Accuracy in parameter estimation for ANCOVA and ANOVA contrasts: Sample size planning via narrow confidence intervals

Lai, Keke; Kelley, Ken

doi:10.1111/j.2044-8317.2011.02029.x

Cited by 27 publications

(20 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Alternative approaches to power calculations are available to researchers and may often provide more intuitive options for sample size estimation. These include processes to optimize the precision of an effect size (Lai & Kelley, 2012; Maxwell, Kelley, & Rausch, 2008), and approaches for non‐superiority hypotheses (Lakens, 2017). However, given that the vast majority of researchers in the field estimate sample size via power calculations, we shall consider this approach in the example.…”

Section: Discussion and Practical Recommendationsmentioning

confidence: 99%

Myths and methodologies: Reliability of non‐invasive estimates of cardiac autonomic modulation during whole‐body passive heating

Akerman

Meade

Notley

et al. 2020

Experimental Physiology

View full text Add to dashboard Cite

Observed individual variability in cardiac baroreflex sensitivity (cBRS) and heart rate variability (HRV) is extensive, especially during exposure to stressors such as heat. A large part of the observed variation may be related to the reliability (consistency) of the measurement. We therefore examined the test–retest reliability of cBRS and HRV measurements on three separate occasions in 14 young men (age: 24 (SD 5) years), at rest and during whole‐body heating (water‐perfused suit) to raise and clamp oesophageal temperature 0.6°C, 1.2°C and 1.8°C above baseline. Beat‐to‐beat measurements of RR interval and systolic blood pressure (BP) were obtained for deriving HRV (from RR), and cBRS calculated via (i) the spontaneous method, α coefficients and transfer function analysis at each level of heat strain, and (ii) during forced oscillations via squat–stand manoeuvres (0.1 Hz) before and after heating. Absolute values and changes in all cBRS estimates were variable but generally consistent with reductions in parasympathetic activity. cBRS estimates demonstrated poor absolute reliability (coefficient of variation ≥25%), but relative reliability (intraclass correlation coefficient; ICC) of some frequency estimates was acceptable (ICC ≥0.70) during low‐heat strain (ICC: 0.56–0.74). After heating, forced oscillations in BP demonstrated more favourable responses than spontaneous oscillations (better reliability, lower minimum detectable change). Absolute reliability of HRV estimates were poor, but relative reliability estimates were often acceptable (≥0.70). Our findings illustrate how measurement consistency of cardiac autonomic modulation estimates are altered during heat stress, and we demonstrate the possible implications on research design and data interpretation.

show abstract

Section: Discussion and Practical Recommendationsmentioning

confidence: 99%

Myths and methodologies: Reliability of non‐invasive estimates of cardiac autonomic modulation during whole‐body passive heating

Akerman

Meade

Notley

et al. 2020

Experimental Physiology

View full text Add to dashboard Cite

show abstract

“…ANCOVA was also used to estimate treatment differences in the probability of repeating a choice after a reward (win-stay) or changing a choice after a loss (lose-shift) during the PL task. The procedures outlined by Lai and Kelley (in press) were used to calculate treatment effect size estimates and corresponding 95% confidence intervals (CI).…”

Section: Methodsmentioning

confidence: 99%

Rimonabant for neurocognition in schizophrenia: A 16-week double blind randomized placebo controlled trial

Boggs

Kelly

McMahon

et al. 2012

Schizophrenia Research

View full text Add to dashboard Cite

Objective To examine the effect of rimonabant on neurocognitive impairments in people with schizophrenia. Methods Participants entered a 16-week double-blind, placebo-controlled, randomized clinical trial. A neurocognitive battery was administered at baseline and end of study. Results In comparison to rimonabant (20mg/day), placebo-treated participants exhibited a significant improvement on the Repeatable Battery for the Assessment of Neuropsychological Status total score. In contrast, rimonabant was associated with significant improvement on a probabilistic learning task. There were no other significant treatment effects. Conclusions Rimonabant did not improve global cognitive functioning, but did improve a specific learning deficit based on response to positive feedback.

show abstract

“…The required sample size to estimate a proportion can be computed with Accuracy In Parameter Estimation (AIPE) procedures (e.g., Cumming, 2014;Kelley & Rausch, 2006;Lai & Kelley, 2012). For example, in R-software by using the 'ufs' (Peters, 2020b) or 'MBESS' (Kelley, 2020) package.…”

Section: Step 2: Estimating the Control Event Rate Corresponding To Amentioning

confidence: 99%

Meaningful change definitions: sample size planning for experimental intervention research

Gruijters

Peters

2020

Psychology & Health

View full text Add to dashboard Cite

Experimental tests of interventions need to have sufficient sample size to constitute a robust test of the intervention's effectiveness with reasonable precision and power. To estimate the required sample size adequately, researchers are required to specify an effect size. But what effect size should be used to plan the required sample size? Various inroads into selecting the a priori effect size have been suggested in the literature-including using conventions, prior research, and theoretical or practical importance. In this paper, we first discuss problems with some of the proposed methods of selecting the effect size for study planning. We then lay out a method for intervention researchers that provides a way out of many of these problems. The proposed method requires setting a meaningful change definition, it is specifically suited for applied researchers interested in planning tests of intervention effectiveness. We provide a hands-on walk through of the method and provide easy-to-use R functions to implement it.

show abstract

Accuracy in parameter estimation for ANCOVA and ANOVA contrasts: Sample size planning via narrow confidence intervals

Cited by 27 publications

References 58 publications

Myths and methodologies: Reliability of non‐invasive estimates of cardiac autonomic modulation during whole‐body passive heating

Myths and methodologies: Reliability of non‐invasive estimates of cardiac autonomic modulation during whole‐body passive heating

Rimonabant for neurocognition in schizophrenia: A 16-week double blind randomized placebo controlled trial

Meaningful change definitions: sample size planning for experimental intervention research

Contact Info

Product

Resources

About