PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 1100133

Analysis of data from multiclinic experiments.

S R Chakravorti·J E Grizzle
View original source ↗Export metadata ↓

Abstract

The analysis of data from multiclinic experiments is put in the framework of a mixed model in which the treatment effects are assumed to be fixed, and clinic and clinic by treatment effects are assumed to be random. The analysis in the unbalanced case is developed under the usual mixed model assumptions. The maximum likelihood estimates and likelihood ratio tests of the parameters are derived following the approach of Hemmerle and Hartley (1973). The T2 test is shown to be asymptotically equivalent to the analysis of variance F test in the balanced case. The distribution of the test statistic in the case of proportional cell frequencies is also discussed. Some investigation is made of the distribution of the test statistic by applying the method of Box (1954).

Explore related subjects

Blood Pressure DeterminationClinical Trials as TopicEvaluation Studies as TopicHumansModels, TheoreticalStatistics as TopicTherapeuticsClinical TrialJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

S R Chakravorti, J E Grizzle. 1975. Analysis of data from multiclinic experiments.. https://pubmed.ncbi.nlm.nih.gov/1100133/

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

KEEP EXPLORING

Related citations

PubMed1992

Decision to treat mild hypertension after assessment by ambulatory monitoring and World Health Organisation recommendations.

OBJECTIVE: To determine if one ambulatory blood pressure recording over 12 hours could detect those patients with mild hypertension who needed treatment according to the World Health Organisation-International Society of Hypertension (ISH) guidelines based on the causal measurement of diastolic blood pressure at successive visits to a clinic. DESIGN: Comparison of decision to treat based on one ambulatory measurement over 12 hours and standard blood pressure measurements over six months in the same patients. SETTING: Outpatient hypertension clinic. SUBJECTS: 130 men and women with diastolic blood pressure of 90-104 mm Hg at second visit to clinic. MAIN OUTCOME MEASURES: Blood pressure measurements over six months. Measurement from ambulatory monitoring. Decision to treat. RESULTS: Of the 130 patients included, 108 were followed up over the six months. Treatment was started according to WHO-ISH criteria in 44 (13 at the third visit, 13 at the fourth, 18 at the fifth). According to the selected criteria for ambulatory blood pressure monitoring 41 patients would have been treated. Both methods agreed that the same 27 patients required treatment and the same 50 did not, but they did not agree in 31 patients. When calculated at the optimal diastolic blood pressure threshold determined by a receiver operating characteristic curve, the sensitivity, specificity, and positive predictive value of ambulatory blood pressure monitoring were 71% (95% confidence interval 57% to 84%), 82% (72% to 92%), and 66% (51% to 81%), respectively. CONCLUSION: If the WHO-ISH criteria are accepted as the standard for deciding to treat patients with mild hypertension the predictive value of one ambulatory blood pressure recording over 12 hours is too low to detect with confidence those patients who need treatment when managed according to these criteria.

Blood Pressure Determination↗