Normal view MARC view ISBD view

Power analysis of trials with multilevel data

By: Moerbeek, Mirjam.
Contributor(s): Teerenstra, Steven.
Material type: materialTypeLabelBookSeries: Chapman & Hall/CRC Interdisciplinary Statistics Series. Publisher: Boca Raton CRC Press 2016Description: xix, 268 p.ISBN: 9781498729895.Subject(s): Mathematical statistics | Statistics - MethodologyDDC classification: 519.5 Summary: Power Analysis of Trials with Multilevel Data covers using power and sample size calculations to design trials that involve nested data structures. The book gives a thorough overview of power analysis that details terminology and notation, outlines key concepts of statistical power and power analysis, and explains why they are necessary in trial design. It guides you in performing power calculations with hierarchical data, which enables more effective trial design. The authors are leading experts in the field who recognize that power analysis has attracted attention from applied statisticians in social, behavioral, medical, and health science. Their book supplies formulae that allow statisticians and researchers in these fields to perform calculations that enable them to plan cost-efficient trials. The formulae can also be applied to other sciences. Using power analysis in trial design is increasingly important in a scientific community where experimentation is often expensive, competition for funding among researchers is intense, and agencies that finance research require proposals to give thorough justification for funding. This handbook shows how power analysis shapes trial designs that have high statistical power and low cost, using real-life examples. The book covers multiple types of trials, including cluster randomized trials, multisite trials, individually randomized group treatment trials, and longitudinal intervention studies. It also offers insight on choosing which trial is best suited to a given project. Power Analysis of Trials with Multilevel Data helps you craft an optimal research design and anticipate the necessary sample size of data to collect to give your research maximum effectiveness and efficiency. (https://www.crcpress.com/Power-Analysis-of-Trials-with-Multilevel-Data/Moerbeek-Teerenstra/p/book/9781498729895)
Tags from this library: No tags from this library for this title. Log in to add tags.
    average rating: 0.0 (0 votes)
Item type Current location Item location Collection Call number Status Date due Barcode
Books Vikram Sarabhai Library
Slot 1415 (0 Floor, East Wing) Non-fiction 519.5 M6P6 (Browse shelf) Available 192567

Table of Contents:

1.Introduction

1.1.Experimentation
1.1.1.Problems with random assignment
1.2.Hierarchical data structures
1.3.Research design
1.3.1.Cluster randomized trial
1.3.2.Multisite trial
1.3.3.Pseudo cluster randomized trial
1.3.4.Individually randomized group treatment trial
1.3.5.Longitudinal intervention study
1.3.6.Some guidance to design choice
1.4.Power analysis for experimental research
1.5.Aim and contents of the book
1.5.1.Aim
1.5.2.Contents

2.Multilevel statistical models

2.1.The basic two-level model
2.2.Estimation and hypothesis test
2.3.Intraclass correlation coefficient
2.4.Multilevel models for dichotomous outcomes
2.5.More than two levels of nesting
2.6.Software for multilevel analysis

3.Concepts of statistical power analysis

3.1.Background of power analysis
3.1.1.Hypotheses testing
3.1.2.Power calculations for continuous outcomes
3.1.3.Power calculations for dichotomous outcomes
3.1.3.1.Risk difference
3.1.3.2.Odds ratio
3.2.Types of power analysis
3.3.Timing of power analysis
3.4.Methods for power analysis
3.5.Robustness of power and sample size calculations
3.6.Procedure for a priori power analysis
3.6.1.An example
3.7.The optimal design of experiments
3.7.1.An example (continued)
3.8.Sample size and precision analysis
3.9.Sample size and accuracy of parameter estimates

4.Cluster randomized trials

4.1.Introduction
4.2.Multilevel model
4.3.Sample size calculations for continuous outcomes
4.3.1.Factors that influence power
4.3.2.Design effect
4.3.3.Sample size formulae for fixed cluster size or fixed number of clusters
4.3.4.Including budgetary constraints
4.4.Sample size calculations for dichotomous outcomes
4.4.1.Risk difference
4.4.2.Odds ratio
4.5.An example

5.Improving statistical power in cluster randomized trials

5.1.Inclusion of covariates
5.2.Minimization, matching, pre-stratification
5.3.Taking repeated measurements
5.4.Crossover in cluster randomized trials
5.5.Stepped wedge designs

6.Multisite trials

6.1.Introduction
6.2.Multilevel model
6.3.Sample size calculations for continuous outcomes
6.3.1.Factors that influence power
6.3.2.Design effect
6.3.3.Sample size formulae for fixed cluster size or fixed number of clusters
6.3.4.Including budgetary constraints
6.3.5.Constant treatment effect
6.4.Sample size calculations for dichotomous outcomes
6.4.1.Odds ratio
6.5.An example

7.Pseudo cluster randomized trials

7.1.Introduction
7.2.Multilevel model
7.3.Sample size calculations for continuous outcomes
7.3.1.Factors that influence power
7.3.2.Design effect
7.3.3.Sample size formulae for fixed cluster size or fixed number of clusters
7.4.Sample size calculations for binary outcomes
7.5.An example

8.Individually randomized group treatment trials

8.1.Introduction
8.2.Multilevel model
8.2.1.Clustering in both treatment arms
8.2.2.Clustering in one treatment arm
8.3.Sample size calculations for continuous outcomes
8.3.1.Clustering in both treatment arms
8.3.1.1.Factors that influence power
8.3.1.2.Sample size formulae for fixed cluster sizes
8.3.1.3.Including budgetary constraints
8.3.2.Clustering in one treatment arm
8.3.2.1.Factors that influence power
8.3.2.2.Sample size formulae for fixed cluster sizes
8.3.2.3.Including budgetary constraints
8.4.Sample size calculations for dichotomous outcomes
8.4.1.Clustering in both treatment arms
8.4.2.Clustering in one treatment arm
8.5.An example

9.Longitudinal intervention studies

9.1.Introduction
9.2.Multilevel model
9.3.Sample size calculations for continuous outcomes
9.3.1.Factors that influence power
9.3.2.Sample size formula for fixed number of measurements
9.3.3.Including budgetary constraints
9.4.Sample size calculations for dichotomous outcomes
9.4.1.Odds ratio
9.5.The effect of drop-out on statistical power
9.5.1.The effects of different drop-out patterns
9.5.2.Including budgetary constraints
9.6.An example

10.Extensions: three levels of nesting and factorial designs

10.1.Introduction
10.2.Three-level cluster randomized trials
10.3.Multisite cluster randomized trials
10.4.Repeated measures in cluster randomized trials and multisite trials
10.5.Factorial designs
10.5.1.Continuous outcome
10.5.2.Binary outcome
10.5.3.Sample size calculation for factorial designs

11.The problem of unknown intraclass correlation coefficients

11.1.Estimates from previous research
11.2.Sample size re-estimation
11.3.Bayesian sample size calculation
11.4.Maximin optimal designs

12.Computer software for power calculations

12.1.Introduction
12.2.Computer program SPA-ML.

Power Analysis of Trials with Multilevel Data covers using power and sample size calculations to design trials that involve nested data structures. The book gives a thorough overview of power analysis that details terminology and notation, outlines key concepts of statistical power and power analysis, and explains why they are necessary in trial design. It guides you in performing power calculations with hierarchical data, which enables more effective trial design.

The authors are leading experts in the field who recognize that power analysis has attracted attention from applied statisticians in social, behavioral, medical, and health science. Their book supplies formulae that allow statisticians and researchers in these fields to perform calculations that enable them to plan cost-efficient trials. The formulae can also be applied to other sciences.

Using power analysis in trial design is increasingly important in a scientific community where experimentation is often expensive, competition for funding among researchers is intense, and agencies that finance research require proposals to give thorough justification for funding. This handbook shows how power analysis shapes trial designs that have high statistical power and low cost, using real-life examples.

The book covers multiple types of trials, including cluster randomized trials, multisite trials, individually randomized group treatment trials, and longitudinal intervention studies. It also offers insight on choosing which trial is best suited to a given project. Power Analysis of Trials with Multilevel Data helps you craft an optimal research design and anticipate the necessary sample size of data to collect to give your research maximum effectiveness and efficiency.

(https://www.crcpress.com/Power-Analysis-of-Trials-with-Multilevel-Data/Moerbeek-Teerenstra/p/book/9781498729895)

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha