Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Statistical Power”

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 1,063 records · Page 59Linked to original sources
PubMed1998

Statistical methods for assessing measurement error (reliability) in variables relevant to sports medicine.

Minimal measurement error (reliability) during the collection of interval- and ratio-type data is critically important to sports medicine research. The main components of measurement error are systematic bias (e.g. general learning or fatigue effects on the tests) and random error due to biological or mechanical variation. Both error components should be meaningfully quantified for the sports physician to relate the described error to judgements regarding 'analytical goals' (the requirements of the measurement tool for effective practical use) rather than the statistical significance of any reliability indicators. Methods based on correlation coefficients and regression provide an indication of 'relative reliability'. Since these methods are highly influenced by the range of measured values, researchers should be cautious in: (i) concluding acceptable relative reliability even if a correlation is above 0.9; (ii) extrapolating the results of a test-retest correlation to a new sample of individuals involved in an experiment; and (iii) comparing test-retest correlations between different reliability studies. Methods used to describe 'absolute reliability' include the standard error of measurements (SEM), coefficient of variation (CV) and limits of agreement (LOA). These statistics are more appropriate for comparing reliability between different measurement tools in different studies. They can be used in multiple retest studies from ANOVA procedures, help predict the magnitude of a 'real' change in individual athletes and be employed to estimate statistical power for a repeated-measures experiment. These methods vary considerably in the way they are calculated and their use also assumes the presence (CV) or absence (SEM) of heteroscedasticity. Most methods of calculating SEM and CV represent approximately 68% of the error that is actually present in the repeated measurements for the 'average' individual in the sample. LOA represent the test-retest differences for 95% of a population. The associated Bland-Altman plot shows the measurement error schematically and helps to identify the presence of heteroscedasticity. If there is evidence of heteroscedasticity or non-normality, one should logarithmically transform the data and quote the bias and random error as ratios. This allows simple comparisons of reliability across different measurement tools. It is recommended that sports clinicians and researchers should cite and interpret a number of statistical methods for assessing reliability. We encourage the inclusion of the LOA method, especially the exploration of heteroscedasticity that is inherent in this analysis. We also stress the importance of relating the results of any reliability statistic to 'analytical goals' in sports medicine.

Bias↗
PubMed2007

Obesity and the risk of epithelial ovarian cancer: a systematic review and meta-analysis.

Obesity is a risk factor for several hormone-related cancers but evidence for an effect on risk of epithelial ovarian cancer remains inconclusive. Many studies evaluating this association have had insufficient statistical power to detect modest effects, particularly for histological subtypes of ovarian cancer. We have therefore assembled the published evidence on obesity and ovarian cancer in a systematic literature review and meta-analysis. We identified eligible studies using Medline and manual review of retrieved references, and included all population-based studies that assessed the association between overweight, body mass index (BMI25-29.9) and obesity (BMI30) and histologically confirmed ovarian cancer. Meta-analysis was restricted to those studies that expressed effect as an odds ratio (OR), risk ratio, or standardised incidence ratio and 95% confidence interval (CI). We identified 28 eligible studies, of which 16 on adult obesity and 9 on obesity in early adulthood were suitable for meta-analysis. Overall, 24 of 28 studies reported a positive association between obesity and ovarian cancer, and in 10 this reached statistical significance. The pooled effect estimate for adult obesity was 1.3 (95%CI1.1-1.5) with a smaller increased risk for overweight (OR1.2;95%CI1.0-1.3). The pooled OR was stronger among case-control studies (OR=1.5) than cohort studies (OR=1.1). Overweight/obesity in early adulthood was also associated with an increased risk of ovarian cancer. There was no evidence that the association varied for the different histological subtypes of ovarian cancer. Ovarian cancer should be added to the list of cancers likely to be related to obesity.

Adolescent↗
PubMed2006

Stroop performance in depressive patients: a preliminary report.

BACKGROUND: The Stroop interference test requires executive control functions, in particular inhibition of a learned routine (in this case word reading). Depressive patients show deficits on tests of executive function. However, the impact of confounding variables like type of depression and anxiety level is not yet elucidated for depressive patients. This is of clinical importance, since executive functions seem to play an important role in predicting treatment response and functional outcome. METHODS: 23 depressive patients and 27 healthy subjects performed a computerized mixed trial Stroop task. Depressive patients were divided according to DSM-IV diagnosis into melancholic and non-melancholic subgroups. Furthermore the level of anxiety was assessed in all subjects. RESULTS: When depressed patients were analyzed as a whole group, they showed only a trend towards higher Stroop interference effect at the beginning of the task. When analysis was performed using according to DSM-IV defined melancholic and non-melancholic subgroups, only non-melancholic patients were impaired in the Stroop task compared to melancholic patients and healthy subjects. LIMITATIONS: The sample size was small resulting in low statistical power. Furthermore, the patients were medicated. CONCLUSIONS: The unexpected result that melancholic patients perform better than non-melancholic ones may be due to their more pronounced rigidity, which makes them more resistant against distraction. Hence, more detailed psychopathological assessment is desirable for future investigations in executive functions of melancholic patients.

Adult↗
PubMed2004

The conditional relative odds ratio provided less biased results for comparing diagnostic test accuracy in meta-analyses.

OBJECTIVE: Meta-analytic techniques are used to combine the results of different studies that have evaluated the accuracy of a given diagnostic test. The techniques commonly generate values that either describe the performance of a particular test or compare the discriminative ability of two tests. The later has received very little attention in the literature, and is the focus of this article. STUDY DESIGN AND SETTING: We summarize existing methods based on an odds ratio (OR) and propose a novel technique for conducting such analysis, the conditional relative odds ratio (CROR). We demonstrate how to extract the required data and calculate several different comparative indexes using a hypothetic example. RESULTS: A paired analysis is preferred to decrease selection bias and increase statistical power. There is no standard method of obtaining the standard error (SE) of each relative OR; thus, the SE of the summary index might be underestimated under the assumption of no within-study variability. CONCLUSION: The CROR method estimates less biased indexes with SEs, and conditioned on discordant results, it is much less problematic ethically and economically. However, small cell counts may lead to larger SEs, and it might be impossible to construct McNemar's 2 x 2 tables for some studies.

Data Interpretation, Statistical↗
PubMed2026

PYRAMA: an open-source tool for advanced meta-analysis of genome wide association studies.

MOTIVATION: Genome-wide association study (GWAS) meta-analysis tools are essential for integrating summary statistics across multiple cohorts, thereby increasing statistical power and validating genetic associations. Widely cited tools, such as METAL, PLINK, and GWAMA, have facilitated numerous significant discoveries in the field of GWAS. Nevertheless, these tools offer a limited set of meta-analysis methods and typically require users to have prior experience with command-line tools to be executed. RESULTS: We present here PYRAMA, an open-source tool which is designed for meta-analysis of genome wide association studies. This work introduces an easy-to-use software package that includes several meta-analysis methods that are absent in similar software packages. PYRAMA is faster compared to other tools, supports robust methods for analysis and meta-analysis, fixed-effects, random-effects and Bayesian meta-analysis and it is currently the only tool that supports meta-analysis with imputation of summary statistics. It is available both as a standalone tool and as a freely available web server. AVAILABILITY AND IMPLEMENTATION: https://github.com/pbagos/PYRAMA, https://doi.org/10.5281/zenodo.17830449.

Genome-Wide Association Study↗
PubMed2006

Detection of carryover in automated milk sampling equipment.

Equipment for sampling milk in automated milking systems may cause carryover problems if residues from one sample remain and are mixed with the subsequent sample. The degree of carryover can be estimated statistically by linear regression models. This study applied various regression analyses to several real and simulated data sets. The statistical power for detecting carryover milk improved considerably when information about cow identity was included and a mixed model was applied. Carryover may affect variation between animals, including genetic variation, and thereby have an impact on management decisions and diagnostic tools based on the milk content of somatic cells. An extended procedure is needed for approval of sampling equipment for automated milking with acceptable latitudes of carryover, and this could include the regression approach taken in this study.

Animals↗
PubMed2004

Sample-size requirements for comparisons of two groups on repeated observations of a binary outcome.

When preparing a research protocol, an investigator must be as careful in projecting sample-size requirements as in specifying hypotheses. In this article, tables are presented that provide estimates of sample-size requirements for statistical power of 0.80 with two-tailed alpha-levels of 0.05 in studies with a balanced design that plan to compare two groups on time-averaged, repeated observations of a binary outcome. The estimates, which are based on the algorithm of Diggle, Heagerty, Liang, and Zeger, are a function of several features of the study, including the response rates for each group, the number of repeated observations per participant, and the strength of the association among observations within participants as quantified with an intraclass correlation coefficient.

Algorithms↗
PubMed2005

Preclinical assessment of HIV vaccines and microbicides by repeated low-dose virus challenges.

BACKGROUND: Trials in macaque models play an essential role in the evaluation of biomedical interventions that aim to prevent HIV infection, such as vaccines, microbicides, and systemic chemoprophylaxis. These trials are usually conducted with very high virus challenge doses that result in infection with certainty. However, these high challenge doses do not realistically reflect the low probability of HIV transmission in humans, and thus may rule out preventive interventions that could protect against "real life" exposures. The belief that experiments involving realistically low challenge doses require large numbers of animals has so far prevented the development of alternatives to using high challenge doses. METHODS AND FINDINGS: Using statistical power analysis, we investigate how many animals would be needed to conduct preclinical trials using low virus challenge doses. We show that experimental designs in which animals are repeatedly challenged with low doses do not require unfeasibly large numbers of animals to assess vaccine or microbicide success. CONCLUSION: Preclinical trials using repeated low-dose challenges represent a promising alternative approach to identify potential preventive interventions.

AIDS Vaccines↗
PubMed2003

Impact of adjuvant chemotherapy and surgical staging in early-stage ovarian carcinoma: European Organisation for Research and Treatment of Cancer-Adjuvant ChemoTherapy in Ovarian Neoplasm trial.

BACKGROUND: All randomized trials of adjuvant chemotherapy for early-stage ovarian cancer have lacked the statistical power to show a difference in the effect on survival between adjuvant chemotherapy and no adjuvant chemotherapy. They have also not taken into account the adequacy of surgical staging. We performed a prospective unblinded, randomized phase III trial to test the efficacy of adjuvant chemotherapy in patients with early-stage ovarian cancer, with emphasis on the extent of surgical staging. METHODS: Between November 1990 and January 2000, 448 patients from 40 centers in nine European countries were randomly assigned to either adjuvant platinum-based chemotherapy (n = 224) or observation (n = 224) following surgery. Endpoints were overall survival and recurrence-free survival, and the analysis was on an intention-to-treat basis. The Kaplan-Meier method was used to perform time-to-event analysis, and the log-rank test was used to compare differences between treatment arms. Statistical tests were two-sided. RESULTS: After a median follow-up of 5.5 years, the difference in overall survival between the two trial arms was not statistically significant (hazard ratio [HR] = 0.69, 95% confidence interval [CI] = 0.44 to 1.08; P =.10). Recurrence-free survival, however, was statistically significantly improved in the adjuvant chemotherapy arm (HR = 0.63, 95% CI = 0.43 to 0.92; P =.02). Approximately one-third of patients (n = 151) had been optimally staged and two-thirds (n = 297) had not. Among patients in the observation arm, optimal staging was associated with a statistically significant improvement in overall and recurrence-free survival (HR = 2.31 [95% CI = 1.08 to 4.96]; P =.03 and HR = 1.82 [95% CI = 1.02 to 3.24] P =.04, respectively). No such association was observed in the chemotherapy arm. In the non-optimally staged patients, adjuvant chemotherapy was associated with statistically significant improvements in overall and recurrence-free survival (HR = 1.75 [95% CI = 1.04 to 2.95]; P =.03 and HR = 1.78 [95% CI = 1.15 to 2.77]; P =.009, respectively). In the optimally staged patients, no benefit of adjuvant chemotherapy was seen. CONCLUSION: Adjuvant chemotherapy was associated with statistically significantly improved recurrence-free survival in patients with early-stage ovarian cancer. The benefit of adjuvant chemotherapy appeared to be limited to patients with non-optimal staging, i.e., patients with more risk of unappreciated residual disease.

Adult↗
PubMed2001

Maintenance of intact sediment box cores as laboratory mesocosms.

Mesocosms consisting of physically and biologically intact segments of natural communities are an ideal compromise between single species tests and ecosystem experiments in the assessment of sediment contamination. Therefore, large intact sediment cores, as mesocosms with naturally co-adapted communities, would allow sediment contamination to be assessed using the replicability and statistical power of laboratory techniques, while retaining much of the ecological realism of field studies. This study investigates the collection and maintenance of such cores, collected from an unimpacted site in Lake Erie. It demonstrates that box cores containing relatively undisturbed freshwater sediments can be brought back to the laboratory and maintained for up to 8 weeks with little change in the resident benthic fauna. Feeding the systems is not required, nor is it deleterious to the indigenous fauna.

Animals↗
PubMed2026

Phylogenomic subsampling and upsampling for efficient evolutionary analyses of big data.

Long runtimes, high memory demands, and reliance on high-performance computing impede phylogenomic analyses. We review a scalable phylogenomic subsampling with upsampling (PSU) framework, in which small subsamples of sites from a concatenated alignment are expanded by upsampling before inference, and the resulting analyses are then aggregated to obtain evolutionary estimates. PSU harnesses the fact that the computational cost of maximum likelihood analysis is strongly influenced by the number of distinct site patterns in the concatenated alignment, whereas statistical power depends primarily on the amount of evolutionary information represented by the total number of sites and substitutions. By reducing the former while restoring the latter through upsampling, PSU can approximate many full-data analyses at substantially lower computational cost. Analysis of simulated and empirical datasets shows that PSU can accurately estimate bootstrap support values, select the optimal substitution model, test evolutionary hypotheses, and infer branch lengths, divergence times, and associated uncertainty measures, while reducing runtime and memory requirements by orders of magnitude. PSU also provides distributions of inferred clade support across independent subsamples, enabling detection of conflicting phylogenetic signals that may remain hidden in conventional bootstrap analysis. Automated tuning of subsample size, the number of subsamples, and the number of upsampling replicates make PSU practical across diverse datasets. We suggest that PSU is a general strategy for scalable phylogenomic inference using a broad range of statistical methods. By enabling analyses of genome-scale alignments on commodity hardware, PSU broadens research access and reduces environmental and infrastructural costs of big-data phylogenomics.

confidence limits↗
PubMed2005

[Diagnostic radiation and the risk of cancer].

The risk of radiation-related cancer following exposure to diagnostic radiation is of much concern. Diagnostic exposure is a repeated one to low dose radiation, while acute exposure occurred among atomic bomb survivors where the epidemiological survey contributes to the current cancer risk estimates of low doses. In several cohort studies on medical exposure at low doses, there is no statistical power of detection due to population size and no dose information. Even in cohort studies on occupational exposure there is no clear conclusion, however, a pooled analysis of nuclear workers in several countries is expected to produce a better basis for risk estimate at low doses. The risk estimate based on the linear non-threshold (LNT) dose response derived from the atomic bomb survivor data remains unresolved scientifically, and thus it has much uncertainty. Recent radiation biology suggests that a bystander effect and adaptive response might modify the estimated cancer risk based on the LNT model at low doses. However, there is no clear evidence in human data. The most effective way to clarify low-dose risk is to focus on the mechanism of radiation carcinogenesis. The risk from almost all diagnostic X-rays may be so small that no excess cancer incidence can be statistically detected.

Cohort Studies↗
PubMed1999

[The incidence of postoperative nausea and vomiting is not effected by routinely applied manual pre-oxygenation during induction of anesthesia].

OBJECTIVE: To evaluate whether routine pre-intubation positive pressure mask ventilation (PPMV) influences the incidence of postoperative nausea and vomiting (PONV). DESIGN: Prospective, randomised single blinded study. PATIENTS: 669 ASA class I-III patients of either sex (number calculated as follows: incidence of PONV = 30%, group difference = 25%, a-error < 5%, statistical power = 90%) scheduled for elective surgery (no eye, neck, nose or ear surgery) of at least 30 min duration. INTERVENTIONS: Approval by the local ethical committee and informed written consent was obtained. After preoxygenation (3 min) and induction of anesthesia with fentanyl (1-2 micrograms.kg-1 b.w.) and thiopental (5 mg.kg-1 b.w) patients were divided into two groups: group 1 patients (without PPMV, n = 333) received succinylcholine 30s after thiopental followed by tracheal intubation. Group 2 patients (with PPMV, n = 336) were ventilated by mask for at least 30s after thiopental injection, followed by succinylcholine and, after another 120s of PPMV, tracheal intubation. All anesthetics were performed by 15 anesthesiologists (8 certified staff members, 7 residents). MEASUREMENTS: Primary endpoint: incidence of PONV during the first 24 h postoperatively. Secondary end point: relation between PONV and medical qualification of the anesthesiologists. NULL HYPOTHESIS: significant difference in PONV between groups. STATISTICS: contingency tables with chi-square and Fisher's exact test, Kruskal-Wallis-test (for categorical variables); ANOVA with post-hoc Scheffe (for continuous variables), p < 0.05. MAIN RESULTS: No difference was found in the incidence of nausea (30.6% vs. 28%, p = 0.5) or vomiting (20.1% vs. 17%, p = 0.32) regardless whether the patients received PPMV or not. Women were nearly three times more likely to suffer from PONV (35.2% vs. 13.8%, p < 0.0001). Distribution of age, weight, height, anesthetic duration and surgical procedures were comparable between groups. The degree of medical qualification did not influence the incidence of PONV (p = 0.543). CONCLUSION: Since neither routine pre-intubation positive pressure mask ventilation nor the medical qualification of the anesthesilogist affect the incidence of PONV neither variable needs to be taken into account in studies concerning PONV.

Adolescent↗
PubMed1996

Comparison of one-sample two-sided sequential t-tests for application in epidemiological studies.

In epidemiological prospective cohort studies, exposure levels of cases with disease and disease-free control subjects can be measured by laboratory analysis of previously stored biological specimens. In such studies, a sequential t-test can be used for preliminary evaluations, at the expense of the smallest possible number of specimens, of whether a new aetiological hypothesis is worth further investigation or whether specimens should rather be spared to test other, more fruitful, hypotheses. For this purpose, we recently compared two sequential probability ratio tests (SPRTs), in which the log-likelihood ratio was either based on an approximation, or computed exactly, and which were adapted to account for various control-to-case matching ratios. The tests turned out relatively conservative, particularly in terms of the significance level achieved. In the present paper, we compare an SPRT for matched or paired data based on Rushton's approximation to the log-likelihood ratio with a profile log-likelihood method developed by Whitehead. The comparison is partly mathematical, and partly based on computerized simulations. Average sample size for a sequential test is already smaller than for the equivalent fixed sample test. Increasing the number of controls matched per case further reduces the average sample size necessary to come to a decision. We show that, irrespective of the number of controls per case, pre-specified levels of statistical power and significance are respected closely by Whitehead's method, but not by Rushton's SPRT. This last procedure can lead to a significant loss in power. Since, in addition, Whitehead's method has been implemented in a commercially available computer program (PEST), we conclude that this method can be preferred to the methods we described earlier. Moreover, compared with the method of Rushton, Whitehead's method has the advantage that it can also be applied to groupwise inspection of the data and that it can also be converted easily into a truncated procedure.

Breast Neoplasms↗
PubMed1996

Influence of criteria on the results of in vitro evaluation of microleakage.

OBJECTIVES: The aim of this study was to compare and explain the statistical methods employed to evaluate the in vitro sealing efficiency of adhesive restorative systems. METHODS: Two hundred and sixty sound freshly extracted human premolars were randomly divided into 13 groups. Standardized cavities were prepared, and the teeth were restored with 13 restorative systems. The teeth were thermocycled, immersed in dye, embedded in resin and sectioned. Five evaluation criteria were recorded: mean, median and mode of the data measured on each tooth, maximum dye penetration measurements on each tooth, and percentage of teeth in each group without any dye penetration. For each parameter, one-way ANOVAs and Duncan a posteriori tests were used to compare the 13 systems. RESULTS: The number of non-statistically different subgroups, pointed out by Duncan tests, was greater when the selected criterion was the maximum dye penetration (6 subgroups) or the percentage of teeth without any penetration (5 subgroups) than when the criterion was the median (3 subgroups), the mode or the mean (4 subgroups). The positioning of the 13 adhesive restorative systems established from the five criteria was different. Equivalent adhesion strategies revealing different experimental results indicate that other factors contribute to the final effectiveness of a particular system: clinical approach with respect to the formation of an elastic bonding layer, and shrinkage, physical and rheological properties of resin composite. SIGNIFICANCE: The results of these in vitro studies of dye penetration must be considered as comparisons and not as absolute conclusions. The maximum dye penetration measured on each tooth, which complies with the aim of the in vitro evaluation of sealing efficiency defined by Pashley (1990) and allows powerful statistical analysis of results, seems to be the best evaluation criterion.

Analysis of Variance↗
PubMed2006

Evaluation of specific and non-specific effects in homeopathy: feasibility study for a randomised trial.

OBJECTIVE: To determine the feasibility, in terms of acceptability to patients, physicians and other staff; data return and statistical power of a study to elucidate the relative contributions of specific and non-specific effects in homeopathic treatment of dermatitis. DESIGN: Randomised, controlled 4-arm trial, 2 arms double-blind. SETTING: Outpatient clinic, Royal London Homoeopathic Hospital. PARTICIPANTS: Seventy-five adult patients with dermatitis. INTERVENTIONS: Patients were randomly allocated to: 'fast track' open verum homeopathy, 'fast track' double-blind verum homeopathy, 'fast track' double-blind placebo homeopathy or waiting list control. MAIN OUTCOME MEASURES: One hundred millimeter visual analogue scale of overall symptom severity; 10 point digital scores of sleep, itching, skin condition; weekly 5-point Likert scale of topical steroid use; Dermatology Life Quality Index at entry and completion. RESULTS: Recruitment was below target, but the study was acceptable to staff and feasible. Blinded patients were more likely to withdraw (P=0.021, chi2 test). After correction for baseline differences and multiple comparisons, no outcome measure showed statistically significant between group differences. Blindness appeared to have a negative effect, but this was confounded by differential withdrawal. CONCLUSIONS: A definitive trial of this design is unlikely to discriminate the relative contributions of the non-specific and specific effects to the outcome of homeopathic treatment of dermatitis, because of patient preference issues.

Adult↗
PubMedDate not supplied

Intravenous cyclophosphamide therapy for systemic sclerosis. A single-center experience and review of the literature with pooled analysis of lung function test results.

OBJECTIVE: Oral cyclophosphamide (CYC) is a promising therapy for Systemic Sclerosis (SSc)-related interstitial lung disease (ILD). The use of intravenous (i.v.) pulses has been considered as an alternative route of drug administration, possibly associated with reduced toxicity. Our objectives were to re-evaluate our experience with i.v. CYC, to review the literature, and to pool our results with those available from other groups, improving the statistical power of the analysis. METHODS: 1) Retrospective analysis of our center experience on 16 patients with SSc and active alveolitis, treated with i.v. CYC 750 mg + 6-methylprednisolone 125 mg every 3 weeks. 2) Pooled analysis of papers published in peer-reviewed journals reporting detailed data on each patient treated with i.v. CYC. The end-point was modification in the results of lung function tests (LFT) after 6 months. Piecewise regression analysis was performed using a linear mixed-effects model adjusted for baseline values to evaluate the changes in LFT. RESULTS: Retrospective analysis. In the period before therapy there was a significant deterioration in FVC (in 6 months: -4.3%; p=0.0009) and DLCO (-2.1%; p=0.018). After 6 months of treatment there was a modest improvement in the FVC (+2.7% p=0.08) and DLCO (+2.2%; p=0.08). Pooled analysis. In 53 evaluable patients, the improvement in LFT reached conventional statistical significance (FVC: +2.85%; 95% confidence intervals: +0.04, +5.66%; p=0.04. DLCO: +4.4%; 95% confidence intervals: +1.2%, +7.5%; p<0.001). CONCLUSION: i.v. CYC for 6 months can achieve a small, but significant improvement of LFT in patients with SSc and active alveolitis.

Adult↗
PubMed2005

Integrative analysis of multiple gene expression profiles with quality-adjusted effect size models.

BACKGROUND: With the explosion of microarray studies, an enormous amount of data is being produced. Systematic integration of gene expression data from different sources increases statistical power of detecting differentially expressed genes and allows assessment of heterogeneity. The challenge, however, is in designing and implementing efficient analytic methodologies for combination of data generated by different research groups. RESULTS: We extended traditional effect size models to combine information from different microarray datasets by incorporating a quality measure for each gene in each study into the effect size estimation. We illustrated our method by integrating two datasets generated using different Affymetrix oligonucleotide types. Our results indicate that the proposed quality-adjusted weighting strategy for modelling inter-study variation of gene expression profiles not only increases consistency and decreases heterogeneous results between these two datasets, but also identifies many more differentially expressed genes than methods proposed previously. CONCLUSION: Data integration and synthesis is becoming increasingly important. We live in a high-throughput era where technologies constantly change leaving behind a trail of data with different forms, shapes and sizes. Statistical and computational methodologies are therefore critical for extracting the most out of these related but not identical sources of data.

Algorithms↗