Variance imputation for overviews of clinical trials with continuous response

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Overviews of clinical trials are an efficient and important means of summarizing information about a particular scientific area. When the outcome is a continuous variable, both treatment effect and variance estimates are required to construct a confidence interval for the overall treatment effect. Often, only partial information about the variance is provided in the publication of the clinical trial. This paper provides heuristic suggestions for variance imputation based on partial variance information. Both pretest-posttest (parallel groups) and crossover designs are considered. A key idea is to use separate sources of incomplete information to help choose a better variance estimate. The imputation suggestions are illustrated with a data set.

Related collections

Most cited references 3

Record: found
Abstract: found
Article: not found

By how much does dietary salt reduction lower blood pressure? I--Analysis of observational data among populations.

David N Wald, Catherine M Law, Paul Frost (1991)

To estimate the quantitative relation between blood pressure and sodium intake. Data were analysed from published reports of blood pressure and sodium intake for 24 different communities (47 000 people) throughout the world. Difference in blood pressure for a 100 mmol/24 h difference in sodium intake. Allowance was made for differences in blood pressure between economically developed and undeveloped communities to minimise overestimation of the association through confounding with other determinants of blood pressure. Blood pressure was higher on average in the developed communities, but the association with sodium intake was similar in both types of community. A difference in sodium intake of 100 mmol/24 h was associated with an average difference in systolic blood pressure that ranged from 5 mm Hg at age 15-19 years to 10 mm Hg at age 60-69. The differences in diastolic blood pressure were about half as great. The standard deviation of blood pressure increased with sodium intake implying that the association of blood pressure with sodium intake in individuals was related to the initial blood pressure--the higher the blood pressure the greater the expected reduction in blood pressure for the same reduction in sodium intake. For example, at age 60-69 the estimated systolic blood pressure reduction in response to a 100 mmol/24 h reduction in sodium intake was on average 10 mm Hg but varied from 6 mm Hg for those on the fifth blood pressure centile to 15 mm Hg for those on the 95th centile. The association of blood pressure with sodium intake is substantially larger than is generally appreciated and increases with age and initial blood pressure.

0 comments Cited 42 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

An overview of randomized trials of sodium reduction and blood pressure.

J Cutler, D. Follmann, P Elliott … (1991)

0 comments Cited 12 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Calcium and blood pressure. An epidemiologic perspective.

Adrian Cutler, E Brittain (1990)

We reviewed the research literature on the epidemiologic relationship between blood pressure levels and calcium, with an emphasis on dietary intake. A conceptual framework for causal inference is summarized; then the designs and results of observational and intervention studies are presented. Of 25 reports of observational studies relating intake of calcium or calcium-rich foods to blood pressure, the majority found some evidence of an inverse association. However, many analyses did not support this relationship, and only two studies have confirmed the inverse association with a prospective design. Nineteen randomized controlled clinical trials of calcium supplementation have been reported, excluding those exclusively in pregnant women. Eleven of these showed no significant effects on blood pressure; in two trials, both systolic and diastolic pressure were significantly reduced; and in the remainder results were equivocal. Pooled analyses yielded estimates of a small (1.8 mm Hg), significant reduction in systolic blood pressure, but no effect on diastolic pressure. Epidemiologic relationships with serum and urinary calcium, and the possible mechanisms of these effects, are also discussed. We conclude that the evidence from studies in humans is suggestive, but not conclusive, regarding a role for calcium in hypertension. Recommendations for further epidemiologic studies are presented.