PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 7858004

Data analysis for repeated measures studies.

M L Ellett
View original source ↗Export metadata ↓

Abstract

Many research questions in nursing can best be answered by designing studies using repeated measures representing pretreatment and posttreatment observations on the same subject. In this article, the author discusses both a parametric statistical test and its nonparametric counterpart and provides guidance regarding when it is appropriate to use each. The steps used in computing both statistics are also provided.

Explore related subjects

Chi-Square DistributionData Interpretation, StatisticalHumansNursing ResearchResearch DesignStatistics, NonparametricComparative StudyJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

M L Ellett. Data analysis for repeated measures studies.. https://doi.org/10.1097/00001610-199411000-00006

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1997

Confidence intervals for directly standardized rates: a method based on the gamma distribution.

We offer an approximation to central confidence intervals for directly standardized rates, where we assume that the rates are distributed as a weighted sum of independent Poisson random variables. Like a recent method proposed by Dobson, Kuulasmaa, Eberle and Scherer, our method gives exact intervals whenever the standard population is proportional to the study population. In cases where the two populations differ non-proportionally, we show through simulation that our method is conservative while other methods (the Dobson et al. method and the approximate bootstrap confidence method) can be liberal.

Chi-Square Distribution↗
PubMed1997

Assessment of viable myocardium and prediction of postoperative improvement in left ventricular function in patients with severe left ventricular dysfunction by quantitative planar stress-redistribution-reinjection 201-T1 imaging.

A noninvasive approach to determine viable but asynergic myocardium will be clinically significant in identifying patients with coronary artery disease and severe left ventricular dysfunction who will benefit most from coronary bypass surgery. Accordingly, 12 patients (mean ejection fraction 0.32 +/- 0.03) underwent quantitative planar stress-redistribution-reinjection thallium scintigraphy and radionuclide ventriculography before and 8 weeks after revascularization for viability and segmental and global left ventricular function assessment, respectively. Reinjection scan showed new fill-in in 63% of segments without redistribution. Postoperative improvement in perfusion and function of asynergic segments were significantly better in viable compared to nonviable segments (P < 0.001, P < 0.01, respectively) with a strong correlation between improvement in 201-T1 uptake and function (P < 0.001). When adequacy of revascularization was considered, the predictive value of a positive preoperative viability test for functional improvement was 83%. Finally, mean ejection fraction and global wall motion score increased significantly after revascularization for the group as a whole (0.32 +/- 0.03 to 0.44 +/- 0.04, P < 0.001 and 24.08 +/- 2.90 to 33.16 +/- 3.32, P < 0.001, respectively). Thus, preoperative quantitative planar stress-redistribution-reinjection thallium imaging detects viable but asynergic segments which improve function postoperatively and may be valuable in selection of patients with severe left ventricular dysfunction for revascularization.

Chi-Square Distribution↗
PubMed1997

Transitivity and emergent sequence performances in young children.

Children taught to sequence pairs of visual stimuli also performed additional sequences without direct training. In Experiment 1, the children were trained to produce a six-stimulus sequence (A > B > C > D > E > F) with one set of forms, and five overlapping two-stimulus sequences (A > B, B > C, C > D, D > E, and E > F) with another set of forms. Few of the children succeeded on tests for the untrained two- (e.g., B > D and B > E) and six-stimulus sequences derivable from the two-stimulus training. The children in Experiments 2 and 3 received only the overlapping sequence training before testing with refined protocols: Nearly all succeeded on tests of emergent sequences involving two, three, four, five, and six stimuli. The results suggest methods for examining transitive relations between pairs of the stimuli used in training and the development of a relation of order among all six of the stimuli involved.

Chi-Square Distribution↗