Statistical Unit Of Analysis Research Articles

Multidisciplinary treatment protocol for ischiatic, sacral, trochanteric or other pressure injuries in people with spinal cord injury: a retrospective cohort study.

Retrospective cohort study Objectives: to describe the incidence and the associated risk factors of post-surgical complications and recurrence in individuals with spinal cord injury/disorder (SCI/D) presenting deep pressure injuries (PIs), treated with a specific surgical and rehabilitation treatment protocol. Tertiary Rehabilitation Hospital for SCI/D in Italy. Retrospective analysis of the medical records of adult individuals with SCI/D, who developed a PI after the first discharge from a Spinal Unit, underwent flap surgery for PI between July 2011 and January 2018. The statistical unit of analysis was the surgical intervention. Logistic regression analysis with robust standard errors was performed to assess risk factors of post-surgical complications. 434 surgical intervention records were included, for a total of 378 patients. The treated PIs were ischiatic in 56.2% of the cases, sacral in 32.5%, trochanteric in 15.7%, and 5.8% were in other sites. In 239 cases (55.1%) a histological diagnosis of osteomyelitis was confirmed. Minor complications occurred in 13.6% of interventions, while major complications were 3.9%. Sacral PI (OR = 2.55, 95%CI: 1.50-4.35) and muscular/musculocutaneous flap (OR = 2.12, 95%CI: 1.05-4.28) were significant factors associated with risk of post-surgical complications. After a mean follow-up of 21 months (range 12-36), six people (1.4%) had a recurrence. Patients with a recurrence had at least one comorbidity compared to 57% of people without recurrences (p = 0.036). Our results demonstrate that complication and recurrence rates can be minimized when an established interdisciplinary and rehabilitation protocol is integrated in the clinical management.

How Communities Benefit from Collaborative Governance: Experimental Evidence in Ugandan Oil and Gas

Abstract This paper reports the results of a field experiment to assess the collaborative effects of community participation in the Ugandan oil and gas sector. Our research design assesses collaborative impacts as relational between community members and different decision-makers in the sector and measures these impacts from the point of view of local people. Local people often face power imbalances in collaborative governance. Decision-makers are increasingly attempting to mitigate such imbalances to improve outcomes for communities, but little experimental evidence exists showing the impact of such efforts. Using multilevel ordered logit models, we estimate positive treatment effects, finding that encouraging the equitable participation of communities improves collaboration with other actors. Next, we use machine-learning techniques to demonstrate a method for targeting communities most likely to benefit from the intervention. We estimate that purposefully targeting communities that would benefit most yields a treatment effect about twice as large, relative to pure random assignment. Our results provide evidence that interventions mindful of community needs can improve collaborative governance and shows how such communities can be most effectively targeted. The experiment took place across 107 villages (53 treatment and 54 control) and the unit of statistical analysis is the household, where we report outcomes measured from 6,062 household surveys (approximately half at baseline and half at endline).

Export Behaviour and Propensity to Innovation in a Developing Country: The Case of Afghanistan

The paper is aimed at examining relation between factors determining export behavior and propensity to innovate to fill Afghanistan specific literature gap. For this purpose, a number of 236 small and medium manufacturing firms were targeted as statistical unit of analysis. Required data were collected through questionnaire distributed to owner/manager of firms. Descriptive statistics as well as multivariate probit regression were utilized to analyze the data. Findings confirmed no significant relationship between export behavior and propensity to innovate. It further suggests that marketing innovation and technological advancement positively and significantly influence export behavior and propensity to innovate. Furthermore, and unlike result of many other similar studies there was insignificant influence of firm size and firm age on propensity to innovation.

Interventions for treating oral lichen planus: corticosteroid therapies.

Oral lichen planus (OLP) is a relatively common chronic T cell-mediated disease, which can cause significant pain, particularly in its erosive or ulcerative forms. As pain is the indication for treatment of OLP, pain resolution is the primary outcome for this review. This review is an update of a version last published in 2011, but focuses on the evidence for corticosteroid treatment only. A second review considering non-corticosteroid treatments is in progress. To assess the effects and safety of corticosteroids, in any formulation, for treating people with symptoms of oral lichen planus. Cochrane Oral Health's Information Specialist searched the following databases to 25 February 2019: Cochrane Oral Health's Trials Register, CENTRAL (2019, Issue 1), MEDLINE Ovid, and Embase Ovid. ClinicalTrials.gov and the World Health Organization International Clinical Trials Registry Platform were searched for ongoing trials. There were no restrictions on language or date of publication. We considered randomised controlled clinical trials (RCTs) of any local or systemic corticosteroid treatment compared with a placebo, a calcineurin inhibitor, another corticosteroid, any other local or systemic (or both) drug, or the same corticosteroid plus an adjunctive treatment. Three review authors independently scanned the titles and abstracts of all reports identified, and assessed risk of bias using the Cochrane tool and extracted data from included studies. For dichotomous outcomes, we expressed the estimates of effects of an intervention as risk ratios (RR), with 95% confidence intervals (CI). For continuous outcomes, we used mean differences (MD) and 95% CI. The statistical unit of analysis was the participant. We conducted meta-analyses only with studies of similar comparisons reporting the same outcome measures. We assessed the overall certainty of the evidence using GRADE. We included 35 studies (1474 participants) in this review. We assessed seven studies at low risk of bias overall, 11 at unclear and the remaining 17 studies at high risk of bias. We present results for our main outcomes, pain and clinical resolution measured at the end of the treatment course (between one week and six months), and adverse effects. The limited evidence available for comparisons between different corticosteroids, and corticosteroids versus alternative or adjunctive treatments is presented in the full review. Corticosteroids versus placebo Three studies evaluated the effectiveness and safety of topical corticosteroids in an adhesive base compared to placebo. We were able to combine two studies in meta-analyses, one evaluating clobetasol propionate and the other flucinonide. We found low-certainty evidence that pain may be more likely to be resolved when using a topical corticosteroid rather than a placebo (RR 1.91, 95% CI 1.08 to 3.36; 2 studies, 72 participants; I² = 0%). The results for clinical effect of treatment and adverse effects were inconclusive (clinical resolution: RR 6.00, 95% CI 0.76 to 47.58; 2 studies, 72 participants; I² = 0%; very low-certainty evidence; adverse effects RR 1.48, 95% 0.48 to 4.56; 3 studies, 88 participants, I² = 0%, very low-certainty evidence). Corticosteroids versus calcineurin inhibitors Three studies compared topical clobetasol propionate versus topical tacrolimus. We found very low-certainty evidence regarding any difference between tacrolimus and clobetasol for the outcomes pain resolution (RR 0.45, 95% CI 0.24 to 0.88; 2 studies, 100 participants; I² = 80%), clinical resolution (RR 0.61, 95% CI 0.38 to 0.99; 2 studies, 52 participants; I² = 95%) and adverse effects (RR 0.05, 95% CI 0.00 to 0.83; 2 studies, 100 participants; very low-certainty evidence) . One study (39 participants) compared topical clobetasol and ciclosporin, and provided only very low-certainty evidence regarding the rate of clinical resolution with clobetasol (RR 3.16, 95% CI 1.00 to 9.93), pain resolution (RR 2.11, 95% CI 0.76 to 5.86) and adverse effects (RR 6.32, 95% CI 0.84 to 47.69). Two studies (60 participants) that compared triamcinolone and tacrolimus found uncertain evidence regarding the rate of clinical resolution (RR 0.86, 95% CI 0.55 to 1.35; very low-certainty evidence) and that there may be a lower rate of adverse effects in the triamcinolone group (RR 0.47, 95% CI 0.22 to 0.99; low-certainty evidence). These studies did not report on pain resolution. Corticosteroids have been first line for the treatment of OLP. This review found that these drugs, delivered topically as adhesive gels or similar preparations, may be more effective than placebo for reducing the pain of symptomatic OLP; however, with the small number of studies and participants, our confidence in the reliability of this finding is low. The results for clinical response were inconclusive, and we are uncertain about adverse effects. Very low-certainty evidence suggests that calcineurin inhibitors, specifically tacrolimus, may be more effective at resolving pain than corticosteroids, although there is some uncertainty about adverse effects and clinical response to tacrolimus showed conflicting results.

The higher, the cooler? Effects of building height on land surface temperatures in residential areas of Beijing

Numerous studies have showed that landscape composition and configuration can significantly affect land surface temperature (LST). Most of these studies focus on the horizontal dimension of landscape structure. Few studies, however, have explored the effects of vertical dimension of urban landscape. This study aims to fill this gap. We focused on the residential landscapes in the central area of Beijing, and quantified the relationships between the vertical structure of buildings and LST. We delineated the boundaries of residential neighborhoods based on high resolution imagery, which were latterly used as the unit of statistical analysis. Building height, and proportional cover of buildings and vegetation were also mapped from high resolution imagery, with aid of digital maps. LST was retrieved from thermal band of TM imagery. We used Pearson correlation, partial correlation and ordinary least squares(OLS) regressions to quantify the relationships between these variables and LST. We found: 1) Land surface temperature varied greatly among residential neighborhoods, ranging from 53.5 °C to 37.0 °C, with a mean of 44.2 °C and a standard deviation of 2.4 °C. High-rise residential neighborhoods had the lowest LST, and mean LST decreased from low-rise to high-rise residential neighborhoods. 2) Building height, building density and vegetation coverage were all significantly correlated with LST. Building height and vegetation coverage has significantly negative effects on LST, but building density had a significantly positive one. 3) Among these variables, building height had greater impact on LST than the other two variables. These results have important implications for urban design and management.

Concomitant Methotrexate Protects Against Total Knee Arthroplasty in Patients with Rheumatoid Arthritis Treated with Tumor Necrosis Factor Inhibitors.

To determine the effects of concomitant methotrexate (MTX) on the incidence of total knee arthroplasty (TKA) resulting from the progression of joint destruction in patients with rheumatoid arthritis (RA) during longterm treatment with tumor necrosis factor (TNF) inhibitors. A total of 155 patients with RA (310 knee joints) received TNF inhibitors at our institute between May 1, 2001, and May 31, 2008. A total of 111 symptomatic (tender and/or swollen) knee joints in 68 patients were retrospectively studied over the course of a minimum of 5 years of followup. The median (interquartile range) followup period was 8.1 (7.0-9.3) years. All data were analyzed using the knee joint as the statistical unit of analysis. TKA during treatment with TNF inhibitors was used as the outcome variable in predictive analyses. The cumulative incidence of TKA was compared by concomitant or no MTX use (MTX±). There were 79 subjects (71%) who received concomitant MTX. According to Kaplan-Meier estimates, the cumulative incidence of TKA for the MTX+ group was significantly lower than that for the MTX- group (24% vs 45% at 5 yrs, respectively, p = 0.035). Multivariate analysis using the Cox proportional hazards model revealed that concomitant MTX (HR 0.44, 95% CI 0.22-0.89), Larsen grade (HR 2.93, 95% CI 1.94-4.41), and older age at baseline (HR 1.04, 95% CI 1.01-1.08) were independent predictors of TKA. Concomitant MTX reduces the incidence of TKA by 56% in patients with RA during longterm treatment with TNF inhibitors.

The pairwise approach to analysing species co‐occurrence

AbstractThe analysis of species co‐occurrence patterns continues to be a main pursuit of ecologists, primarily because the coexistence of species is fundamentally important in evaluating various theories, principles and concepts. Examples include community assembly, equilibrium versus non‐equilibrium organization of communities, resource partitioning and ecological character displacement, the local–regional species diversity relationship, and the metacommunity concept. Traditionally, co‐occurrence has been measured and tested at the level of an entire species presence–absence matrix wherein various algorithms are used to randomize matrices and produce statistical null distributions of metrics that quantify structure in the matrix. This approach implicitly recognizes a presence–absence matrix as having some real ecological identity (e.g. a set of species exhibiting nestedness among a set of islands) in addition to being a unit of statistical analysis. An emerging alternative is to test for non‐random co‐occurrence between paired species. The pairwise approach does not analyse matrix‐level structure and thus views a species pair as the fundamental unit of co‐occurrence. Inferring process from pattern is very difficult in analyses of co‐occurrence; however, the pairwise approach may make this task easier by simplifying the analysis and resulting inferences to associations between paired species.

Implications of nested designs in school-based mental health services research

Evaluating school-based mental health services for children and youth with emotional disturbance (ED) has been a challenge for researchers. One particular challenge is the study design of using the student as the statistical unit of analysis, which in certain cases may lead to a violation of the “independence of error” assumption. However, the alternative to this nested design, including fewer students and more schools, can be costly and administratively complex. This study examines data from two national studies including 314 students with ED and served in special education programs and their caregivers from 24 schools in the US to identify the extent to which nesting or design effects occur in this population. The results show that variables focusing on psychopathology are less affected by nesting but school-related variables such as academic functioning are more affected. Design effects varied by grade level, suggesting that grade should be considered when designing such evaluations.

Analysis of Differences in Proportions from Clustered Data with Multiple Measurements in Diagnostic Studies

In diagnostic studies, proportions such as sensitivities are often to be calculated and to be compared between different diagnostic procedures. As statistical unit of analysis, multiple observational units may be assessed within each patient, i.e., multiple lesions in an organ. As a requirement, these are to be assessed by multiple blinded readers. In this paper we propose a method to cover correlations between units within patients, correlations between procedures and correlations between different raters assessing each observational unit. The proposed approach is a two-step method to analyze clustered data with multiple measurements to compare diagnostic procedures in a paired modality design and the correlation between the readers in a paired reader design. The performance of the approach was compared to a generalized estimation equations model (GEEs) by power simulations. Power simulations suggest, that the two-step approach is not inferior to GEEs with regard to the single readers as well as with regard to the average reader. An intuitive approach was developed next to established methods to analyze "paired modality, paired reader" and "unpaired modality, paired reader" studies with binary endpoints when estimating proportions and differences in proportions for clustered data with multiple measurements. This two-step approach is an alternative method to cover routine designs of diagnostic studies where the difference of proportions is to be estimated directly along with confidence intervals.

Cesarean delivery for twins: A systematic review and meta-analysis

Objective: We undertook a systematic review and meta-analysis to determine whether a policy of planned cesarean section or vaginal delivery is better for twins. Study Design: We searched MEDLINE and EMBASE from 1980 through May 2001 using combinations of the following terms: twin, delivery, cesarean section, vaginal birth, birth weight, and gestational age. Studies that compared planned cesarean section to planned vaginal birth for babies weighing at least 1500 g or reaching at least 32 weeks' gestation were included. We computed pooled odds ratios for perinatal or neonatal mortality, low 5-minute Apgar score, neonatal morbidity, and maternal morbidity. The infant was the unit of statistical analysis. Results were considered statistically significant if the 95% CI did not encompass 1.0. Results: We retrieved 67 articles, 63 of which were excluded. Four studies with a total of 1932 infants were included in the analysis. A low 5-minute Apgar score occurred less frequently in twins delivered by planned cesarean section (odds ratio, 0.47; 95% CI, 0.26-0.88) principally because of a reduction among twins if twin A was in breech position (odds ratio, 0.33; 95% CI, 0.17-0.65). Twins delivered by planned cesarean section spent significantly longer in the hospital (mean difference, 4.01 days; 95% CI, 0.73-7.28 days). There were no significant differences in perinatal or neonatal mortality, neonatal morbidity, or maternal morbidity. Conclusion: Planned cesarean section may decrease the risk of a low 5-minute Apgar score, particularly if twin A is breech. Otherwise, there is no evidence to support planned cesarean section for twins. (Am J Obstet Gynecol 2003;188:220-7.)

Using pooled exposure assessment to improve efficiency in case-control studies.

Assays can be so expensive that interesting hypotheses become impractical to study epidemiologically. One need not, however, perform an assay for everyone providing a biological specimen. We propose pooling equal-volume aliquots from randomly grouped sets of cases and randomly grouped sets of controls, and then assaying the smaller number of pooled samples. If an effect modifier is of concern, the pooling can be done within strata defined by that variable. For covariates assessed on individuals (e.g., questionnaire data), set-based counterparts are calculated by adding the values for the individuals in each set. The pooling set then becomes the unit of statistical analysis. We show that, with appropriate specification of a set-based logistic model, standard software yields a valid estimated exposure odds ratio, provided the multiplicative formulation is correct. Pooling minimizes the depletion of irreplaceable biological specimens and can enable additional exposures to be studied economically. Statistical power suffers very little compared with the usual, individual-based analysis. In settings where high assay costs constrain the number of people an investigator can afford to study, specimen pooling can make it possible to study more people and hence improve the study's statistical power with no increase in cost.

Statistical Comparison of Movement Amplitudes from Groupings of Normal Geriatric Speakers

An implicit assumption of many studies of articulatory kinematics is that all normal speakers are equivalent, at least in a statistical sense. The present report investigated this assumption by performing post hoc analyses on random groups of 8 normal, geriatric males. Results of these analyses suggest that, at least for the geriatric population, small numbers of subjects may not represent the parent population adequately, especially when the unit of statistical analysis is the individual trial. These findings have implications for the types of generalizations that can be made from studies with small samples and suggest the need for more comprehensive investigations of speech kinematics.

Public Perceptions of the Risks and Benefits of Technology1

This study attempted to verify and extend previous research on people's perceptions of the risks and benefits of technology and their judgments concerning the acceptability of technology safety regulations. The study addressed several limitations of prior work, in that: (1) it was the first “expressed‐preference” study to collect data from large, representative samples of Americans; (2) the research design made “person,” rather than “technology,” the unit of statistical analysis; and (3) the study employed an expanded set of independent variables, including three qualitative benefit characteristics. The results confirmed several major conclusions of prior expressed‐preference research, the most important being that members of the public tend to define “risks,”“benefits,” and “acceptability” in a complex, multidimensional manner; and that their definitions differ significantly from those used by professional risk‐managers and other technical experts in quantitative assessments of risk and acceptability. The results also indicated that people's stances toward technology regulation tend to cut across traditional sociodemographic lines.

Within-mouth correlations and reliabilities for probing depth and attachment level.

Replicate measurements of probing depth and attachment level were made by three examiners on the six Ramfjord teeth of 34 patients. Within-mouth correlations were high for single measurements, and yet higher for means across replicate measurements. Inter- and intra-examiner variability were both found to be low relative to between-patient variability. Conclusions are that the low within-mouth correlations reported by others may be the result of poor reliability, and that it is inappropriate to take the individual site as the unit of statistical analysis in clinical studies of periodontitis.

Effects of prenatal X-irradiation on open-field behavior in rats: application of randomized fostering technique and mapping results.

Sprague-Dawley (SD) rats were given X-irradiation (150 R) on Day 17 of gestation. After birth, all male pups were pooled once and then assigned randomly to irradiated mothers and control mothers. Offspring were administered an open-field test at about 7 weeks of age. The analysis was performed on the basis of two approaches: In the per subject approach, individual subject data (aggregation across Day 2 through Day 4) were treated as the basic unit of statistical analysis. In the per litter approach, double aggregation (aggregation across Day 2 through Day 4 for each subject and aggregation across subjects within each litter) was used. The per subject approach was slightly more sensitive as to the treatment effect, but it induced a reduction in the magnitude of eta squared. A principal component analysis was performed using eta squared together with those of several reference groups. Results were plotted on a map constructed from component scores. The characteristics of behavior in X-irradiated rats were very similar to those of the earlier stage of trials in terms of the location on the map. The postnatal maternal effect on open-field behavior was not serious and was adequately negligible in practice. A new fostering procedure was proposed and its advantages discussed.

Litter Effects in Open-Field Behavior and Distortion of Type I Error Rate with Individual Animals as the Unit of Statistical Analysis

Using open-field test data of male rats, a correlation provided an estimate of the magnitude of dependency among litter mates. A simulation experiment was performed to estimate the magnitudes of Type I error rate distortions when individual scores instead of litter mean scores were employed as the unit of statistical analysis. The results showed a rather large correlation among litter mates in defecation, latency of defecation, and latency of urination, suggesting that it is better to avoid treating the individual animal as the unit of statistical analysis. However, the magnitude of correlations in the remaining measures was negligible. As to Type I error rate, except for defecation, latency of defecation, and latency of urination, the obtained values obtained were not seriously affected. A very seriously inflated distortion in the error rate was found for body weight.

Issues Related to Designing and Conducting School Health Education Research

Abstract Investigators interested in conducting school health research face many important challenges. First, an appropriate research course for school health must be charted so the most important research issues are addressed in a systematic way. Second, there is a continuing need to develop scientifically sound research methods that can be used in the school setting. Third, there is the immediate need to identify ways of overcoming the usual problems encountered in the conduct of school health research. This paper focuses on the third challenge, via an analysis of the research design and measurement issues that most frequently confront school health researchers. The research design issues addressed include randomization of experimental units to treatments and selection of the appropriate statistical unit of analysis. The measurement issues addressed included use of existing versus newly developed instruments, use of norm-referenced versus criterion-referenced instruments, use of self-report techniques, ...

Issues Related to Designing and Conducting School Health Education Research

Investigators interested in conducting school health research face many important challenges. First, an appropriate research course for school health must be charted so the most important research issues are addressed in a systematic way. Second, there is a continuing need to develop scientifically sound research methods that can be used in the school setting. Third, there is the immediate need to identify ways of overcoming the usual problems encountered in the conduct of school health research. This paper focuses on the third challenge, via an analysis of the research design and measurement issues that most frequently confront school health researchers. The research design issues addressed include randomization of experimental units to treatments and selection of the appropriate statistical unit of analysis. The measurement issues addressed included use of existing versus newly developed instruments, use of norm-referenced versus criterion-referenced instruments, use of self-report techniques, and appropriate use of affective instruments. Following an analysis of the issues a series of relevant questions are posed.

Comparisons of behavioral, motoric and electrical criteria for assessment of sleep-wake states in the rabbit

Each of the sleep and wake states of animals are characterized by specific patterns of behavioral, motoric, and electrophysiological activity. The purpose of this study was to determine the amount of agreement among these three patterns. Sleep-wake behavior of two adult rabbits was observed for 4 continuous hours by an experienced judge. At the same time, a single-channel analog recording of motility and an analog recording of the electrical activity of the hippocampus were obtained. Each recording was scored by assigning a state category to each 10-second epoch. The three descriptions were then compared for agreement using the 10-second epoch as the unit of statistical analysis. There was a mean agreement of 85.12% between the techniques of direct observation and judgment of motility recordings. A mean agreement of 95.64% was obtained when comparing the hippocampal recordings and those of direct observation; the hippocampal and motility recordings had a mean agreement of 85.38%. The high correlations among the three different procedures support the hypothesis that state is a construct representing a set of underlying neurophysiological properties of the organism which express themselves in a similar and invariant manner via behavior, motility, and electrical brain activity.

Effects of anxiety on science‐related attitudes

Summaries English Relationships between anxiety and various science‐related attitudes were explored for a sample of 116 eighth and ninth grade classes. This study differed from previous research in that it involved science students specifically, it used attitudinal as distinct from cognitive outcomes, it employed the class mean as the unit of statistical analysis, and certain student background characteristics were controlled when estimating the strength of anxiety‐outcome relationships. Simple correlations between anxiety and attitude scores ranged from ‐‐ 0.10 to ‐‐ 037 for different scales, while semi‐partial correlations (with corresponding attitude pre‐test and general ability controlled) ranged from ‐‐ 0.09 to ‐‐ 0.27. Results suggest that student anxiety can impede science students’ progress towards achieving important attitude aims.