The Difference Between Hake’s Normalized Gain g and Effect Size Cohen’s d for Measuring the Improvement of Student’s Scientific Literacy

2019 ◽  
Author(s):  
Adib Rifqi Setiawan
Keyword(s):  
Student Learning ◽  
Effect Size ◽  
Scientific Literacy ◽  
Cohen’S D ◽  
The Difference ◽  
Cohen's D ◽  
Normalized Gain

This work investigate the implications on claims about student learning that result from choosing between one of two metrics: Hake’s normalized gain g and effect size Cohen’s d, that is based exclusively on the preexist data about scientific literacy on physics and biology across Indonesia.

The Difference Between Hake’s Normalized Gain g and Effect Size Cohen’s d for Measuring the Improvement of Students’ Scientific Literacy

2019 ◽  
Author(s):  
Adib Rifqi Setiawan
Keyword(s):  
Student Learning ◽  
Effect Size ◽  
Scientific Literacy ◽  
Cohen’S D ◽  
The Difference ◽  
Cohen's D ◽  
Normalized Gain

This work investigate the implications on claims about student learning that result from choosing between one of two metrics: Hake’s normalized gain g and effect size Cohen’s d, that is based exclusively on the preexist data about scientific literacy on physics and biology across Indonesia.

The Difference Between Normalized Gain g and Effect Size Cohen’s d for Measuring the Improvement of Student’s Scientific Literacy

2019 ◽  
Author(s):  
Adib Rifqi Setiawan
Keyword(s):  
Education Research ◽  
Student Learning ◽  
Effect Size ◽  
Physics Education ◽  
Scientific Literacy ◽  
Biology Education ◽  
Cohen’S D ◽  
The Difference ◽  
Cohen's D ◽  
Normalized Gain

As an undergraduate from Physics Education, I began teaching of Biology at the secondary school on 22 July 2018 until 30 June 2019 when I acceded to come back at primary school, both Islamic Madrasah. Teaching at the Islamic Madrasah is a hassle because I should consider my perspective on Islam in teaching. However, teaching at the Islamic Madrasah is not and should not be considered a burden or chore that just needs to be done. It is a crucial part of moslem scholar, as we all want to do scientifically sound research and we should all strive to be effective teachers. Through teaching, we are responsible for the education of the next generation of islamic peoples, who will use their own unique ideas and skill sets to advance their society. Teaching, in general, should not be seen as a hassle in scholar, but rather as a skill to be developed and a responsibility to be taken seriously. Teaching does not have to decrease research productivity, it can greatly enhance research if we allow it to. One of my evidence about this statement is my experience and work. After a year devoted to spruce up the teaching of Biology, I produced a series of work on scientific literacy related Biology, that continues my undergraduate thesis, which was related Physics. In these works, I wrote about my experiences teaching Biology in Islamic Madrasah. Then, I became think to reconsider my method on measuring student learning. Measuring student learning is a complicated but necessary task for understanding the student’s improvement and effectiveness of instruction. I have curious about the the difference between normalized gain g and effect size Cohen’s d for measuring the improvement of student’s scientific literacy. I used normalized gain g in my undergraduate thesis nor my first work on Biology Education, then used effect size Cohen’s d on my latest work on scientific literacy in teaching of Biology. I see need reasons for using one or both of them, to be explained in any writings on educational research. So, in this work I investigate about my curiousity. My investigation focused on the implications on claims about student learning that result from choosing between one of two metrics. The metrics are normalized gain g, which is the most common method used in Physics Education Research (PER), and effect size Cohen’s d, which is broadly used in Discipline-Based Education Research (DBER) including Biology Education Research (BER). Data for the analyses came from the research about scientific literacy on Physics and Biology Education from courses at institutions across Indonesia. The results showed that the two metrics lead to different inferences about student learning. First, normalized gain g being biased in favor of populations with higher pretest means. Second, effect size Cohen’s d may mitigate the limitations of these metric for measuring the learning of high or low pretest populations of students by accounting for the distribution of tests scores. Third, by comparing the two metrics across all data, effect size Cohen’s d is larger than normalized gain g in these cases for the same size change in the means. This work reveals that the bias in normalized gaing can harm efforts to improve student’s scientific literacy by misrepresenting the efficacy of teaching practices across populations of students and across institutions. This work, also, recommends use effect size Cohen’s d for measuring student learning, based on reliability statistical method for calculating student learning. In addition, using effect size Cohen’s d would allow scholars to use their work in subsequent studies and meta-analyses, align with the practices of the larger education research community, nor facilitating more cross-disciplinary conversations and collaborations as well.

The Difference Between Hake’s Normalized Gain g and Effect Size Cohen’s d for Measuring the Improvement of Student’s Scientific Literacy

2019 ◽  
Author(s):  
Adib Rifqi Setiawan
Keyword(s):  
Student Learning ◽  
Effect Size ◽  
Scientific Literacy ◽  
Cohen’S D ◽  
The Difference ◽  
Cohen's D ◽  
Normalized Gain

This work investigate the implications on claims about student learning that result from choosing between one of two metrics: Hake’s normalized gain g and effect size Cohen’s d, that is based exclusively on the preexist data about scientific literacy on physics and biology across Indonesia.

Comparing Normalized Gain g and Effect Size Cohen’s d to Measure the Improvement of Student’s Scientific Literacy

2019 ◽  
Author(s):  
Adib Rifqi Setiawan
Keyword(s):  
Education Research ◽  
Student Learning ◽  
Effect Size ◽  
Physics Education ◽  
Scientific Literacy ◽  
Biology Education ◽  
Physics Education Research ◽  
Cohen’S D ◽  
Cohen's D ◽  
Normalized Gain

In this work I investigate about my curiousity. My investigation focused on the implications on claims about student learning that result from choosing between one of two metrics. The metrics are normalized gain g, which is the most common method used in Physics Education Research (PER), and effect size Cohen’s d, which is broadly used in Discipline-Based Education Research (DBER) including Biology Education Research (BER). Data for the analyses came from the research about scientific literacy on Physics and Biology Education from courses at institutions across Indonesia. This work reveals that the bias in normalized gaing can harm efforts to improve student’s scientific literacy by misrepresenting the efficacy of teaching practices across populations of students and across institutions. This work, also, recommends use effect size Cohen’s d for measuring student learning, based on reliability statistical method for calculating student learning.

The Profile of Students’ Competencies in Biology Learning–Scientific Literacy Oriented

2019 ◽  
Author(s):  
Syarofis Si'ayah ◽  
Adib Rifqi Setiawan ◽  
Wahyu Eka Saputri ◽  
Matahari
Keyword(s):  
Time Series ◽  
Secondary Schools ◽  
Effect Size ◽  
Scientific Literacy ◽  
Cohen’S D ◽  
Series Design ◽  
Time Series Design ◽  
Biology Learning ◽  
Normalized Gain ◽  
D Value

The goal of this work using time series design was to obtain the profile of students’ competencies in biology learning–scientific literacy oriented in secondary schools. It was obtained that students’ competencies increased in medium category with normalized gain value of 0.586 and learning had effectiveness in medium category with effect size Cohen's d value of 0.548.

A non-parametric effect size measure capturing changes in central tendency and shape of data distributions more flexibly than Cohen’s d

2020 ◽  
Author(s):  
Jörn Lötsch ◽  
Alfred Ultsch
Keyword(s):  
Effect Size ◽  
Data Science ◽  
Heterogeneous Data ◽  
Machine Learning Algorithms ◽  
Central Tendency ◽  
Effect Size Measure ◽  
Specific Data ◽  
Cohen’S D ◽  
Size Measure ◽  
Cohen's D

Abstract Calculating the magnitude of treatment effects or of differences between two groups is a common task in quantitative science. Standard effect size measures based on differences, such as the commonly used Cohen's, fail to capture the treatment-related effects on the data if the effects were not reflected by the central tendency. "Impact” is a novel nonparametric measure of effect size obtained as the sum of two separate components and includes (i) the change in the central tendency of the group-specific data, normalized to the overall variability, and (ii) the difference in the probability density of the group-specific data. Results obtained on artificial data and empirical biomedical data showed that impact outperforms Cohen's d by this additional component. It is shown that in a multivariate setting, while standard statistical analyses and Cohen’s d are not able to identify effects that lead to changes in the form of data distribution, “Impact” correctly captures them. The proposed effect size measure shares the ability to observe such an effect with machine learning algorithms. It is numerically stable even for degenerate distributions consisting of singular values. Therefore, the proposed effect size measure is particularly well suited for data science and artificial intelligence-based knowledge discovery from (big) and heterogeneous data.

scholarly journals 0636 Using AI To Predict Future CPAP Adherence and the Impact of Behavioral and Technical Interventions

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A243-A243
Author(s):  
W Hevener ◽  
B Beine ◽  
J Woodruff ◽  
D Munafo ◽  
C Fernandez ◽  
...  
Keyword(s):  
Effect Size ◽  
Statistical Significance ◽  
Post Intervention ◽  
Cpap Adherence ◽  
Cohen’S D ◽  
Usage Patterns ◽  
Patient Outreach ◽  
Cohen's D ◽  
The Impact ◽  
Usage Data

Abstract Introduction Clinical management of CPAP adherence remains an ongoing challenge. Behavioral and technical interventions such as patient outreach, coaching, troubleshooting, and resupply may be deployed to positively impact adherence. Previous authors have described adherence phenotypes that retrospectively categorize patients by discrete usage patterns. We design an AI model that predictively categorizes patients into previously studied adherence phenotypes and analyzes the statistical significance and effect size of several types of interventions on subsequent CPAP adherence. Methods We collected a cross-sectional cohort of subjects (N = 13,917) with 455 days of daily CPAP usage data acquired. Patient outreach notes and resupply data were temporally synchronized with daily CPAP usage. Each 30-days of usage was categorized into one of four adherence phenotypes as defined by Aloia et al. (2008) including Good Users, Variable Users, Occasional Attempters, and Non-Users. Cross-validation was used to train and evaluate a Recurrent Neural Network model for predicting future adherence phenotypes based on the dynamics of prior usage patterns. Two-sided 95% bootstrap confidence intervals and Cohen’s d statistic were used to analyze the significance and effect size of changes in usage behavior 30-days before and after administration of several resupply interventions. Results The AI model predicted the next 30-day adherence phenotype with an average of 90% sensitivity, 96% specificity, 95% accuracy, and 0.83 Cohen’s Kappa. The AI model predicted the number of days of CPAP non-use, use under 4-hours, and use over 4-hours for the next 30-days with OLS Regression R-squared values of 0.94, 0.88, and 0.95 compared to ground truth. Ten resupply interventions were associated with statistically significant increases in adherence, and ranked by adherence effect size using Cohen’s d. The most impactful were new cushions or masks, with a mean post-intervention CPAP adherence increase of 7-14% observed in Variable User, Occasional Attempter, and Non-User groups. Conclusion The AI model applied past CPAP usage data to predict future adherence phenotypes and usage with high sensitivity and specificity. We identified resupply interventions that were associated with significant increases in adherence for struggling patients. This work demonstrates a novel application for AI to aid clinicians in maintaining CPAP adherence. Support  

scholarly journals S80. CHILDHOOD TRAUMA AND SOCIAL COGNITION IN DELUSIONAL PSYCHOSES

2020 ◽  
Vol 46 (Supplement_1) ◽  
pp. S64-S65
Author(s):  
Covadonga Díaz-Caneja ◽  
Marcos González-Iglesias ◽  
Victoria Del Amo ◽  
Ignacio García-Cabeza ◽  
Celso Arango ◽  
...  
Keyword(s):  
Working Memory ◽  
Executive Function ◽  
Social Cognition ◽  
Childhood Trauma ◽  
Neuropsychological Functioning ◽  
Attributional Bias ◽  
Cohen’S D ◽  
Dsm Iv ◽  
The Difference ◽  
Cohen's D

Abstract Background Deficits in social cognition could be involved in the pathogenesis of delusions in psychotic disorders (Bentall et al., 2009). Childhood trauma (CT) has been associated with an increased risk for psychosis (Varese et al., 2012). Neurocognitive and social cognition deficits could mediate in the association between CT and psychosis (Mansueto et al., 2019). Social cognition and childhood trauma have been understudied so far in delusional disorder (DD). We aimed to assess social cognition in a sample of patients with delusional psychoses (i.e., DD and schizophrenia) and healthy controls (HC) and to explore the potential effect of childhood trauma on social cognition and delusion. Methods This cross-sectional, transdiagnostic study included 69 patients with a DSM-IV-TR-confirmed diagnosis of DD (mean age 44.06 ± 11.39 years, 53.6% female), 77 with DSM-IV-TR-confirmed schizophrenia (mean age 38.12 ± 9.27 years, 27.3% female), and 63 HC (mean age 43.6 ± 13.0 years, 68.3% female). Attributional bias was assessed with the “Internal, Personal, and Situational Attributions Questionnaire.” Theory of Mind (ToM) performance was assessed with the “Reading the Mind in the Eyes Test” and the “Faux Pas Recognition Test.” Childhood trauma was measured with the “Childhood Trauma Questionnaire.” Neuropsychological functioning was measured with a comprehensive battery assessing attention, verbal learning, working memory, and executive function. We used ANCOVAs and linear regression analyses to assess the association between the three measures of social cognition and i) diagnosis, ii) dimensional measures of delusion proneness (Peters Delusion Inventory, PDI) and intensity (Maudsley Assessment of Delusion Schedule, MADS), and iii) childhood trauma; after controlling for potential confounders (age, sex, socioeconomic status, and estimated premorbid intelligence quotient). Results Patients with DD showed significantly poorer performance on the “Eyes Test” than HC (Cohen’s d=-0.44, p=0.037), after controlling for potential confounding variables. The difference was no longer significant after controlling for verbal memory. Patients with schizophrenia (d=-1.54, p<0.001) and DD (Cohen’s d=-0.60, p=0.002) showed significantly poorer performance than HC on the “Faux Pas Test,” after controlling for potential confounders. The difference between patients with schizophrenia and HC remained significant after controlling for neuropsychological functioning (Cohen’s d=-1.09, p<0.001), while differences between patients with DD and HC were no longer significant after controlling for executive function and working memory performance (Cohen’s d=-0.23, p=0.596). No significant differences were found between diagnostic groups in externalizing or personalizing attributional bias. In the fully adjusted models, intensity of the delusional idea was significantly associated with performance in the “Faux Pas Test” in DD, and with externalizing and personalizing attributional bias in schizophrenia. A positive history of CT was significantly associated with lower performance on the “Faux Pas Test” (Cohen’s d=-0.40, p=.022) and higher delusional proneness scores in the delusional psychosis samples (Cohen’s d=-0.49, p=.006), but not in HC. Discussion Social cognition deficits are associated with delusional intensity in delusional psychoses. Childhood trauma could increase the risk of psychosis through its effect on social cognition.

scholarly journals The Unforgettables: a chorus for people with dementia with their family members and friends

2018 ◽  
Vol 30 (6) ◽  
pp. 779-789 ◽  
Author(s):  
Mary Sherman Mittelman ◽  
Panayiota Maria Papayannopoulou
Keyword(s):  
Quality Of Life ◽  
Social Support ◽  
Pilot Study ◽  
Effect Size ◽  
Family Members ◽  
Positive Effects ◽  
Cohen’S D ◽  
People With Dementia ◽  
Cohen's D

Summary/AbstractOur experience evaluating a museum program for people with dementia together with their family members demonstrated benefits for all participants. We hypothesized that participation in a chorus would also have positive effects, giving them an opportunity to share a stimulating and social activity that could improve their quality of life. We inaugurated a chorus for people with dementia and their family caregivers in 2011, which rehearses and performs regularly. Each person with dementia must be accompanied by a friend or family member and must commit to attending all rehearsals and the concert that ensues. A pilot study included a structured assessment, take home questionnaires and focus groups. Analyses of pre-post scores were conducted; effect size was quantified using Cohen's d. Results showed that quality of life and communication with the other member of the dyad improved (Effect size: Cohen's d between 0.32 and 0.72) for people with dementia; quality of life, social support, communication and self-esteem improved (d between 0.29 and 0.68) for caregivers. Most participants stated that benefits included belonging to a group, having a normal activity together and learning new skills. Participants attended rehearsals in spite of harsh weather conditions. The chorus has been rehearsing and performing together for more than 6 years and contributing to its costs. Results of this pilot study suggest that people in the early to middle stage of dementia and their family members and friends can enjoy and learn from rehearsing and performing in concerts that also engage the wider community. It is essential to conduct additional larger studies of the benefits of participating in a chorus, which may include improved quality of life and social support for all, and reduced cognitive decline among people with dementia.

scholarly journals Effect Size Guidelines, Sample Size Calculations, and Statistical Power in Gerontology

2019 ◽  
Vol 3 (4) ◽  
Author(s):  
Christopher R Brydges
Keyword(s):  
Individual Differences ◽  
Sample Size ◽  
Effect Size ◽  
Effect Sizes ◽  
Group Differences ◽  
Cohen’S D ◽  
Pearson's R ◽  
Sample Size Calculations ◽  
Cohen's D ◽  
Pearson’S R

Abstract Background and Objectives Researchers typically use Cohen’s guidelines of Pearson’s r = .10, .30, and .50, and Cohen’s d = 0.20, 0.50, and 0.80 to interpret observed effect sizes as small, medium, or large, respectively. However, these guidelines were not based on quantitative estimates and are only recommended if field-specific estimates are unknown. This study investigated the distribution of effect sizes in both individual differences research and group differences research in gerontology to provide estimates of effect sizes in the field. Research Design and Methods Effect sizes (Pearson’s r, Cohen’s d, and Hedges’ g) were extracted from meta-analyses published in 10 top-ranked gerontology journals. The 25th, 50th, and 75th percentile ranks were calculated for Pearson’s r (individual differences) and Cohen’s d or Hedges’ g (group differences) values as indicators of small, medium, and large effects. A priori power analyses were conducted for sample size calculations given the observed effect size estimates. Results Effect sizes of Pearson’s r = .12, .20, and .32 for individual differences research and Hedges’ g = 0.16, 0.38, and 0.76 for group differences research were interpreted as small, medium, and large effects in gerontology. Discussion and Implications Cohen’s guidelines appear to overestimate effect sizes in gerontology. Researchers are encouraged to use Pearson’s r = .10, .20, and .30, and Cohen’s d or Hedges’ g = 0.15, 0.40, and 0.75 to interpret small, medium, and large effects in gerontology, and recruit larger samples.

Sign in / Sign up

Export Citation Format

Share Document