Statistical Power Analysis

Murphy, Kevin R.; Myors, Brett; Wolach, Allen H.

doi:10.4324/9781315773155

Cited by 130 publications

(35 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[12][13][14][15]17,24 However, the methods for comparing skill were not optimal resulting in a lack of power in the significance test and an underestimation of the impact of initialisation. The power of a significance test is defined as the probability that it will correctly detect a real signal, and depends largely on the size of the signal being tested, [40][41][42] referred to as the effect size. Previous studies have assessed simple differences (or ratios) of skill, but this approach does not maximise the effect size when part of the skill is common to both sets of forecasts.…”

Section: Resultsmentioning

confidence: 99%

Robust skill of decadal climate predictions

et al. 2019

View full text Add to dashboard Cite

There is a growing need for skilful predictions of climate up to a decade ahead. Decadal climate predictions show high skill for surface temperature, but confidence in forecasts of precipitation and atmospheric circulation is much lower. Recent advances in seasonal and annual prediction show that the signal-to-noise ratio can be too small in climate models, requiring a very large ensemble to extract the predictable signal. Here, we reassess decadal prediction skill using a much larger ensemble than previously available, and reveal significant skill for precipitation over land and atmospheric circulation, in addition to surface temperature. We further propose a more powerful approach than used previously to evaluate the benefit of initialisation with observations, improving our understanding of the sources of skill. Our results show that decadal climate is more predictable than previously thought and will aid society to prepare for, and adapt to, ongoing climate variability and change.npj Climate and Atmospheric Science (2019)2:13 ; https://doi.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust skill of decadal climate predictions

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Bonferroni adjustments were made for each ANCOVA or MANCOVA but no overall experiment-wise adjustments were made. By convention, partial eta squared effect sizes are interpreted as: .01~small, .06~medium, and .14~large (Murphy & Myors, 2004).…”

Section: Discussionmentioning

confidence: 99%

“…* and † = p < .05 for a given pairwise comparison. By convention, partial eta squared effect sizes are interpreted as: .01~small, .06~medium, and .14~large (Murphy & Myors, 2004). Bonferroni adjustments were made for each ANCOVA or MANCOVA but no overall experiment-wise adjustments were made.…”

Section: Aimmentioning

confidence: 99%

Comparing the Neuropsychological Test Performance of Operation Enduring Freedom/Operation Iraqi Freedom (OEF/OIF) Veterans with and without Blast Exposure, Mild Traumatic Brain Injury, and Posttraumatic Stress Symptoms

Storzbach

O’Neil

Roost

et al. 2015

J Int Neuropsychol Soc

View full text Add to dashboard Cite

To compare neuropsychological test performance of Veterans with and without mild traumatic brain injury (MTBI), blast exposure, and posttraumatic stress disorder (PTSD) symptoms. We compared the neuropsychological test performance of 49 Operation Enduring Freedom/Operation Iraqi Freedom (OEF/OIF) Veterans diagnosed with MTBI resulting from combat blast-exposure to that of 20 blast-exposed OEF/OIF Veterans without history of MTBI, 23 OEF/OIF Veterans with no blast exposure or MTBI history, and 40 matched civilian controls. Comparison of neuropsychological test performance across all four participant groups showed a complex pattern of mixed significant and mostly nonsignificant results, with omnibus tests significant for measures of attention, spatial abilities, and executive function. The most consistent pattern was the absence of significant differences between blast-exposed Veterans with MTBI history and blast-exposed Veterans without MTBI history. When blast-exposed Veteran groups with and without MTBI history were aggregated and compared to non-blast-exposed Veterans, there were significant differences for some measures of learning and memory, spatial abilities, and executive function. However, covariation for severity of PTSD symptoms eliminated all significant omnibus neuropsychological differences between Veteran groups. Our results suggest that, although some mild neurocognitive effects were associated with blast exposure, these neurocognitive effects might be better explained by PTSD symptom severity rather than blast exposure or MTBI history alone.

show abstract

“…To determine the necessary sample size for this study, power analyses for the design were calculated a priori using G * Power 3.1 (Buchner, Erdfelder, & Faul, 1997). Based on Myors & Wolach's (2014) recommended power statistic of 0.80, an analysis of variance (ANOVA) with fixed effects, omnibus, one-way was conducted. Given an effect size of 0.14 (low effect size), alpha level of 0.05, power statistic of .80, seven groups, and three response variables, the study's sample size of 702 possesses sufficient power to determine whether there is a relationship between the independent variable and outcome measures if such a relationship exists and is robust enough to detect.…”

Section: Data Analysesmentioning

confidence: 99%

An Examination of Differences in Moral Disengagement and Empathy Among Bullying Participant Groups

Haddock

Jimerson

2017

J. relat. res.

View full text Add to dashboard Cite

This study examines how different roles in school bullying (e.g., bullies, victims, defenders) vary in cognitive and affective empathy and moral disengagement. Findings from this study revealed that levels of empathy and moral disengagement differed significantly among bullying groups for 702 6th, 7th, and 8th grade students in the United States. An analysis of variance showed differential patterns between bullying groups and outcome variables (i.e., cognitive and affective empathy and moral disengagement). In addition, the correlation between moral disengagement and empathy was statistically significant and negative. Affective empathy and cognitive empathy both significantly predicted moral disengagement; with every one unit increase in moral disengagement, affective empathy decreased by .38 and cognitive empathy decreased by .39. Students who scored higher in moral disengagement tended to score lower in empathy. The current findings confirm and extend the literature on the relation between moral disengagement, empathy, prosociality, and victimising behaviour. This information can inform school-wide and targeted intervention efforts.

show abstract

Statistical Power Analysis

Cited by 130 publications

References 0 publications

Robust skill of decadal climate predictions

Robust skill of decadal climate predictions

Comparing the Neuropsychological Test Performance of Operation Enduring Freedom/Operation Iraqi Freedom (OEF/OIF) Veterans with and without Blast Exposure, Mild Traumatic Brain Injury, and Posttraumatic Stress Symptoms

An Examination of Differences in Moral Disengagement and Empathy Among Bullying Participant Groups

Contact Info

Product

Resources

About