Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “multilevel analysis”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 649 records · Page 36Linked to original sources
PubMed2000

Detection of microcalcifications by means of multiscale methods and statistical techniques.

The detection of clustered microcalcifications can help the radiologist to detect early breast cancer. Microcalcifications exhibit some important characteristics, such as small size and high luminosity. Use of a computer-aided diagnosis (CAD) method can prevent them being overlooked. In this report, a multiresolution analysis is performed based on a multilevel wavelet transformation. Decomposition produces sub-band images which become visible only as details of the different scales. Thereafter, all the images will be combined in a final image, in order to obtain an image that contains all the interest details at the scale where microcalcifications tend to appear. Once the image, called detail image, is obtained, it is necessary to determine which details correspond with microcalcifications. Statistical analysis of the histogram permits classification of the zones likely to contain microcalcifications. Applying this statistical techniques over the whole image and representing the results in a two-dimensional map, clustered microcalcification regions are clearly distinguishable.

Breast Neoplasms↗
PubMed2006

Understanding team adaptation: a conceptual analysis and model.

This endeavor provides a multidisciplinary, multilevel, and multiphasic conceptualization of team adaptation with theoretical roots in the cognitive, human factors, and industrial-organizational psychology literature. Team adaptation and the emergent nature of adaptive team performance are defined from a multilevel, theoretical standpoint. An input-throughput-output model is advanced to illustrate a series of phases unfolding over time that constitute the core processes and emergent states underlying adaptive team performance and contributing to team adaptation. The cross-level mixed-determinants model highlights team adaptation in a nomological network of lawful relations. Testable propositions, practical implications, and directions for further research in this area are also advanced.

Adaptation, Psychological↗
PubMedDate not supplied

Applying multilevel analytic strategies in adolescent substance use prevention research.

BACKGROUND: School-based drug prevention programs have been criticized on methodologic grounds because the unit of analysis is often not the unit of randomization, thus increasing the likelihood of Type I errors. Application of multilevel analytic strategies appropriately corrects this biasing tendency. This study demonstrates the practical use of such analysis. METHODS: Data from 2,370 seventh-grade students participating in a substance use prevention trial were analyzed using a multilevel strategy. We examined the effectiveness of a social pressure resistance training and a normative education (NORM) intervention against an information-only control group. RESULTS: The NORM condition revealed 1-year program effects for cigarette and marijuana use with individuals as the unit of analysis and only marginal effects with classroom as the unit of analysis. No program effects were found using school as the analysis unit. A multilevel strategy revealed program effects for cigarettes and marijuana with both class and school as grouping levels. The effect for alcohol use was significant at the 2-year follow-up. CONCLUSIONS: Interventions establishing conservative drug use norms in classrooms may be an effective strategy in reducing substance use onset among adolescents. Utilization of appropriate analytic strategies is important in the analysis and interpretation of data containing nested structures.

Adolescent↗
PubMed2000

Multilevel modeling in epidemiology with GLIMMIX.

Previous work has shown that multilevel modeling can be a valuable technique for epidemiologic analysis. The complexity of using this approach, however, continues to restrict its general application. A critical factor is the lack of flexible and appropriate software for multilevel modeling. SAS provides a macro, GLIMMIX, that can be used for multilevel modeling, but that is not sufficient for a complete epidemiologic analysis. We here provide additional code to obtain epidemiologic output from GLIMMIX, illustrated with new data on diet and breast cancer from the European Community Multicenter Study on Antioxidants, Myocardial Infarction, and Breast Cancer (EURAMIC). Our results give epidemiologists an easily used tool for fitting multilevel models.

Breast Neoplasms↗
PubMed2006

Addressing the issues that arise in analysing multicentre cost data, with application to a multinational study.

Differences in the mean, spread and skewness of cost data collected from different countries present problems for analysis and interpretation. Here we develop generalised linear multilevel models to estimate the effects of patient and national characteristics on costs. Using gamma distributions and multiplicative effects for patient characteristics fitted the data better than models which assumed normal distributions or estimated additive effects. A multilevel gamma model is employed to allow for heterogeneity in the effects of patient case-mix across centres. Analysis of multinational cost data must recognise differences in mean, spread and skewness across centres, as well as the data's hierarchical structure.

Costs and Cost Analysis↗
PubMed2005

Multilevel mixed linear models for survival data.

For the analysis of correlated survival data mixed linear models are useful alternatives to frailty models. By their use the survival times can be directly modelled, so that the interpretation of the fixed and random effects is straightforward. However, because of intractable integration involved with the use of marginal likelihood the class of models in use has been severely restricted. Such a difficulty can be avoided by using hierarchical-likelihood, which provides a statistically efficient and fast fitting algorithm for multilevel models. The proposed method is illustrated using the chronic granulomatous disease data. A simulation study is carried out to evaluate the performance.

Case-Control Studies↗
PubMed2000

The application of multilevel, multivariate modelling to orthodontic research data.

OBJECTIVE: To demonstrate the use of multilevel multivariate modelling in the evaluation of multiple outcome dental data. BASIC RESEARCH DESIGN: Multiple outcome dental research data are used to illustrate the problems of analysing such complex information structures i.e. several outcomes clustered within subjects. Appropriate and statistically efficient methods of data analysis are proposed and illustrated step-by-step. The data structure is analysed using multilevel multivariate regression techniques and this process is discussed in comparison to conventional single-level multiple regression. PARTICIPANTS: Questionnaire data were obtained from an orthognathic study of 84 subjects seeking treatment and 106 'non-treatment' controls (full details of which are reported elsewhere). RESULTS: Multivariate multiple regression analysis demonstrated a number of advantages over separate single-level multiple regression approaches, including a gain in statistical efficiency and greater insight into: a) the role of (significant) explanatory variables and b) outcome variable interactions. Multilevel multivariate analysis reduced the risk of both Tipe I and Type II statistical errors. CONCLUSIONS: The study demonstrates the benefit of multilevel multivariate modelling over conventional single-level techniques for statistical analysis of multiple outcome data. As a result of ongoing technical developments in the power, speed and memory of modern PCs, multilevel multivariate regression can now be undertaken with relative ease. Consequently, researchers are better equipped to analyse such complex data structures, particularly within dentistry where multivariate data are common.

Data Interpretation, Statistical↗
PubMedDate not supplied

Clinical outcome following infra-inguinal percutaneous transluminal angioplasty for critical limb ischemia.

OBJECTIVE: The aim of this study was to assess the efficacy and durability of infra-inguinal PTA in patients with CLI, in terms of clinical outcome. DESIGN: Retrospective study of 50 consecutive patients with CLI that were exclusively treated by infra-inguinal PTA. METHODS: The indications for intervention were rest pain in seven (14%) patients, non-healing ulcers in 27 (54%), and gangrenous lesions in 16 (32%). Thirty-three (66%) of these patients presented with a single arterial lesion, and the remaining 17 (34%) with multilevel arterial lesions. Kaplan-Meier analysis was used to assess survival, patency, limb-salvage rates, and amputation-free survival. RESULTS: A total of 67 endovascular procedures were performed and 59 (88.1%) of them were considered to be technically successful. The median follow-up period was 12 months (interquartile range: 17 months). The 30-day mortality was 4%, while the cumulative survival rates at 12, 24, and 36 months were 73%, 67%, and 59%, respectively. The cumulative primary patency rates at 12 and 24 months were 63% and 52%, respectively, and remained unchanged thereafter. The estimated secondary patency rate was 72% at 36 months. There was only one below-knee amputation in the patients that were treated exclusively with infra-inguinal PTA. The cumulative amputation-free survival at the same period was estimated at 60%. CONCLUSIONS: Infra-inguinal PTA had a good early and late outcome in this series of patients with a limited life expectancy. These results are comparable to historical results of surgical revascularization in the treatment of CLI. There is need for a randomized study to determine the primary optimal interventional approach for patients with CLI.

Aged↗
PubMed1987

The use of LOTUS 1-2-3 in statistics.

This paper describes a convenient way of performing statistical tests in biology. The recent development of powerful spreadsheet programs for microcomputers has made it possible to easily apply various statistical significance tests on biological data. Presently the following tests have been implemented in the LOTUS 1-2-3 framework: Student's t-test, chi-square test, analysis of variance (single classification random ANOVA), Student-Neumann-Kuels test, correlation analysis and analysis of linear regression (single and multilevel design). The most important advantages gained by using 1-2-3 instead of the commercial statistical software packages are the simplicity of entering data, the possibility of asking "what-if?" questions, the simple, but useful graphical presentation of data and the ease of actual building of the tests.

Biometry↗
PubMed1979

Dental dolorimetry for human pain research: methods and apparatus.

Electrical stimulation of human tooth pulp provides a means of safely producing human pain in the laboratory. This paper describes a dolorimetry and data collection system for stimulating volunteers, recording responses and analyzing data. The system allows multilevel stimulation in pseudorandom sequences and analysis of results using the methods of Sensory Decision Theory. It consists of modified commercial equipment, specially designed circuitry, an interface, and a programmable calculator. Fundamental problems and safety considerations for electrical dental stimulation are reviewed. Reliability of stimulation and response measurement is discussed.

Clinical Trials as Topic↗
PubMed2004

A preliminary study of multilevel geographic distribution & prevalence of Aedes aegypti (Diptera: Culicidae) in the state of Goa, India.

BACKGROUND & OBJECTIVES: Dengue virus activity has never been reported in the state of Goa. The present study was carried out to document a multilevel geographic distribution, prevalence and preliminary analysis of risk factors for the invasions of Aedes aegypti in Goa. METHODS: A geographic information system (GIS) based Ae. aegypti surveys were conducted in dry (April 2002) and wet (July 2002) seasons in the rural and urban settlements. The random walk method was used for household coverage. The non-residential area visits included ancillaries of roadways, railways, air-and seaports. Simultaneous adult mosquito collections and one-larva per container technique were adopted. RESULTS: The Ae. aegypti larval and adult prevalence was noted in all the four urban areas in both dry (Density index (DI)= 3 to 6) and wet (DI= 5 to 7) seasons and only one out of 3 villages showed Ae aegypti presence in wet season (DI= 5 to 7). In the residential areas, hutments showed higher relative prevalence indices (Breteau index, BI=100; container index, CI=11.95; adult house index, AHI=13.33) followed by close set cement houses (BI=44.1; CI=12.0; AHI=11.24). Ae aegypti relative prevalence indices were also more for households with pets (BI=85.11; CI=12.5; AHI= 42.85); those with tap had higher risk (larval house index, LHI =32.03; relative risk, RR>2, n=256). Plastic drum was the most preferred breeding place (chi(2) = 19.81; P<0.01; RR=3.41) among domestic containers and rubber tyres (chi(2) = 11.86; P<0.01; RR=3.61)among sundry/rainfilled containers. INTERPRETATION & CONCLUSION: Established Ae aegypti prevalence in the urban settlements during dry and wet seasons and its scattered distribution in a rural settlement spell risk of dengue infection at macro-level. In the residential areas nature and types of the households, tap water supply and storage and communities' attitude and practices contribute to sustained meso-level risk of Ae aegypti prevalence dependant DEN. The non-residential areas offer transient meso-level risk as Ae aegypti prevalence was seasonally unstable and monsoon dependent. Risk at micro-level was due to the preferred larval habitats of Ae aegypti breeding viz., residential plastic-ware and tyres, and transport tyres in non-residential areas.

Aedes↗
PubMed2006

[Lymphatic mapping and parametrial lymph nodes identification in patients with early stage cervical cancer].

OBJECTIVE: To determine the presence, distribution, and metastasis incidence of parametrial lymph nodes (PLN) of patients with cervical cancer and to investigate the role of lymphatic mapping and topographic section in PLN identification. METHODS: Sixty patients with early stage (Ib-IIa) cervical cancer undergoing radical hysterectomy and pelvic lymphadenectomy were included in the study. Before surgery 4 ml methylene was injected into the cervix around the tumor. The blue-dyed lymph nodes were identified as sentinel lymph nodes (SLN) during operation. An immediate topographic section on uterine specimen was performed to separate the PLN from parametria for pathologic examination. RESULTS: Ninety five PLN were presented in 38 (63%) of 60 specimens, with a mean size in diameter of (0.46 +/- 0.24) cm. Among the total PLN, 57 (60%) were located parallel to uterine artery through the entire broad ligament, and the other 38 (40%) were scattered in cardinal ligament, sacral ligament and vesicocervical ligament. After lymphatic mapping, 69 (73%) of PLN were dyed and identified as SLN. Parametrial metastasis was found in 12 (20%) patients, and parametrium was the only site containing positive nodes in 2 patients with parametrial metastasis. On routine pathologic evaluation, 17 PLN were found to be positive. Among the remaining 78 PLN, multilevel sectioning in conjunction with immunohistochemical analysis was carried out and 3 PLN containing micrometastases were identified. CONCLUSIONS: The study shows that PLN are usually found in the parametria, and these nodes often contain metastatic diseases which are easily overlooked. Lymphatic mapping followed by meticulous topographic section is feasible in PLN identification in patients with cervical cancer.

Adult↗
PubMed2001

Meta-analysis of continuous outcome data from individual patients.

Meta-analyses using individual patient data are becoming increasingly common and have several advantages over meta-analyses of summary statistics. We explore the use of multilevel or hierarchical models for the meta-analysis of continuous individual patient outcome data from clinical trials. A general framework is developed which encompasses traditional meta-analysis, as well as meta-regression and the inclusion of patient-level covariates for investigation of heterogeneity. Unexplained variation in treatment differences between trials is considered as random. We focus on models with fixed trial effects, although an extension to a random effect for trial is described. The methods are illustrated on an example in Alzheimer's disease in a classical framework using SAS PROC MIXED and MLwiN, and in a Bayesian framework using BUGS. Relative merits of the three software packages for such meta-analyses are discussed, as are the assessment of model assumptions and extensions to incorporate more than two treatments.

Alzheimer Disease↗
PubMed2003

Factors that predict the benefit of lowering intraocular pressure in normal tension glaucoma.

PURPOSE: To study whether the benefit of lowering of intraocular pressure (IOP) varies according to certain traits. DESIGN: Randomized clinical trial, secondary analysis. METHODS: Visual field data were analyzed from 144 subjects (144 eyes) randomized not to receive IOP-lowering treatment or to have the IOP lowered by 30%. Survival analyses were applied to compare times to progression between groups. Changes in mean deviation global index over time were compared with multilevel random effects models. RESULTS: By univariate analysis, the most readily demonstrated treatment benefit occurred in patients without baseline disk hemorrhage, of female gender, with family history of glaucoma, without family history of stroke, without personal history of cardiovascular disease, and with mild disk excavation; IOP lowering benefited females with migraine (P <.05) but perhaps without eliminating all migraine-associated risk. CONCLUSIONS: It is suggested that different factors may contribute to the glaucomatous optic neuropathy in different cases of normal tension glaucoma, interacting with IOP to different degrees and, thereby, affecting the magnitude of benefit of IOP lowering. Further study is required to establish interactions that would have implications for understanding the disease mechanisms in glaucomatous cupping, for guiding development of new treatment modalities, and for making clinical decisions regarding prognosis and management of individual patients.

Analysis of Variance↗
PubMed2002

Classification tree analysis: a statistical tool to investigate risk factor interactions with an example for colon cancer (United States).

OBJECTIVE: Classification tree analysis is a potentially powerful tool for investigating multilevel interactions. Within the context of colon cancer etiology it may help identify disease pathways and evaluate important interactions of risk factors. METHODS: We apply classification tree analysis as a statistical method to investigate interactions of risk factors for colon cancer. We use data collected from a population-based case-control study of newly diagnosed cases of colon cancer (N = 4403 cases and controls). RESULTS: Our results indicate that, as expected, there are many factors that influence colon cancer risk, and that they interact on many levels. We find that the most important factor is the utilization of aspirin and/or non-steroidal anti-inflammatory drugs (NSAID), with those taking this medication having lower risk. Family history appears as a level two modifying factor when NSAID are not used, whereas Western diet is the second factor when NSAID are taken. The final tree has six levels, contains several modifying factors and correctly classifies case or control status for 60.8% (95% CI 59.4-62.2) of all individuals. CONCLUSIONS: Our results suggest that risk factors work together to determine disease risk. By accounting for interactions between risk factors we become better able to dissect disease pathways and determine those risk factors that increase susceptibility to disease. Our results highlight the importance of designing studies so that interactions can be addressed.

Adult↗
PubMed2006

Tobacco use among immigrant and nonimmigrant adolescents: individual and family level influences.

PURPOSE: To identify individual and family level characteristics that might explain differences in rates of tobacco use among immigrant and nonimmigrant adolescents. METHODS: Data for analysis come from a probability sample of 5401 adolescents aged 12-18 years participating in the Ontario Health Survey (OHS). Three groups were compared: (a) adolescents born in Canada to Canadian-born parents (n = 3886), (b) adolescents born in Canada to immigrant parents (n = 1233), and (c) adolescents born outside of Canada (n = 282). Discrete, multilevel logistic regression was used in the analysis. RESULTS: Adolescents born outside of Canada report the lowest rates of tobacco use, despite greater economic hardship. A negative association emerges between family socioeconomic status and tobacco use among adolescents born in Canada but not among adolescents born outside of Canada. Immigrant youth are less likely to affiliate with peers who smoke and are more likely to come from families where parents do not smoke: these differences partially explain the decreased rates of tobacco use among immigrant adolescents. CONCLUSIONS: Although subject to greater economic hardship, immigrant youth are less likely to engage in tobacco use. Protective factors associated with immigrant family life, such as lower rates of parental tobacco use and less exposure among immigrant adolescents to peers who smoke, may counteract some of the negative effects of poverty and social hardship. Future research should begin to address the processes that lead to adaptive outcomes among adolescents from immigrant families, despite greater exposure to social disadvantage.

Adolescent↗
PubMed2005

Multilevel generalized linear models for modelling age-related gender difference in violent behaviour and associated factors in the general household population.

It is preferable to use longitudinal data when studying patterns of violence and antisocial behaviour over the lifespan together with the associated risk factors in the general population. From the statistical modelling perspective, random samples of cross-sectional data, representative of the population, can be a reliable alternative. Sampling, weighting, and possible geographical clustering of the behaviour must be considered in the analysis together with correct choice of model as a function of age, although cohort effects and age effects are not separated from the analysis. This paper demonstrates the use of multilevel generalized linear models in the British National Survey of Psychiatric Morbidity in 2000. A multilevel logistic model as a special case of a generalized linear model with individual weightings was adapted for a dichotomous measure of violence and extended to Poisson and negative binomial outcomes. Three types of age function, discrete age effects, continuous age effects, and piecewise polynomial function of age intervals were evaluated for goodness of fit, and for their practical advantages and disadvantages. Models were developed for possible risk factors in relation to specific age groups of interest.

Adolescent↗
PubMed2005

Combined use of field and laboratory testing to predict preferred flow paths in an heterogeneous aquifer.

Elevated nitrate concentrations within a municipal water supply aquifer led to pilot testing of a field-scale, in situ denitrification technology based on carbon substrate injections. In advance of the pilot test, detailed characterization of the site was undertaken. The aquifer consisted of complex, discontinuous and interstratified silt, sand and gravel units, similar to other well studied aquifers of glaciofluvial origin, 15-40 m deep. Laboratory and field tests, including a conservative tracer test, a pumping test, a borehole flowmeter test, grain-size analysis of drill cuttings and core material, and permeameter testing performed on core samples, were performed on the most productive depth range (27-40 m), and the results were compared. The velocity profiles derived from the tracer tests served as the basis for comparison with other methods. The spatial variation in K, based on grain-size analysis, using the Hazen method, were poorly correlated with the breakthrough data. Trends in relative hydraulic conductivity (K/K(avg)) from permeameter testing compared somewhat better. However, the trends in transient drawdown with depth, measured in multilevel sampling points, corresponded particularly well with those of solute mass flux. Estimates of absolute K, based on standard pumping test analysis of the multilevel drawdown data, were inversely correlated with the tracer test data. The inverse nature of the correlation was attributed to assumptions in the transient drawdown packages that were inconsistent with the variable diffusivities encountered at the scale of the measurements. Collectively, the data showed that despite a relatively low variability in K within the aquifer under study (within a factor of 3), water and solute mass fluxes were concentrated in discrete intervals that could be targeted for later bioremediation.

Cities↗