Use Of Confidence Intervals Research Articles

Adaptation of Saccharomyces to High Glucose Concentrations and Its Impact on Growth Kinetics of Alcoholic Fermentations.

Prior adaptation of Saccharomyces cerevisiae to the fermentation medium ensures its implantation and success in alcoholic fermentations. Fermentation kinetics can be characterized with mathematical models to objectively measure the success of adaptation and growth. The study aims at assessing and comparing two pre-culture procedures using, respectively, one or two adaptation steps, analyzing the impact of different initial glucose concentrations on the fermentation profiles of S. cerevisiae cultures, and assessing the performance of three predictive growth models (Buchanan's, modified Gompertz, and Baranyi and Roberts models) under varied initial glucose concentrations. We concluded that both protocols produced S. cerevisiae pre-cultures with similar viability and biomass increase, which suggests that short protocols may be more cost-effective. Furthermore, the study highlights the need of inoculating a high S. cerevisiae population to minimize the depletion of dissolved oxygen in the medium and to ensure that glucose is predominantly directed toward the ethanol formation at early fermentative steps. This study shows that the relationship between kinetic parameters is model-dependent, which hinders inter-study comparisons and stresses the need for standardized growth models. We advocate for the generalized use of confidence intervals of the kinetic parameters to facilitate objective inter-study comparisons.

Efficient social media sentiment analysis using confidence interval-based classification of online product brands

This paper presents an efficient method for categorizing the sentiments of Internet users, with a focus on social media users, using a confidence interval to estimate the reliability of sentiment predictions. The classification is based on the sentiments expressed in their posts, which are divided into positive, negative, and neutral categories. The paper presents an analysis table that analyzes sentiments and opinions about online product brands. The process includes two steps: 1) analyzing sentiments from text data using machine learning techniques, and 2) describing a five-step sentiment and opinion classification process that includes data collection, preprocessing, algorithm application, validation, and visualization. The proposed solution is implemented using Python, along with the scikit-learn, NumPy, pandas, and Dash libraries, and leverages the use of confidence intervals to assess the accuracy and reliability of the sentiment analysis model.

Changes in methodological study characteristics in psychology between 2010-2021.

In 2015, the Open Science Collaboration repeated a series of 100 psychological experiments. Since a considerable part of these replications could not confirm the original effects and some of them pointed in the opposite direction, psychological research is said to lack reproducibility. Several general criticisms can explain this finding, such as the standardized use of undirected nil-null hypothesis tests, samples being too small and selective, lack of corrections for multiple testing, but also some widespread questionable research practices and incentives to publish positive results only. A selection of 57,909 articles from 12 renowned journals is processed with the JATSdecoder software to analyze the extent to which several empirical research practices in psychology have changed over the past 12 years. To identify journal- and time-specific changes, the relative use of statistics based on p-values, the number of reported p-values per paper, the relative use of confidence intervals, directed tests, power analysis, Bayesian procedures, non-standard α levels, correction procedures for multiple testing, and median sample sizes are analyzed for articles published between 2010 and 2015 and after 2015, and in more detail for every included journal and year of publication. In addition, the origin of authorships is analyzed over time. Compared to articles that were published in and before 2015, the median number of reported p-values per article has decreased from 14 to 12, whereas the median proportion of significant p-values per article remained constant at 69%. While reports of effect sizes and confidence intervals have increased, the α level is usually set to the default value of .05. The use of corrections for multiple testing has decreased. Although uncommon in each case (4% in total), directed testing is used less frequently, while Bayesian inference has become more common after 2015. The overall median estimated sample size has increased from 105 to 190.

Increasing information gain in animal research by improving statistical model accuracy

Reduction of the numbers of laboratory animals is one of the three pillars of ethical animal research. Equivalently, information gain per animal should be maximized. A road towards this goal that is barely taken in current animal research is the more accurate statistical modeling of experiments. Here we show for a typical experiment (“open field test”) with outcomes that are non-normally distributed count data, how this can be implemented and what information gain is achieved. We contrast the state of the art – the use of confidence intervals based on null-hypothesis significance testing (NHST) –, with a Bayesian approach with the same underlying normal model, and a Bayesian approach with a more accurate negative binomial model. We find that the more accurate model leads to a marked improvement of knowledge gained with the experiment, especially for small sample sizes. As experimental data that violate assumptions of simple, conventional models are frequent, our findings have wider implications.

Journals like Acta Paediatrica should encourage authors to provide uncertainty estimates in manuscripts.

Medical literature has historically focused on reporting p values and sharply contrasting results.1 However, notable steps have been taken to understand uncertainty and some researchers have suggested abandoning p values.2 Uncertainty is typically estimated by confidence intervals in frequentist statistics or by credible intervals, using the Bayesian approach. The benefits include the range of the possible results, as confidence intervals typically indicate whether results represent the true effect. Furthermore, the width of the interval indicates how likely it is that the effect estimate is correct. This provides additional value, instead of just giving dichotomised interpretation based on p-values, whether it is statistically significant or not.3 Table 1 presents an example, based on two hypothetical scenarios with identical absolute risks, to illustrate this point. This shows that reporting practices make a notable difference and that providing the absolute rates, relative rates and uncertainty estimates makes it easier for readers. However, I have noticed variations in reporting practices in most medical journals, including Acta Paediatrica. I searched the Web of Science database on 31 January 2023 for papers published in Acta Paediatrica in 2022 that reflected current result-reporting practices. This identified 157 full-length original studies. Other kinds of papers were excluded, such as brief reports, editorials and review. Five case series that had less than 30 participants were excluded, as they were unlikely to have enough power to conduct reasonable statistical testing. The papers were assessed using Covidence software (Veritas Health Innovation). The main outcome measure was using reporting practices to describe the differences or values of the main outcomes. I also extracted the use of confidence intervals and p values in the results sections. No ethical approval was required for this study. The 157 results were evaluated and 121 were included in the analysis. I found that 83% reported p values and 70% reported confidence intervals in the full-text results sections or tables. Both were reported in 58% of the papers and neither in 4%. p values were exclusively used in 26% and confidence intervals were exclusively used in 12%. The use of p values was more common than confidence intervals in the journal in 2022 and the exclusive use of p values was notably more frequent in original research papers. p value reporting is still more common than confidence interval reporting. As explained earlier, confidence intervals provide clear benefits over p values. But it should be noted that, although confidence intervals provide uncertainty estimates, the tendency for dichotomous interpretation of these still exists. It is simple to decide whether an intervention is effective or not by examining the overlap of one or zero, depending on the method used. However, this should not be the case, as the confidence intervals can be interpreted based on whether they include an effect that is compatible with either an increase or decrease in the outcome.4 For example, if an intervention has an observed risk ratio of 0.90 and the confidence interval is 0.50 to 1.30. It can be interpreted that the range of effect estimate includes both increase and decrease in the risks. However, in a similar case with risk ratio of 0.90, if the confidence intervals are 0.79 to 1.01, the effect sizes include a clear decrease, but unlikely increase. In this case, the finding should be interpreted as being more in favour of the intervention. If only p values had been used, this interpretation of the results would be nearly impossible. Previous studies have identified that authors are more likely to only present p values for so-called significant findings.5 A possible way to improve the reporting practice in medical journals has been the use of statistical editors, although it could be achieved by strict general editorial policies. Furthermore, the use of reporting checklists has been shown to improve reporting quality and unify reporting practices.6 However, more education for researchers and other parties, such as journals, editors, funders and universities, is the most desired goal when it comes to improving reporting practices in medical science. The aim of research should be to provide methodologically relevant papers, instead of focusing on statistical significance and impact.7 A clear limitation of this review is that it was only conducted by one author, which increases the likelihood of unintended mistakes in the extraction process. Furthermore, there are no uncertainty estimates in this report. This may seem ironic, but as this is just a descriptive report, these were left out. A further limitation was the lack of comparison to different journals or historical volumes of Acta Paediatrica, but the aim was to describe current reporting practices. Uncertainty is one of the key concepts in current medical reporting. Journals can decide and guide authors to embrace uncertainty more in reporting. Acta Paediatrica could achieve this by emphasising that authors should always provide uncertainty estimates in manuscripts. None. None.

The Quality of Otolaryngology- Head and Neck Surgery Literature over the Last Decade.

To describe the changes in the quality of the Otolaryngology-Head and Neck Surgery (OTOHNS) literature over the last decade, and compare it to other surgical-based fields. Based on impact factors, the top eight clinical U.S. OTOHNS journals were selected, and articles were analyzed from 2020 (Oto 2020) and compared to 2010 (Oto 2010). This was done similarly for Neurosurgery, Orthopedic, Ophthalmology, and General Surgery journals in 2020 (non-Oto). To limit bias and account for random variability, the first 10 research articles from each journal in each group were included. Data regarding the study type, level of evidence, use of confidence intervals, and funding source were collected. Based on an a priori power analysis, 160 articles were analyzed for Oto 2010 and Oto 2020. Compared to Oto 2020, Oto 2010 had more level 1 and 2 evidence (12 vs. 4; p=0.032) and less reporting of confidence intervals (10 vs. 32; p < 0.001). Comparing the top 160 articles from 2020 from Non-Oto and OTOHNS (Oto), Non-Oto had more level 1 and 2 evidence (19 vs. 6; p=0.0047), more randomized controlled trials (8 vs. 1; p=0.016), and less reporting of confidence intervals (42 vs. 58; p=0.009). High quality studies remain relatively scarce in the OTOHNS literature. Although reporting of confidence intervals has improved over the last decade, aggregate levels of evidence and extramurally funded studies lag behind other surgical-based fields. Better study design will provide stronger evidence basis, in hopes of improving clinical care. N/A Laryngoscope, 133:1853-1856, 2023.

Confidence Intervals and Smallest Worthwhile Change Are Not a Panacea

Recently, a group of editors from physiotherapy journals wrote a joint editorial on the use of statistics in their journals. Like many editorials before them, the editors, who were not statistical experts themselves, put forth numerous recommendations to physiotherapy researchers on how to analyze and report their statistical analyses. This editorial unfortunately suffers from numerous mischaracterizations or outright falsehoods regarding statistics. After a thorough review, two major issues appear throughout the editorial. First, the editors incorrectly state that the use of confidence intervals (CI) would alleviate some of the issues with significance testing. Second, the editors incorrectly assume “smallest worthwhile change” statistics are immutable facts related to some ground truth of treatment effects. In this critical review, we briefly outline some of the problematic statements made by the editors, point out why it is too premature to adopt an estimation approach relying on a minimal clinically relevant difference, and offer some simple alternatives that we believe are statistically sound and easy for the average physiotherapy researcher to implement.

Absolute precision confidence intervals for unstandardized mean differences using sequential stopping rules.

Societies and journals in psychology encourage use of confidence intervals (CIs) on effect sizes. Gaining a maximum of precision of the CI at a minimum cost is desirable. Methods are available to calculate a sample size to provide some percent "assurance" that the final CI will be no wider than a desired value under the fixed-sample rule (FSR), in which a sample size must be decided a priori. Such assurance is expensive, and still subject to failure. The desired width can be specified either in standardized or unstandardized units, and this article focuses on unstandardized widths. A sequential stopping rule (SSR) can generate a CI for a mean difference that is always the desired width, and the average use of subjects is about the same as the FSR sample size without assurance. Improper use of sequential sampling can lead to a CI that has degraded coverage - the interval may contain the population value only 90% of the time for a nominal 95% CI. SSR methods are available to deliver CIs that are within a certain tolerance of the nominal coverage or that are at least the nominal coverage on average. These methods can be assessed by simulations, and they involve a manipulation of the minimum sample size, the desired width, or the practical confidence coefficient used to calculate CIs during the SSR experiment. As with FSR, more exact CIs are generated when the population standard deviation can be estimated accurately.

Is There a Confidence Interval for That? A Critical Examination of Null Outcome Reporting in Accounting Research

ABSTRACT This study evaluates how accounting researchers analyze and report null outcomes based on an examination of recent accounting research publications. As null outcomes fail to provide compelling evidence against a proposed null hypothesis, in and of themselves, they have little inferential value. Nevertheless, we find that articles routinely interpret such outcomes in a highly conclusive manner, using terms such as did not, is no difference, find no effect, equals, no association, etc. We also find little evidence that articles subject the available evidence to further statistical examinations that might provide relevant insights about the studied phenomenon. The analysis also illustrates the use of confidence intervals as a useful approach for providing insights about the inconsequentiality and precision of null outcomes. JEL Classifications: B41; M40.

Studying Early Decision Making with Progressive Bar Charts.

We conduct a user study to quantify and compare user performance for a value comparison task using four bar chart designs, where the bars show the mean values of data loaded progressively and updated every second (progressive bar charts). Progressive visualization divides different stages of the visualization pipeline-data loading, processing, and visualization-into iterative animated steps to limit the latency when loading large amounts of data. An animated visualization appearing quickly, unfolding, and getting more accurate with time, enables users to make early decisions. However, intermediate mean estimates are computed only on partial data and may not have time to converge to the true means, potentially misleading users and resulting in incorrect decisions. To address this issue, we propose two new designs visualizing the history of values in progressive bar charts, in addition to the use of confidence intervals. We comparatively study four progressive bar chart designs: with/without confidence intervals, and using near-history representation with/without confidence intervals, on three realistic data distributions. We evaluate user performance based on the percentage of correct answers (accuracy), response time, and user confidence. Our results show that, overall, users can make early and accurate decisions with 92% accuracy using only 18% of the data, regardless of the design. We find that our proposed bar chart design with only near-history is comparable to bar charts with only confidence intervals in performance, and the qualitative feedback we received indicates a preference for designs with history.

Three Research-Based Quantitative Reasoning Modules for Introductory Organismal Biology Laboratories

We have designed three laboratory modules for an introductory organismal biology course with an emphasis on quantitative reasoning and data analysis skills. Module 1 tests for dimorphism in crayfish chelae using a paired statistical design. Module 2 tests for allometric growth of tapeworm hook structures using a regression model. Module 3 tests for differences in stomatal densities between two groups of plants using a two-sample statistical approach. For all three modules, we emphasize the use of confidence intervals to draw statistical conclusions about hypotheses. Knowledge about the basic biology of animals and plants is required, including arthropods, platyhelminths, and vascular plants. Background reading on dimorphism, allometry, and transpiration provides the necessary foundation to develop questions and hypotheses. Some familiarity with R is necessary for both students and instructors, although the activities can be modified for analysis with Excel or another statistical package. These modules can be taught independently or together as a unit within a course. As stated in the AAAS document, <em>Vision and Change: A Call to Action</em>, the ability to use quantitative reasoning is a core competency that must be developed by all biology students. These modules address the call for instruction in quantitative reasoning and provide a hands-on active introduction to key tools that will be required to build students&rsquo; statistical repertoire in more advanced courses. <em>Primary Image:</em>&nbsp;A highlight of the three modules used in our introductory organismal biology course, including the use of calipers to test for dimorphism in the size of crayfish chelae (upper right), a leaf impression (lower right) from a hydrangea plant (lower left) used to test hypotheses about stomata densities, and the image of an <em>Echinococcus </em>tapeworm (upper left) to test hypotheses about allometry.&nbsp;&nbsp;

ГЕОДЕЗІЯ, КАРТОГРАФІЯ І АЕРОФОТОЗНІМАННЯ

The aim of the research is to diagnose the metrological characteristics of high-precision GNSS-observations by methods of non-classical error theory of measurements (NETM) based on Ukrainian reference stations. Methodology. We selected 72 GNSS reference stations, downloaded daily observation files from the LPI analysis center server, and created time series in the topocentric coordinate system. The duration of the time series is almost two years (March 24, 2019 - January 2, 2021). Using a specialized software package, the time series have been cleaned of offsets and breaks, seasonal effects, and the trend component has been removed. Verification of empirical distributions of errors was provided by the procedure of NETM on the recommendations offered by G. Jeffries and on the principles of hypothesis tests the theory according to Pearson's criterion. The main result of the research. It is established that the obtained time series of coordinates of reference GNSS stations do not confirm the hypothesis of their conformity to the normal Gaussian distribution law. NETM diagnostics of the accuracy of high-precision GNSS measurements, which is based on the use of confidence intervals for assessing the asymmetry and kurtosis of a significant sample, followed by the Pearson test, confirms the presence of weak, not removed from GNSS-processing, sources of systematic errors. Scientific novelty. The authors use the possibility of NETM to improve the processing of high-precision GNSS measurements and the need to take into account the sources of systematic errors. Failure to take into account certain factors creates the effect of shifting the time coordinate series, which, in turn, leads to subjective estimates of station velocity, i.e. their geodynamic interpretation. Practical significance. Research of the reasons for deviations of errors distribution from the established norms provides metrological literacy of carrying out high-precision GNSS measurements of large samples.

Reliabilities of Discrepancy Scores and Supplemental Tables for the WASI–II

We analyzed data from the WASI–II manual to determine discrepancy score reliabilities of the Verbal Comprehension (VCI) and Perceptual Reasoning (PRI) indexes and the four subtests in the child and adult standardization samples. Reliabilities of the VCI–PRI discrepancy scores range from .78 to .86 for children and .82 to .89 for adults and generally are large enough to justify hypothesis generation. Discrepancy score reliabilities of the subtests range from .64 to .82 and .66 to .84 for children and adults, respectively, and therefore must be considered on a score-by-score basis in formulating hypotheses. Tables are provided to identify significant differences between pairs of subtests and to determine ipsative strengths and weaknesses when each subtest is compared to the mean of four subtests. The use of confidence intervals for the interpretation of discrepancy scores is presented. If additional discrepancy score reliabilities and cut-offs are desired, the necessary formulas are provided.

Should We Be Confident in Published Research? A Case Study of Confidence Interval Reporting in Health Education and Behavior Research

Confidence intervals (CIs) have been highlighted as “the best” reporting device when reporting statistical findings. However, researchers often fail to maximize the utility of CIs in research. We seek to (a) present a primer on CIs; (b) outline reporting practices of health researchers; and (c) discuss implications for statistical best practice reporting in social science research. Approximately 1,950 peer-reviewed articles were examined from six health education, promotion, and behavior journals. We recorded: (a) whether the author(s) reported a CI; (b) whether the author(s) reported a CI estimate width, either numerical or visual; and (c) whether an associated effect size was reported alongside the CI. Of the 1,245 quantitative articles in the final sample, 46.5% (n = 580) reported confidence interval use; , and 518 provided numerical/visual interval estimates. Of the articles reporting CIs, 383 (64.2%) articles reported a CI with an associated effect size, meeting the American Psychological Association’s (APA) recommendation for statistical reporting best-practice. Health education literature demonstrates inconsistent statistical reporting practices, and falls short in employing best practices and consistently outlining the minimum expectations recommended by APA. In an effort to maximize utility and implications of health education, promotion, and behavior research, future investigations should provide comprehensive information regarding research findings.

In defense of group fuzzy AHP: A comparison of group fuzzy AHP and group AHP with confidence intervals

Group aggregation of the Analytic Hierarchy Process (AHP), both with crisp and fuzzy numbers, is a widely researched field in group multiple criteria decision-making. Typically, if uncertainty needs to be reflected in the outcome of an AHP, triangular fuzzy numbers are used, although this is a controversial method, as many argue that the traditional 1–9 scale used in crisp AHP introduces uncertainty to the decision-making process, leaving no need for fuzzification. This research introduces the use of confidence intervals around the aggregated group mean to estimate the score ranges generated through group fuzzy AHP (GFAHP), as confidence intervals are simpler to calculate and more familiar to many. A comparison of the score ranges resulting from GFAHP and group aggregation using crisp numbers with confidence intervals around the group mean score, aggregating on individual priorities using both the arithmetic mean and geometric mean, was completed. The concept of using confidence intervals on crisp scores to generate score ranges was implemented through a case study to select a new all-wheel drive crossover vehicle. This study shows that confidence intervals introduce excessive uncertainty to the decision-making problem.

Ο έλεγχος μηδενικών υποθέσεων: διαδικασία, παρανοήσεις και μερικές προτάσεις για καλύτερες πρακτικές

The rationale of Null Hypothesis Significance Testing (NHST) is described, and the consequences of its hybridism are discussed. The paper presents examples published in “PSYCHOLOGY: The Journal of the HPS” refer to NHST and interpret its outcomes. We examined the 445 articles published between 1992 and 2010. We noted misuses of NHST and searched for any use of confidence intervals or error bars or use of these to support interpretation. Part of the paper focuses on the statistical-reform debate and provides detailed guidance about good statistical practices in the analysis of research data and the interpretation of findings. The proposed guide does not fall into the trap of mandating the use of particular procedures; it rather aims to support readers’ understanding of research results.

Statistics in scientific articles published in the European Annals of Otorhinolaryngology Head & Neck Diseases

ObjectivesTo evaluate biostatistics in scientific articles published in the European Annals of Otorhinolaryngology Head & Neck Diseases. Materials and methodsRetrospective analysis of 76 scientific articles published in 2018 and 2019. The main goal was to describe the percentage of articles using biostatistics and to explore for potential associations with the article's main characteristics. Secondary goals were, within the group of articles using statistical tests, to describe the type of statistics used, the assessment of normality in case of comparison of mean values, the p-value threshold for significance, the use of confidence intervals, and power analysis. ResultsStatistics were used in 73.7% of articles, without any significant association with main characteristics. Within the group of articles using statistics, the tests used were parametric, non-parametric and not specified in 77.7%, 51.4% and 1.8% of cases, respectively. Normality was checked in 14.2% of article using parametric tests to evaluate mean values. The p-value significance threshold was set at .05, .01, .005 levels and not defined in 60.7%, 1.8%, 1.8% and 35.7% of articles, respectively, while confidence intervals and power analyses were documented in 10.7% and 5.3%, respectively. ConclusionThis article underlines the need for better use of statistics in the European Annals of Otorhinolaryngology Head & Neck Diseases, to improve the quality of scientific articles published in the organ of written expression of the French and International French-speaking Societies of Otorhinolaryngology, and to support the ongoing move toward better medical science.

The efficacy and safety of EGFR-TKI combined with chemotherapy in non-small cell lung cancer (NSCLC) patients with EGFR co-mutation with other oncogenic alterations.

e21666 Background: Previous studies indicated primary resistance to EGFR-TKIs might occur in EGFR co-mutation with other oncogenic alterations, including TP53, KRAS, PIK3CA and so on. However, the optimal therapeutic regimens for EGFR co-mutation other oncogenic alterations were still unknown. This respective observation study aimed to evaluate the efficacy and safety of EGFR-TKIs combined with chemotherapy in this sub-population, in order to offer new treatments in clinical practice. Methods: In this retrospectively study, from March 2017 to November 2019 advanced NSCLC patients with EGFR co-mutation with other oncogenic alterations in Medical Oncology of Respiratory, Affiliated Tumor Hospital of Guangxi Medical University were screened for eligibility. All included patients were administrated with EGFR-TKIs combined with platinum-based chemotherapy or EGFR-TKIs monotherapy. The clinicopathological data of the patients, and the efficacy and safety of treatment were accorded for statistic analysis. The Kaplan-Meier method was used to estimate median PFS and OS. For all analyses, p value &lt; 0.05 was considered statistically significant, and confidence interval use 95% confidence level. The primary outcome was Progression-free survival (PFS), and Overall survival (OS), Disease control rate (DCR) and safety profile were considered to be the secondary endpoints. Results: Total 23 patients were enrolled in this retrospectively study. The median age of the combination and monotherapy group was 58.7± 8.8 and 58.9 ± 13.5years, respectively. The frequency of female patients was 53.8% and 40% in monotherapy and combination group, respectively. The median PFS (mPFS) was 5.03 months (95% CI: 1.16- 8.9) and not reach in combination therapy group (P = 0.004). No significantly different in mOS was observed in two groups (P = 0.244). The DCR was 92.3% and 100% in monotherapy and combination group, respectively. In combination group, the common adverse events of grade 1 or 2 were adverse reactions of the blood system and rash (40%). Treatment-related grade 3 or 4 toxicity appeared in 3 patients and no patients harbored treatment-related above grade 4 side effects. No cases of treatment-related death occurred. Conclusions: EGFR-TKIs combined with chemotherapy was effective in NSLCL patients with EGFR co-mutation with other oncogenic alterations and side-effects were tolerable. The outcomes of this study should be confirmed by prospective clinical trials in future.

Constructing Fuzzy Hypothesis Methods to Determine Critical-To-Quality Service Items

This paper constructs a performance evaluation matrix (PEM) with beta distribution. Beta is between zero and one, making it a suitable indicator to describe customer ratings of importance and satisfaction from 0% to 100%. According to the spirit of ceaseless improvement put forward by total quality management, the average ratings are set as the standard, and then the coordinates of each satisfaction and importance item is located in the performance areas. This makes it easy to identify critical-to-quality items that require improvement. However, the data collection method of questionnaires inevitably involves sampling error, and the opinions of customers are often ambiguous. To solve these problems, we constructed a fuzzy testing method based on confidence intervals. The use of confidence intervals decreases the chance of misjudgment caused by sampling errors, and more precisely gets closer to customers’ voices. This result is more reasonable than the traditional statistical testing principle. The proposed methods are applied to assessment of a computer-assisted language learning (CALL) system to display their competence.

Applied linguistics research in three decades: a methodological synthesis of graduate theses in an EFL context

The recent years have witnessed an increasing awareness in methodological issues in the field of applied linguistics, which brought about what Byrnes (Mod Lang J 97:825–827, 2013) and Plonsky (The Routledge handbook of instructed second language research, Routledge, New York, pp 505–521, 2017) referred to as “methodological turn” and “methodological awareness”, respectively. To contribute to this fresh line of research, this review, drawing on the methodological synthetic techniques, sought to describe and evaluate the aggregative and developmental status of experimental research in an EFL context. Having developed an experimental coding sheet and a manual book, we selected the eligible studies based on informed included/excluded criteria. As a result, we analyzed 285 unpublished applied linguistics MA theses which were distributed over a 30-year period. The cumulative results revealed a set of strengths and deficiencies across the data set. Of notable findings were inconsistent reporting practices (e.g., low statistical power, the minimum use of confidence intervals and effect sizes, and inconsistent reporting of p values). However, signs of improvement over three decades were conspicuous (e.g., reporting effect sizes, checking statistical assumptions, etc.). Implications and recommendations for the research methodologists, postgraduate students, and policy makers are discussed.