was 30.6±6.6 years in the intervention group and 31.6±6.5 years in the control group. The mean levels of knowledge and attitude increased significantly after the intervention (P<0.001). We suggest using the current educational intervention based on the HBM to promote women's knowledge and attitudes towards preconception care.

Integrated soil fertility management reduces termite damage to crops on degraded soils in western Ethiopia

Crop damage by termite is known to be severe in degraded soils. However, the role of organic inputs in reducing crop damage by termite has not been systematically studied in Ethiopia. Therefore, the objectives of this study were to quantify (i) the influence of integrated use of manure and NP fertilizer on termite damage and pod yields of hot pepper (Capsicum frutescence L.), (ii) the optimum rate of manure and NP fertilizer for hot pepper production for the study area, and (iii) the association between different rates of nitrogen (N) fertilizer and plant damage by termite. Two separate experiments were conducted for three consecutive seasons on degraded soils that were hotspots of termite activity. The treatments in experiment 1 consisted of different rates of well-composted manure applied in combination with NP fertilizer, whereas experiment 2 consisted of different rates of N fertilizer with basal application of 44kg Pha−1. In experiment 1, the combined application of manure and NP fertilizer significantly (P<0.05) reduced plant damage but increased pod yields compared with the control treatment and the recommended NP fertilizer. Plant damage by termites decreased from 29% in the first season to 11% in the third season, while pod yield increased from 378kgha−1 in the first season to 2339kgha−1 in the third season. The results of the repeated measures data analysis also indicated significant (P<0.0001) differences among the seasons in plant damage by termite and pod yield. In experiment 2, continuous application of the different rates of N fertilizer did not significantly reduced plant damage by termite while the N effect lacked consistency on pod yield. However, the application of N at rates ≥75 and >100kgha−1 increased termite damages to hot pepper in the first and second seasons, respectively. Overall, the application of one-fourth of the recommended NP fertilizer (25/11kgN/Pha−1) along with 10t manure ha−1 was found to be optimum for hot pepper production for the study area and similar agroecosystem. Therefore, we recommend adoption of the integrated use of manure and NP fertilizer to prevent soil degradation and reduce termite damage in western Ethiopia.

Medical Care Utilization During 1 Year Prior to Death in Suicides Motivated by Physical Illnesses

ObjectivesMany epidemiological studies have suggested that a variety of medical illnesses are associated with suicide. Investigating the time-varying pattern of medical care utilization prior to death in suicides motivated by physical illnesses would be helpful for developing suicide prevention programs for patients with physical illnesses.MethodsSuicides motivated by physical illnesses were identified by the investigator's note from the National Police Agency, which was linked to the data from the Health Insurance Review and Assessment. We investigated the time-varying patterns of medical care utilization during 1 year prior to suicide using repeated-measures data analysis after adjustment for age, gender, area of residence, and socioeconomic status.ResultsAmong 1994 suicides for physical illness, 1893 (94.9%) suicides contacted any medical care services and 445 (22.3%) suicides contacted mental health care during 1 year prior to suicide. The number of medical care visits and individual medical expenditures increased as the date of suicide approached (p<0.001). The number of medical care visits for psychiatric disorders prior to suicide significantly increased only in 40- to 64-year-old men (p=0.002), women <40 years old (p=0.011) and women 40 to 64 years old (p=0.021) after adjustment for residence, socioeconomic status, and morbidity.ConclusionsMost of the suicides motivated by physical illnesses contacted medical care during 1 year prior to suicide, but many of them did not undergo psychiatric evaluation. This underscores the need for programs to provide psychosocial support to patients with physical illnesses.

Repeated measures semiparametric regression using targeted maximum likelihood methodology with application to transcription factor activity discovery.

In longitudinal and repeated measures data analysis, often the goal is to determine the effect of a treatment or aspect on a particular outcome (e.g., disease progression). We consider a semiparametric repeated measures regression model, where the parametric component models effect of the variable of interest and any modification by other covariates. The expectation of this parametric component over the other covariates is a measure of variable importance. Here, we present a targeted maximum likelihood estimator of the finite dimensional regression parameter, which is easily estimated using standard software for generalized estimating equations. The targeted maximum likelihood method provides double robust and locally efficient estimates of the variable importance parameters and inference based on the influence curve. We demonstrate these properties through simulation under correct and incorrect model specification, and apply our method in practice to estimating the activity of transcription factor (TF) over cell cycle in yeast. We specifically target the importance of SWI4, SWI6, MBP1, MCM1, ACE2, FKH2, NDD1, and SWI5. The semiparametric model allows us to determine the importance of a TF at specific time points by specifying time indicators as potential effect modifiers of the TF. Our results are promising, showing significant importance trends during the expected time periods. This methodology can also be used as a variable importance analysis tool to assess the effect of a large number of variables such as gene expressions or single nucleotide polymorphisms.

Is Self-Confidence a Bias Factor in Higher-Order Catastrophe Models? An Exploratory Analysis—A Critique

The current paper criticizes the concept, research methodology, data analyses, and validity of the conclusions made in Hardy, Woodman, and Carrington’s (2004) article published in this journal. In their repeated-measures analysis of data from the performances of 7 golfers, they did not examine changes in performance scores on successive holes. Instead, Hardy et al. used several ANOVA models to examine how performance varied with respect to somatic and cognitive anxiety level and self-confidence interaction. By doing so, their findings produced effects which we argue to be conceptually and empirically limited. We also address problems associated with dichotomization of continuous variables, measurement errors when splitting data, eradication of random significant effects, cell sizes in segmental quadrant analysis, and correlation between somatic and cognitive anxiety. We believe these difficulties prevent any reliable conclusions and/or generalizations from being made.

Comparison of methods for incomplete repeated measures data analysis in small samples

This paper presents missing data methods for repeated measures data in small samples. Most methods currently available are for large samples. In particular, no studies have compared the performance of multiple imputation methods to that of non-imputation incomplete analysis methods. We first develop a strategy for multiple imputations for repeated measures data under a cell-means model that is applicable for any multivariate data with small samples. Multiple imputation inference procedures are applied to the resulting multiply imputed complete data sets. Comparisons to other available non-imputation incomplete data methods is made via simulation studies to conclude that there is not much gain in using the computer intensive multiple imputation methods for small sample repeated measures data analysis in terms of the power of testing hypotheses of parameters of interest.

Body mass index growth in a sample of U.S. children: repeated measures data analysis of the Minneapolis Children's Blood Pressure Study.

Longitudinal assessments of the body mass index (BMI) in children and adolescents are limited. The purpose of the study was to describe the growth patterns of the BMI in children and young adults. Black and White children of Minneapolis Children's Blood Pressure Study (MCBPS) were 6 to 9 years old at entry and were followed for 12 years at 19 separate visits. Those with at least five visits (n = 1,302) were included for analysis, using non-linear mixed effects models in conjunction with the Gompertz curve. The growth patterns of four sex-ethnic groups were different at three levels: starting level (SL) (kg/m(2)), asymptote level (AL) (kg/m(2)), and peak growth age (PGA) (in years). In this context, SL is the average BMI level at age 6, AL is the average BMI level when growth diminishes, and PGA is the average age at which the rate of growth in the BMI peaks. The SL (16.3 +/- 0.1) for White males was significantly greater than SL in the other three sex-ethnic groups, among which there were no significant differences. There was a significant ethnic difference in AL between Black females (25.5 +/- 0.3) and White females (24.4 +/- 0.2) and a marginally significant difference in AL between Black females and Black males (24.4 +/- 0.3). For PGA, only sex differences were significant: Black females reached the peak at the earliest age at (11.5 +/- 0.1) years, followed by White females (11.7 +/- 0.1), Black males (12.6 +/- 0.1), and White males (12.8 +/- 0.1).

Design and analysis of research on sport performance enhancement.

The purpose of this study was to assess research aimed at measuring performance enhancements that affect success of individual elite athletes in competitive events. Simulations show that the smallest worthwhile enhancement of performance for an athlete in an international event is 0.7-0.4 of the typical within-athlete random variation in performance between events. Using change in performance in events as the outcome measure in a crossover study, researchers could delimit such enhancements with a sample of 16-65 athletes, or with 65-260 in a fully controlled study. Sample size for a study using a valid laboratory or field test is proportional to the square of the within-athlete variation in performance in the test relative to the event; estimates of these variations are therefore crucial and should be determined by repeated-measures analysis of data from reliability studies for the test and event. Enhancements in test and event may differ when factors that affect performance differ between test and event; overall effects of these factors can be determined with a validity study that combines reliability data for test and event. A test should be used only if it is valid, more reliable than the event, allows estimation of performance enhancement in the event, and if the subjects replicate their usual training and dietary practices for the study; otherwise the event itself provides the only dependable estimate of performance enhancement. Publication of enhancement as a percent change with confidence limits along with an analysis for individual differences will make the study more applicable to athletes. Outcomes can be generalized only to athletes with abilities and practices represented in the study. estimates of enhancement of performance in laboratory or field tests in most previous studies may not apply to elite athletes in competitive events.

Methods for repeated measures data analysis with missing values

There are various techniques for dealing with incomplete data; some are computationally highly intensive and others are not as computationally intensive, while all may be comparable in their efficiencies. In spite of these developments, analysis using only the complete data subset is performed when using popular statistical software. In an attempt to demonstrate the efficiencies and advantages of using all available data, we compared several approaches that are relatively simple but efficient alternatives to those using the complete data subset for analyzing repeated measures data with missing values, under the assumption of a multivariate normal distribution of the data. We also assumed that the missing values occur in a monotonic pattern and completely at random. The incomplete data procedure is demonstrated to be more powerful than the procedure of using the complete data subset, generally when the within-subject correlation gets large. One other principal finding is that even with small sample data, for which various covariance models may be indistinguishable, the empirical size and power are shown to be sensitive to misspecified assumptions about the covariance structure. Overall, the testing procedures that do not assume any particular covariance structure are shown to be more robust in keeping the empirical size at the nominal level than those assuming a special structure.

Comparison of Quantitative Whole-Body Autoradiographic and Tissue Dissection Techniques in the Evaluation of the Tissue Distribution of [14C]Daptomycin in Rats 1

Quantitative whole-body autoradiography (QWBA) was evaluated and compared to tissue dissection/liquid scintillation counting (TD/LSC) techniques by determining the tissue distribution of radiocarbon in rats following iv administration of the antibiotic [14C]daptomycin (LY146032). QWBA, using computer-assisted video-image analysis, was initially evaluated by characterizing and calibrating commercial standards to blood and brain, kidney, liver, and lung homogenates. Frozen (carboxymethyl)cellulose blocks containing tissue homogenates spiked with [14C]glucose (370–37 000 Bq/g or 10–1000 nCi/g) were sectioned and optical densities (OD) measured. Characterization of QWBA included repeated measures data analysis to determine the significance of tissue type and intra- and inter-section and block variability. Regression models relating OD to radiocarbon concentration were also used to calibrate commercial standards for use in QWBA analyses. Results indicated that there were no substantial differences between OD readings from different tissues; however, the greatest source of variation in OD reading was section thickness. Because quantitative variations were largely attributed to section thickness, an internal standard (IS), consisting of liver homogenates spiked with [14C]glucose, was evaluated as a correction factor. Tissue concentrations of radiocarbon in male Fischer 344 rats were evaluated by QWBA and TD/LSC techniques 0.25 h following a single iv 10 mg/kg dose of [14C]daptomycin. Results indicated that tissue concentrations of radiocarbon obtained by QWBA, normalized using an IS, were comparable to those obtained by TD/LSC.

Incomplete Repeated Measures Data Analysis in the Presence of Treatment Effects

Abstract This article illustrates an analysis strategy for repeated measures data where some of the measurements are missing from the subjects on one or more occasions, with a special application to data arising from repeated measurement designs when some observations are missing after the first treatment period. Using all available data, “almost” maximum likelihood estimators for the parameters of interest are obtained under the assumption of a multivariate normal distribution of the data. Inference procedures for these parameters in small samples from popular two-treatment designs are discussed.

Incomplete Repeated Measures Data Analysis in the Presence of Treatment Effects

Incomplete Repeated Measures Data Analysis in the Presence of Treatment Effects

ANALYSIS OF REPEATED MEASURES DATA

Data with repeated measures occur frequently in agricultural research. This paper is a brief overview of statistical methods for repeated measures data. Statistical analysis of repeated measures data requires special attention due to the correlation structure, which may render standard analysis of variance techniques invalid. For balanced data, multivariate analysis of variance methods can be employed and adjustments can be applied to univariate methods, as means of accounting for the correlation structure. But these analysis of variance methods do not apply readily with unbalanced data, and they overlook the regression on time. Regression curves for treatment groups can be obtained by fitting a curve to each experimental unit; and then averaging the coefficients over the units. Treatment groups can be compared by applying univariate and multivariate methods to the group means of the coefficients. This approach does not require knowledge of the correlation structure of the repeated measures, and an approximate version of it can be applied with unbalanced data.

ANALYSIS OF REPEATED-MEASURES DATA WITH OUTLIERS

ANALYSIS OF REPEATED-MEASURES DATA WITH OUTLIERS