Estimating Standardized Effect Sizes for Two- and Three-Level Partially Nested Data

2016 ◽  
pp. 1-17 ◽  
Author(s):  
Mark H. C. Lai ◽  
Oi-man Kwok
Keyword(s):  
Effect Sizes ◽  
Nested Data ◽  
Standardized Effect Sizes

scholarly journals A randomized controlled trial testing the efficacy of a Nurse Home Visiting Program for Pregnant Adolescents

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Daniel Fatori ◽  
Pedro Fonseca Zuccolo ◽  
Elizabeth Shephard ◽  
Helena Brentani ◽  
Alicia Matijasevich ◽  
...  
Keyword(s):  
Child Development ◽  
Home Environment ◽  
Adolescent Mothers ◽  
Home Visiting ◽  
Controlled Trial ◽  
Effect Sizes ◽  
Randomized Controlled ◽  
Nurse Home Visiting ◽  
Standardized Effect Sizes ◽  
Home Visiting Program

AbstractTo test the efficacy of a nurse home visiting program (HVP) on child development, maternal and environmental outcomes in the first years of life. We conducted a randomized controlled trial to test the efficacy of Primeiros Laços, a nurse HVP for adolescent mothers living in a poor urban area of São Paulo, Brazil. Eighty adolescent mothers were included and randomized to receive either Primeiros Laços (intervention group, n = 40) or healthcare as usual (control group, n = 40). Primeiros Laços is a home visiting intervention delivered by trained nurses that starts during the first 16 weeks of pregnancy and continues to the child’s age of 24 months. Participants were assessed by blind interviewers at 8–16 weeks of pregnancy (baseline), 30 weeks of pregnancy, and 3, 6, 12, and 24 months of child’s age. We assessed oscillatory power in the mid-range alpha frequency via electroencephalography when the children were aged 6 months. Child development was measured by the Bayley Scales of Infant Development Third Edition (BSID-III). Weight and length were measured by trained professionals and anthropometric indexes were calculated. The home environment and maternal interaction with the child was measured by the Home Observation and Measurement of the Environment. Generalized estimating equation models were used to examine intervention effects on the trajectories of outcomes. Standardized effect sizes (Cohen’s d) were calculated using marginal means from endpoint assessments of all outcomes. The trial was registered at clinicaltrial.gov: NCT02807818. Our analyses showed significant positive effects of the intervention on child expressive language development (coefficient = 0.89, 95% CI [0.18, 1.61], p = 0.014), maternal emotional/verbal responsivity (coefficient = 0.97, 95% CI [0.37, 1.58], p = 0.002), and opportunities for variety in daily stimulation (coefficient = 0.37, 95% CI [0.09, 0.66], p = 0.009). Standardized effect sizes of the intervention were small to moderate. Primeiros Laços is a promising intervention to promote child development and to improve the home environment of low-income adolescent mothers. However, considering the limitations of our study, future studies should be conducted to assess Primeiros Laços potential to benefit this population.Clinical Trial Registration: The study was registered at clinicaltrial.gov (Registration date: 21/06/2016 and Registration number: NCT02807818).

Confidence Intervals

2009 ◽  
Vol 217 (1) ◽  
pp. 15-26 ◽  
Author(s):  
Geoff Cumming ◽  
Fiona Fidler
Keyword(s):  
Confidence Interval ◽  
Confidence Intervals ◽  
Null Hypothesis ◽  
Prediction Intervals ◽  
Effect Sizes ◽  
Significance Testing ◽  
Null Hypothesis Significance Testing ◽  
P Values ◽  
Standardized Effect Sizes ◽  
Mainstream Science

Most questions across science call for quantitative answers, ideally, a single best estimate plus information about the precision of that estimate. A confidence interval (CI) expresses both efficiently. Early experimental psychologists sought quantitative answers, but for the last half century psychology has been dominated by the nonquantitative, dichotomous thinking of null hypothesis significance testing (NHST). The authors argue that psychology should rejoin mainstream science by asking better questions – those that demand quantitative answers – and using CIs to answer them. They explain CIs and a range of ways to think about them and use them to interpret data, especially by considering CIs as prediction intervals, which provide information about replication. They explain how to calculate CIs on means, proportions, correlations, and standardized effect sizes, and illustrate symmetric and asymmetric CIs. They also argue that information provided by CIs is more useful than that provided by p values, or by values of Killeen’s prep, the probability of replication.

scholarly journals Reexamining the effect of gustatory disgust on moral judgment: A multi-lab direct replication of Eskine, Kacinik, and Prinz (2011)

2018 ◽  
Author(s):  
Eric Ghelfi ◽  
Cody D Christopherson ◽  
Heather L. Urry ◽  
Richie L Lenne ◽  
Nicole Legate ◽  
...  
Keyword(s):  
Large Scale ◽  
Bayes Factor ◽  
Mixed Effects ◽  
Original Study ◽  
Taste Perception ◽  
Effect Sizes ◽  
Linear Mixed Effects ◽  
Standardized Effect Sizes ◽  
Meta Analyses ◽  
Moral Wrongness

Eskine, Kacinik, and Prinz’s (2011) influential experiment demonstrated that gustatory disgust triggers a heightened sense of moral wrongness. We report a large-scale multi-site direct replication of this study conducted by participants in the Collaborative Replications and Education Project. Participants in each sample were randomly assigned to one of three beverage conditions: bitter/disgusting, control, or sweet. Then, participants made a series of judgments indicating the moral wrongness of the behavior depicted in each of six vignettes. In the original study (N = 57), drinking the bitter beverage led to higher ratings of moral wrongness than drinking the control and sweet beverages; a beverage contrast was significant among conservative (N = 19) but not liberal (N = 25) participants. In this report, random effects meta-analyses across all participants (N = 1,137 in k = 11 studies), conservative participants (N = 142, k = 5), and liberal participants (N = 635, k = 9) revealed standardized effect sizes that were smaller than reported in the original study. Some were in the opposite of the predicted direction, all had 95% confidence intervals containing zero, and most were smaller than the effect size the original authors could meaningfully detect. In linear mixed-effects regressions, drinking the bitter beverage led to higher ratings of moral wrongness than drinking the control beverage but not the sweet beverage. Bayes Factor tests reveal greater relative support for the null hypothesis. The overall pattern provides little to no support for the theory that physical disgust via taste perception harshens judgments of moral wrongness.

scholarly journals Research practices and statistical reporting quality in 250 economic psychology master's theses: a meta-research investigation

2019 ◽  
Vol 6 (12) ◽  
pp. 190738 ◽  
Author(s):  
Jerome Olsen ◽  
Johanna Mosen ◽  
Martin Voracek ◽  
Erich Kirchler
Keyword(s):  
Statistical Power ◽  
Testing Effect ◽  
Reporting Quality ◽  
Open Science ◽  
Sample Size Determination ◽  
Effect Sizes ◽  
Research Practices ◽  
Questionable Research Practices ◽  
Standardized Effect Sizes ◽  
Research Findings

The replicability of research findings has recently been disputed across multiple scientific disciplines. In constructive reaction, the research culture in psychology is facing fundamental changes, but investigations of research practices that led to these improvements have almost exclusively focused on academic researchers. By contrast, we investigated the statistical reporting quality and selected indicators of questionable research practices (QRPs) in psychology students' master's theses. In a total of 250 theses, we investigated utilization and magnitude of standardized effect sizes, along with statistical power, the consistency and completeness of reported results, and possible indications of p -hacking and further testing. Effect sizes were reported for 36% of focal tests (median r = 0.19), and only a single formal power analysis was reported for sample size determination (median observed power 1 − β = 0.67). Statcheck revealed inconsistent p -values in 18% of cases, while 2% led to decision errors. There were no clear indications of p -hacking or further testing. We discuss our findings in the light of promoting open science standards in teaching and student supervision.

Sign in / Sign up

Export Citation Format

Share Document