Terms Of Sample Size Research Articles

Evaluating the Quality of Public Services Through Social Media

Public services need to be evaluated regularly to identify areas that need further improvement. Data collection via Twitter is affordable and timely, so it has the potential to be utilized to evaluate the quality of public service. This study utilizes tweets mentioning three service units of the provincial government of Jakarta and applies both sentiment analysis and topic classification to predict a rating/score of public service quality. The research goal is to examine if the evaluation of public services based on social media data is possible. The findings indicate that the use of Twitter has an advantage in terms of sample size and variety of opinions. Tweets can be translated into scores as well. Nonetheless, the representativeness issue and the predominance of complaint tweets can affect the reliability of the results.

A systematic review of treatment for patients with burning mouth syndrome.

BackgroundBurning mouth syndrome is a chronic idiopathic intractable intraoral dysaesthesia that remains a challenge to clinicians due to its poorly understood pathogenesis and inconsistent response to various treatments.AimThis review aimed to study the short- (≤3 months) and long-term (>3 months) effectiveness and sustainable benefit of different burning mouth syndrome treatment strategies and the associated side effects.Materials and methodsRandomised controlled trials of burning mouth syndrome treatment compared with placebo or other interventions with a minimum follow up of 2 months were searched from the PubMed, Embase and Cochrane database (published to July 2020).ResultsTwenty-two studies were selected based on the inclusion and exclusion criteria and analysed. Nine categories of burning mouth syndrome treatment were identified: Anticonvulsant and antidepressant agents, phytomedicine and alpha lipoic acid supplements, low-level laser therapy, saliva substitute, transcranial magnetic stimulation, and cognitive behaviour therapy. Cognitive behaviour therapy, topical capsaicin and clonazepam, and laser therapy demonstrated favourable outcome in both short- and long-term assessment. Phytomedicines reported a short-term benefit in pain score reduction. The pooled effect of alpha lipoic acid (ALA) pain score improvement was low, but its positive effects increased in long term assessment.ConclusionA more significant volume in terms of sample size, multi-centres, and multi-arm comparison of therapeutic agents with placebo and longitudinal follow-up studies is recommended to establish a standardised burning mouth syndrome treatment protocol. Further studies are required to assess the analgesic benefits of topical clonazepam and capsaicin, alternative medicines with neurodegenerative prevention capability and psychology support in treating burning mouth syndrome and reducing systemic adverse drug reactions.Registration International Prospective Register of Systematic Reviews (PROSPERO):Protocol ID - CRD42020160892.

Sampling plans using extended EWMA statistic with and without auxiliary information

In this paper, we propose an Acceptance Sampling Plan (ASP) using the statistic suggested by Naveed et al. (2018) under the condition of known and unknown population standard deviation (SD) for the presence of with and without Auxiliary Information (AI). It is presumed that the study variable of quality trait and AI follow the bivariate normal distribution. The plan parameters of the recommended plan are discussed for all four cases under the constraint that specified producer and consumer risks are gratified. The suggested plan is compared in terms of sample size (SS) with numerous existing plans and showed that the presented plan has a smaller SS for any value of AQL, LQL. Various tables of plan parameters have been erected using various combinations of smoothing constants for industrial use. For the workable purpose, the industrial example has also been examined. At last, concluding remarks are discussed.

Nutritional Support Indications in Gastroesophageal Cancer Patients: From Perioperative to Palliative Systemic Therapy. A Comprehensive Review of the Last Decade.

Gastric cancer treatments are rapidly evolving, leading to significant survival benefit. Recent evidence provided by clinical trials strongly encouraged the use of perioperative chemotherapy as standard treatment for the localized disease, whereas in the advanced disease setting, molecular characterization has improved patients’ selection for tailored therapeutic approaches, including molecular targeted therapy and immunotherapy. The role of nutritional therapy is widely recognized, with oncologic treatment’s tolerance and response being better in well-nourished patients. In this review, literature data on strategies or nutritional interventions will be critically examined, with particular regard to different treatment phases (perioperative, metastatic, and palliative settings), with the aim to draw practical indications for an adequate nutritional support of gastric cancer patients and provide an insight on future directions in nutritional strategies. We extensively analyzed the last 10 years of literature, in order to provide evidence that may fit current clinical practice both in terms of nutritional interventions and oncological treatment. Overall, 137 works were selected: 34 Randomized Clinical Trials (RCTs), 12 meta-analysis, 9 reviews, and the most relevant prospective, retrospective and cross-sectional studies in this setting. Eleven ongoing trials have been selected from clinicaltrial.gov as representative of current research. One limitation of our work lies in the heterogeneity of the described studies, in terms of sample size, study procedures, and both nutritional and clinical outcomes. Indeed, to date, there are no specific evidence-based guidelines in this fields, therefore we proposed a clinical algorithm with the aim to indicate an appropriate nutritional strategy for gastric cancer patients.

Rigor, reproducibility, and transparency of randomized controlled trials in obstetrics and gynecology

Randomized controlled trials are considered the highest level of evidence but fewer than half are reproducible. A rigorous methodology improves trial quality, but reproducibility may be limited by a lack of transparency in reporting. The Consolidated Standards of Reporting Trials guidelines define reporting standards, and pretrial registration requires a predefined methodology and predefined outcomes. We evaluated obstetrics and gynecology trials published in 6 journals in terms of their adherence to the Consolidated Standards of Reporting Trials guidelines. Second, we evaluated pretrial registration compliance and concordance between the registry and publication. Furthermore, we evaluated the differences in trial characteristics among randomized controlled trials with the highest level of compliance and those with lower levels of compliance and adherence to guidelines by journal type. This was a cross-sectional study of obstetrics and gynecology trials published between 2017 and 2019 in 6 journals (American Journal of Obstetrics & Gynecology, BJOG: An International Journal of Obstetrics and Gynaecology, Obstetrics & Gynecology, The Journal of the American Medical Association, The Lancet, and The New England Journal of Medicine). Randomized controlled trials were identified via PubMed and manual journal archive searches. The primary outcome was adequate compliance with the Consolidated Standards of Reporting Trials guidelines defined as ≥80% of the checklist items present. Secondary outcomes included completion of pretrial registration and concordance between the pretrial registration and publication in terms of the outcomes and sample size. We compared the characteristics between trials with adequate compliance and those with inadequate compliance. Secondary analyses included comparisons of characteristics of the trials in the top quartile for compliance with the Consolidated Standards of Reporting Trials guidelines with those of the trials in lower quartiles and compliance with guidelines in obstetrics-gynecology vs non-obstetrics-gynecology journals. In an exploratory analysis, trends in compliance with the Consolidated Standards of Reporting Trials guidelines across the study period were assessed. A post hoc sensitivity analysis evaluated the outcomes after the exclusion of 2 retracted trials. Of the 170 trials included, 80% (95% confidence interval, 74%-86%) were adequately compliant with the Consolidated Standards of Reporting Trials manuscript guidelines and 66% (95% confidence interval, 59%-73%) were compliant with the abstract guidelines. Nearly all trials (98%) reported pretrial registration. Concordance between pretrial registration and publication in terms of the primary outcomes was identified for 77% of the trials, concordance in terms of the secondary outcomes was observed in 32% of the trials, and concordance in terms of sample size was observed in 60% of the trials. Trials with adequate compliance were more likely to be preregistered, include an a priori power calculation, and use an intent to treat analysis. Trials in the top quartile for compliance with the Consolidated Standards of Reporting Trials guidelines were more likely to be multicenter, international, and government funded. More trials from non-obstetrics-gynecology journals were in the top quartile for compliance with the Consolidated Standards of Reporting Trials guidelines than trials from obstetrics-gynecology journals (64.9% vs 25.7%; P<.001). No significant trends in adequate compliance were identified across the study period. Results did not differ significantly in the sensitivity analysis. Of all the trials included, 20% of obstetrics-gynecology trials published in 6 high-impact journals were not compliant with the Consolidated Standards of Reporting Trials guidelines, and there were major discrepancies between pretrial registration and publication. Transparency, reproducibility, and scientific rigor in obstetrics and gynecology trial reporting needs to be improved.

Enhancing Textile Industry’s Employee Satisfaction through Market Sensing Capability and Internal Marketing Practice

Recognize the importance of employee satisfaction in any organization, this study is piloted to forestall the effect of Internal Marketing Practice and Market Sensing capability on employees’ satisfaction in the context of the Indonesian textile industry as one of the fast-growing industry criteria in Asian markets. The drive behind this study is to examine the relationship between Internal marketing practice, Market Sensing Capability, and Employee Satisfaction. Furthermore, this study plans to see that how Cultural congruence moderates the relationship between Employee Satisfaction through Internal Marketing Practice along with Market Sensing Capability by advancing a research model. According to this study’s requirement, the quantitative methodology is chosen, with purposive method of 323 employees was selected and analyzed. By using a web-based survey approach was selected for data, entailing of structured questionnaire. A structural equation model was operated for results on AMOS that supported the hypothetical relationship between all hypotheses. This study will guide the managers of textile firms to recognize that how important is employee satisfaction and how they can improve their practices to strengthen employee satisfaction. This study also contributes in cultural Congruence and market sensing capability literature. It is not free from limitations specifically in terms of sample size and variables that can be addressed in the future.

Acceptance sampling plans based on Topp-Leone Gompertz distribution

The present study presents additional properties of Topp-Leone Gompertz (TL-G) distribution developed by Nzei et al. (2020). All derived mathematical properties play an essential role in reliability analysis. The aim is not only to derive properties of TL-G distribution but also to develop acceptance sampling plans for lot sentencing in which the quality characteristic of the products follows the TL-G distribution. Two acceptance sampling plans, single and repetitive, based on TL-G distribution using the time truncated scheme, have been considered. The application has been observed on a real dataset of the strength of 1.5 cm glass fiber. A simulation-based study has also been conducted when the quality characteristic of the items follows the TL-G distribution. The effect of the misspecification of the parameters has been discussed for the repetitive acceptance sampling plan. Optimal parameters and the minimum average sample number have been obtained for both plans by satisfying consumer’s and producer’s risks simultaneously. The findings indicate that the sample size and acceptance number decrease as the termination ratio, consumer’s risk, and acceptable quality level increase. The repetitive sampling plan performs better than the single sampling plan in terms of sample size and the probability of accepting a lot of products whose lifetime follows the TL-G distribution. It has also been concluded that there is no misspecification of the TL-G distribution parameters for the termination ratio, a=1.0. Hence, the same repetitive sampling plans can be used for lot sentencing.

Digital Rock Physics: A Geological Driven Workflow for the Segmentation of Anisotropic Ruhr Sandstone

Over the last 3 decades, Digital Rock Physics (DRP) has become a complementary part of the characterization of reservoir rocks due to the non-destructive testing character of this technique. The use of high-resolution X-ray Computed Tomography (XRCT) has become widely accepted to create a digital twin of the material under investigation. Compared to other imaging techniques, XRCT technology allows a location-dependent resolution of the individual material particles in volume. However, there are still challenges in assigning physical properties to a particular voxel within the digital twin, due to standard histogram analysis or sub-resolution features in the rock. For this reason, high-resolution image-based data from XRCT, transmitted-light microscope, Scanning Electron Microscope (SEM) as well as geological input properties like geological diagenesis, mineralogical composition, sample’s microfabrics, and estimated sample’s porosity are combined to obtain an optimal spatial segmented image of the studied Ruhr sandstone. Based on a homogeneity test, which corresponds to the evaluation of the gray-scale image histogram, the preferred scan sample sizes in terms of permeability, thermal, and effective elastic rock properties are determined. In addition, these numerically derived property predictions are compared with laboratory measurements to obtain possible upper limits for sample size, segmentation accuracy, and a geometrically calibrated digital twin of the Ruhr sandstone. The comparison corresponding gray-scale image histograms as a function of sample sizes with the corresponding advanced numerical simulations provides a unique workflow for reservoir characterization of the Ruhr sandstone.

Preference of Prior for Two-Component Mixture of Lomax Distribution

Recently, El-Sherpieny et al., (2020), suggested Type-II hybrid censoring method for parametric estimation of Lomax distribution (LD) without due regard being given to the choice of priors and posterior risk associated with the model. This paper fills this gap and derived the new LD model with minimum posterior risk for the selection of priors. It derives a closed form expression for Bayes estimates and posterior risks using square error loss function (SELF), weighted loss function (WLF), quadratic loss function (QLF) and DeGroot loss function (DLF). Prior predictive approach is used to elicit the hyperparameters of mixture model. Analysis of Bayes estimates and posterior risks is presented in terms of sample size (n), mixing proportion (p) and censoring rate (t0), with the help of simulation study. Usefulness of the model is demonstrated on applying it to simulated and real-life data which show promising results in terms of better estimation and risk reduction.

Acquired Brain Injury and Interventions in the Offender Population: A Systematic Review.

Background and Aims: The prevalence of acquired brain injury (ABI) in offender populations appears much higher than in the general population, being estimated at 50% compared to 12%, respectively. Taking into account ABI-related cognitive and social impairments or behavioral changes in forensic treatments might be relevant and may improve treatment outcomes. The aim of the current review is to summarize and integrate the literature on psychological interventions or treatments for consequences of ABI in the forensic setting. Reviewing this literature could provide crucial information for improving treatment options for offenders with ABI, which may contribute to reducing recidivism.Methods: The PubMed/MEDLINE, PsychInfo, CINAHL, COCHRANE, and Web of Science databases were searched for studies in adult offenders with ABI that evaluated the effect of psychological interventions with a focus on ABI-related impairments and recidivism.Results: This review identified four intervention studies that met the inclusion criteria. These included an adult population (≥18-year-old) in a forensic setting (given the focus of the current review on treatment, defined here as an environment in which offenders are treated while being incarcerated or as outpatients), non-pharmacological treatments and were published in English or Dutch between 2005 and 2020. All studies reported some positive effects of the intervention on interpersonal behavior, cognition and recidivism. The aspects of the interventions that seemed most beneficial included personalized treatment and re-entry plans, support for the individual and their environment and psychoeducation about the effects of ABI.Discussion: Although positive effects were reported in the studies reviewed, all studies had methodological limitations in terms of sample size, study design and outcome measures which affects the strength of the evidence. This limits strong conclusions and generalizability to the entire offender population.Conclusion: Despite high prevalence of ABI in offender populations, interventions in forensic settings seldom address the effect of ABI. The few studies that did take ABI into account reported positive effects, but those results should be interpreted with caution. Future studies are warranted, since this does seem an important venue to improve treatment, which could eventually contribute to reducing recidivism.

Using the geometric average hazard ratio in sample size calculation for time-to-event data with composite endpoints

BackgroundSample size calculation is a key point in the design of a randomized controlled trial. With time-to-event outcomes, it’s often based on the logrank test. We provide a sample size calculation method for a composite endpoint (CE) based on the geometric average hazard ratio (gAHR) in case the proportional hazards assumption can be assumed to hold for the components, but not for the CE.MethodsThe required number of events, sample size and power formulae are based on the non-centrality parameter of the logrank test under the alternative hypothesis which is a function of the gAHR. We use the web platform, CompARE, for the sample size computations. A simulation study evaluates the empirical power of the logrank test for the CE based on the sample size in terms of the gAHR. We consider different values of the component hazard ratios, the probabilities of observing the events in the control group and the degrees of association between the components. We illustrate the sample size computations using two published randomized controlled trials. Their primary CEs are, respectively, progression-free survival (time to progression of disease or death) and the composite of bacteriologically confirmed treatment failure or Staphylococcus aureus related death by 12 weeks.ResultsFor a target power of 0.80, the simulation study provided mean (± SE) empirical powers equal to 0.799 (±0.004) and 0.798 (±0.004) in the exponential and non-exponential settings, respectively. The power was attained in more than 95% of the simulated scenarios and was always above 0.78, regardless of compliance with the proportional-hazard assumption.ConclusionsThe geometric average hazard ratio as an effect measure for a composite endpoint has a meaningful interpretation in the case of non-proportional hazards. Furthermore it is the natural effect measure when using the logrank test to compare the hazard rates of two groups and should be used instead of the standard hazard ratio.

Meal and Sleep Timing before and during the COVID-19 Pandemic: A Cross-Sectional Anonymous Survey Study from Sweden.

The COVID-19 pandemic and related restrictions, such as stay-at-home-orders, have significantly altered daily routines and lifestyles. Given their importance for metabolic health, we herein compared sleep and meal timing parameters during vs. before the COVID-19 pandemic based on subjective recall, in an anonymous Swedish survey. Among 191 adults (mean age: 47 years; 77.5% females), we show that social jetlag, i.e., the mismatch in sleep midpoint between work and free days, was reduced by about 17 min during the pandemic compared with the pre-pandemic state (p < 0.001). Concomitantly, respondents’ sleep midpoint was shifted toward morning hours during workdays (p < 0.001). A later daily eating midpoint accompanied the shift in sleep timing (p = 0.001). This effect was mainly driven by a later scheduled first meal (p < 0.001). No difference in the timing of the day’s last meal was found (p = 0.814). Although our survey was limited in terms of sample size and by being cross-sectional, our results suggest that the delay in sleep timing due to the COVID-19 pandemic was accompanied by a corresponding shift in the timing of early but not late meals.

Time-varying coefficient model estimation through radial basis functions

ABSTRACT In this paper, we estimate the dynamic parameters of a time-varying coefficient model through radial kernel functions in the context of a longitudinal study. Our proposal is based on a linear combination of weighted kernel functions involving a bandwidth, centered around a given set of time points. In addition, we study different alternatives of estimation and inference including a Frequentist approach using weighted least squares along with bootstrap methods, and a Bayesian approach through both Markov chain Monte Carlo and variational methods. We compare the estimation strategies mention above with each other, and our radial kernel functions proposal with an expansion based on regression spline, by means of an extensive simulation study considering multiples scenarios in terms of sample size, number of repeated measurements, and subject-specific correlation. Our experiments show that the capabilities of our proposal based on radial kernel functions are indeed comparable with or even better than those obtained from regression splines. We illustrate our methodology by analyzing data from two AIDS clinical studies.

Cost model of variable multiple dependent state sampling plan with rectifying inspection

It is always foreseen to upturn the efficiency of an acceptance sampling plan for lot sentencing. In this research, variable multiple dependent state sampling plan considering the quality cost with rectifying inspection is proposed for normally distributed quality characteristics. The staple objective is to curb the total cost of the lot under inspection and improve the quality of outgoing lots. Tables are constructed for optimal plan parameters by increasing forgoing lots. The behavior of cost parameters on total cost has been investigated. Protection and cost curves are portrayed to show the efficacy of the proposed plan with rectifying single acceptance sampling plan using the cost model. Using the cost model, the proposed plan turns out to be more effectual than the single acceptance sampling plan in terms of sample size, average outgoing quality, and total cost. has emerged having a substantial effect on total cost trailed by and with the tiniest effect. Finally, an example is given to demonstrate the proposed plan.

Phenotypic Response to Light Versus Shade Associated with DNA Methylation Changes in Snapdragon Plants (Antirrhinum majus).

The phenotypic plasticity of plants in response to change in their light environment, and in particularly, to shade is a schoolbook example of ecologically relevant phenotypic plasticity with evolutionary adaptive implications. Epigenetic variation is known to potentially underlie plant phenotypic plasticity. Yet, little is known about its role in ecologically and evolutionary relevant mechanisms shaping the diversity of plant populations in nature. Here we used a reference-free reduced representation bisulfite sequencing method for non-model organisms (epiGBS) to investigate changes in DNA methylation patterns across the genome in snapdragon plants (Antirrhinum majus L.). We exposed plants to sunlight versus artificially induced shade in four highly inbred lines to exclude genetic confounding effects. Our results showed that phenotypic plasticity in response to light versus shade shaped vegetative traits. They also showed that DNA methylation patterns were modified under light versus shade, with a trend towards global effects over the genome but with large effects found on a restricted portion. We also detected the existence of a correlation between phenotypic and epigenetic variation that neither supported nor rejected its potential role in plasticity. While our findings imply epigenetic changes in response to light versus shade environments in snapdragon plants, whether these changes are directly involved in the phenotypic plastic response of plants remains to be investigated. Our approach contributed to this new finding but illustrates the limits in terms of sample size and statistical power of population epigenetic approaches in non-model organisms. Pushing this boundary will be necessary before the relationship between environmentally induced epigenetic changes and phenotypic plasticity is clarified for ecologically relevant mechanisms with evolutionary implications.

The Effectiveness of Dynamic Geometry Software Applications in Learning Mathematics: A Meta-Analysis Study

The purpose of this study was to (1) assess the impact of using Dynamic Geometry Software (DGS) on students’ mathematical abilities, (2) determine the differences in effectiveness based on study characteristics in order to help educators decide under what conditions the use of DGS would be suitable in improving students' mathematical abilities. This meta-analysis study investigates 57 effect sizes from 50 articles that have been published in journals, international and domestic proceedings from 2010 to 2020 using the Comprehensive Meta-Analysis (CMA) tool as a calculation tool. Meanwhile, the Hedges coefficient is applied to the calculation of the effect size at the 95% confidence level. Based on a random effect model with a standard error of 0.09, the analysis results have found an overall effect size of 1.07. This means that learning using DGS has a high positive effect on students' mathematical abilities. The effect size of 1.07 explains the average student who uses DGS exceeds 84% math ability of those in conventional classes that are initially equivalent. Analysis of the study characteristics found significant differences in terms of sample size, student to computer ratio, and education level. This research showed the DGS used was more effective under certain conditions. First, it is very effective in sample conditions less than or equal to 30. Second, it provides classrooms with a sufficient number of computers, allowing students to use them individually, which is required to achieve higher effectiveness levels. Third, DGS is effective in high schools and colleges than in junior high schools. These facts can help educators in deciding on the appropriate sample sizes, student to computer ratios, and future levels of education in using DGS.

The Relationship Between Living with Dogs and Social and Emotional Development in Childhood

ABSTRACT In this study, we aimed to identify possible significant differences in the socioemotional development of children who live with dogs in their daily lives, compared with children who do not have this type of contact, and to determine the extent to which these differences are associated with sex. We studied a sample of 120 children (53.3% girls) aged between three and five years old comprising two intact groups (dog and non-dog) from two public (state) schools and one private school. These two groups were balanced in terms of sample size (n = 60 each group) and participant age. The data were collected using the personal-social domain of the Battelle Developmental Inventory, which assesses adult interaction, expression of feelings and affections, self-image, peer interaction, cooperation, and social role. A factorial multivariate analysis of variance test was conducted to identify any differences in the children’s socioemotional development based on sex or their contact with dogs. We found that contact with dogs had a significant association with socialization in both boys and girls and that the differences between the two groups (dog and non-dog) were of a large magnitude. In fact, the group that had contact with dogs obtained significantly higher average scores in all subdomains corresponding to the personal-social domain of the Battelle Developmental Inventory, as expected. Our results show that contact with dogs at home during early childhood is related to more advanced social development in both boys and girls, which is consistent with the findings of other studies. However, more research is needed to clarify which other factors (e.g., individual or family-related or socioeconomic) may be involved in the benefits of having a dog during childhood.

Weighted generalized Quasi Lindley distribution: Different methods of estimation, applications for Covid-19 and engineering data

&lt;abstract&gt;&lt;p&gt;Recently, a new lifetime distribution known as a generalized Quasi Lindley distribution (GQLD) is suggested. In this paper, we modified the GQLD and suggested a two parameters lifetime distribution called as a weighted generalized Quasi Lindley distribution (WGQLD). The main mathematical properties of the WGQLD including the moments, coefficient of variation, coefficient of skewness, coefficient of kurtosis, stochastic ordering, median deviation, harmonic mean, and reliability functions are derived. The model parameters are estimated by using the ordinary least squares, weighted least squares, maximum likelihood, maximum product of spacing's, Anderson-Darling and Cramer-von-Mises methods. The performances of the proposed estimators are compared based on numerical calculations for various values of the distribution parameters and sample sizes in terms of the mean squared error (MSE) and estimated values (Es). To demonstrate the applicability of the new model, four applications of various real data sets consist of the infected cases in Covid-19 in Algeria and Saudi Arabia, carbon fibers and rain fall are analyzed for illustration. It turns out that the WGQLD is empirically better than the other competing distributions considered in this study.&lt;/p&gt;&lt;/abstract&gt;

Comparison of Data Mining Classification Algorithms on Educational Data under Different Conditions

The purpose of this study was to examine the performance of Naive Bayes, k-nearest neighborhood, neural networks, and logistic regression analysis in terms of sample size and test data rate in classifying students according to their mathematics performance. The target population was 62728 students in the 15-year-old group who were participated in the Programme for International Student Assessment (PISA) in 2012 from The Organisation for Economic Co-operation and Development (OECD) countries. The performance of each algorithm was tested by using 11%, 22%, 33%, 44% and 55% of each dataset for small (500 students), medium (1000 students) and large (5000 students) sample sizes. 100 replications were performed for each analysis. As the evaluation criteria, accuracy rates, RMSE values, and total elapsed time were used. RMSE values for each algorithm were statistically compared by using Friedman and Wilcoxon tests. The results revealed that while the classification performance of the methods increased as the sample size increased, the increase of training data ratio had different effects on the performance of the algorithms. The Naive Bayes showed high performance even in small samples, performed the analyzes very quickly, and was not affected by the change in the training data ratio. Logistic regression analysis was the most effective method in large samples but had a poor performance in small samples. While neural networks showed a similar tendency, its overall performance was lower than Naive Bayes and logistic regression. The lowest performances in all conditions were obtained by the k-nearest neighborhood algorithm.

Investigation of Studies for the Use of Augmented Reality Applications for Educational Purposes: Content Analysis

Augmented reality is a technology used in almost every stage of our daily life. It has become widespread in several fields such as engineering, healthcare, advertising, defense industry, and entertainment. The use of augmented reality technology that combines virtual and real environments is increasing every day. Augmented reality technology, which allows multiple multimedia materials to be used together, is a preferred teaching material in educational environments. This study is a content analysis study. Turkish studies that addressed the use of augmented reality applications for educational purposes and that were published between 2012 and 2019 were analyzed and descriptive analysis was performed according to their distribution by years, a number of authors, research patterns, sample sizes, data collection tools, and data analysis methods. For this purpose, the keywords Augmented reality, educational practices, education technologies and educational technologies were searched in ULAKBİM, YÖK National Thesis Center and Google Academy databases and 106 scientific studies, 60 thesis and 46 articles published between 2012 and 2019 in Turkish were obtained. Then, these studies were examined using the content analysis method. The publication classification form, developed by Sözbilir, Kutu, and Yasar (2012) as a data collection tool, was rearranged in line with the sub-problems. These sub-problems are research patterns, data analysis methods, data collection tools, number of authors, distribution by years and sample sizes. The data were presented with descriptive statistics methods such as frequency and percentage, with graphs and tables. As a result it was found that the studies in the field of augmented were published mostly in 2019. It was also observed that most of the investigated articles had two authors in terms of the number of authors. In addition quasi-experimental design, one of the most common quantitative research methods, was found to be used as the research design. In terms of sample size, it was seen that a sample size between 51-100 was used. It was also observed that the most used data collection tool was the achievement tests prepared according to the purpose of the research. The analysis of the results section of the studies revealed that the t-test, which is one of the the parametric tests, was used most frequently in the analysis of the data. The results of this study will reveal the tendency of the studies and identify deficiencies in the existing studies and thus will be a guide for future studies.