scholarly journals Statistical Reliability of 10 Years of Cyber Security User Studies

2021 ◽  
pp. 171-190
Author(s):  
Thomas Groß
Keyword(s):  
Publication Bias ◽  
Cyber Security ◽  
Power Distribution ◽  
Statistical Power ◽  
Total Sample ◽  
User Studies ◽  
Effect Sizes ◽  
Standard Errors ◽  
Statistical Reliability ◽  
Statistical Inferences

AbstractBackground. In recent years, cyber security user studies have been appraised in meta-research, mostly focusing on the completeness of their statistical inferences and the fidelity of their statistical reporting. However, estimates of the field’s distribution of statistical power and its publication bias have not received much attention.Aim. In this study, we aim to estimate the effect sizes and their standard errors present as well as the implications on statistical power and publication bias.Method. We built upon a published systematic literature review of 146 user studies in cyber security (2006–2016). We took into account 431 statistical inferences including t-, $$\chi ^2$$ χ 2 -, r-, one-way F-tests, and Z-tests. In addition, we coded the corresponding total sample sizes, group sizes and test families. Given these data, we established the observed effect sizes and evaluated the overall publication bias. We further computed the statistical power vis-à-vis of parametrized population thresholds to gain unbiased estimates of the power distribution.Results. We obtained a distribution of effect sizes and their conversion into comparable log odds ratios together with their standard errors. We, further, gained funnel-plot estimates of the publication bias present in the sample as well as insights into the power distribution and its consequences.Conclusions. Through the lenses of power and publication bias, we shed light on the statistical reliability of the studies in the field. The upshot of this introspection is practical recommendations on conducting and evaluating studies to advance the field.

scholarly journals The earth is flat (p>0.05): Significance thresholds and the crisis of unreplicable research

2017 ◽  
Author(s):  
Valentin Amrhein ◽  
Fränzi Korner-Nievergelt ◽  
Tobias Roth
Keyword(s):  
Publication Bias ◽  
Null Hypothesis ◽  
Statistical Power ◽  
Alternative Hypothesis ◽  
Statistical Significance ◽  
Practical Importance ◽  
Decision Rules ◽  
Effect Sizes ◽  
P Values ◽  
True Effect

The widespread use of 'statistical significance' as a license for making a claim of a scientific finding leads to considerable distortion of the scientific process (American Statistical Association, Wasserstein & Lazar 2016). We review why degrading p-values into 'significant' and 'nonsignificant' contributes to making studies irreproducible, or to making them seem irreproducible. A major problem is that we tend to take small p-values at face value, but mistrust results with larger p-values. In either case, p-values can tell little about reliability of research, because they are hardly replicable even if an alternative hypothesis is true. Also significance (p≤0.05) is hardly replicable: at a realistic statistical power of 40%, given that there is a true effect, only one in six studies will significantly replicate the significant result of another study. Even at a good power of 80%, results from two studies will be conflicting, in terms of significance, in one third of the cases if there is a true effect. This means that a replication cannot be interpreted as having failed only because it is nonsignificant. Many apparent replication failures may thus reflect faulty judgement based on significance thresholds rather than a crisis of unreplicable research. Reliable conclusions on replicability and practical importance of a finding can only be drawn using cumulative evidence from multiple independent studies. However, applying significance thresholds makes cumulative knowledge unreliable. One reason is that with anything but ideal statistical power, significant effect sizes will be biased upwards. Interpreting inflated significant results while ignoring nonsignificant results will thus lead to wrong conclusions. But current incentives to hunt for significance lead to publication bias against nonsignificant findings. Data dredging, p-hacking and publication bias should be addressed by removing fixed significance thresholds. Consistent with the recommendations of the late Ronald Fisher, p-values should be interpreted as graded measures of the strength of evidence against the null hypothesis. Also larger p-values offer some evidence against the null hypothesis, and they cannot be interpreted as supporting the null hypothesis, falsely concluding that 'there is no effect'. Information on possible true effect sizes that are compatible with the data must be obtained from the observed effect size, e.g., from a sample average, and from a measure of uncertainty, such as a confidence interval. We review how confusion about interpretation of larger p-values can be traced back to historical disputes among the founders of modern statistics. We further discuss potential arguments against removing significance thresholds, such as 'we need more stringent decision rules', 'sample sizes will decrease' or 'we need to get rid of p-values'.

scholarly journals The earth is flat (p > 0.05): significance thresholds and the crisis of unreplicable research

PeerJ ◽  
2017 ◽  
Vol 5 ◽  
pp. e3544 ◽  
Author(s):  
Valentin Amrhein ◽  
Fränzi Korner-Nievergelt ◽  
Tobias Roth
Keyword(s):  
Publication Bias ◽  
Null Hypothesis ◽  
Statistical Power ◽  
Statistical Significance ◽  
Practical Importance ◽  
Effect Sizes ◽  
Point Estimate ◽  
Selective Reporting ◽  
Interval Estimate ◽  
True Effect

The widespread use of ‘statistical significance’ as a license for making a claim of a scientific finding leads to considerable distortion of the scientific process (according to the American Statistical Association). We review why degradingp-values into ‘significant’ and ‘nonsignificant’ contributes to making studies irreproducible, or to making them seem irreproducible. A major problem is that we tend to take smallp-values at face value, but mistrust results with largerp-values. In either case,p-values tell little about reliability of research, because they are hardly replicable even if an alternative hypothesis is true. Also significance (p ≤ 0.05) is hardly replicable: at a good statistical power of 80%, two studies will be ‘conflicting’, meaning that one is significant and the other is not, in one third of the cases if there is a true effect. A replication can therefore not be interpreted as having failed only because it is nonsignificant. Many apparent replication failures may thus reflect faulty judgment based on significance thresholds rather than a crisis of unreplicable research. Reliable conclusions on replicability and practical importance of a finding can only be drawn using cumulative evidence from multiple independent studies. However, applying significance thresholds makes cumulative knowledge unreliable. One reason is that with anything but ideal statistical power, significant effect sizes will be biased upwards. Interpreting inflated significant results while ignoring nonsignificant results will thus lead to wrong conclusions. But current incentives to hunt for significance lead to selective reporting and to publication bias against nonsignificant findings. Data dredging,p-hacking, and publication bias should be addressed by removing fixed significance thresholds. Consistent with the recommendations of the late Ronald Fisher,p-values should be interpreted as graded measures of the strength of evidence against the null hypothesis. Also largerp-values offer some evidence against the null hypothesis, and they cannot be interpreted as supporting the null hypothesis, falsely concluding that ‘there is no effect’. Information on possible true effect sizes that are compatible with the data must be obtained from the point estimate, e.g., from a sample average, and from the interval estimate, such as a confidence interval. We review how confusion about interpretation of largerp-values can be traced back to historical disputes among the founders of modern statistics. We further discuss potential arguments against removing significance thresholds, for example that decision rules should rather be more stringent, that sample sizes could decrease, or thatp-values should better be completely abandoned. We conclude that whatever method of statistical inference we use, dichotomous threshold thinking must give way to non-automated informed judgment.

scholarly journals The earth is flat (p>0.05): Significance thresholds and the crisis of unreplicable research

2017 ◽  
Author(s):  
Valentin Amrhein ◽  
Fränzi Korner-Nievergelt ◽  
Tobias Roth
Keyword(s):  
Publication Bias ◽  
Null Hypothesis ◽  
Statistical Power ◽  
Statistical Significance ◽  
Practical Importance ◽  
Effect Sizes ◽  
Selective Reporting ◽  
Interval Estimate ◽  
P Values ◽  
True Effect

The widespread use of 'statistical significance' as a license for making a claim of a scientific finding leads to considerable distortion of the scientific process (according to the American Statistical Association). We review why degrading p-values into 'significant' and 'nonsignificant' contributes to making studies irreproducible, or to making them seem irreproducible. A major problem is that we tend to take small p-values at face value, but mistrust results with larger p-values. In either case, p-values tell little about reliability of research, because they are hardly replicable even if an alternative hypothesis is true. Also significance (p≤0.05) is hardly replicable: at a good statistical power of 80%, two studies will be 'conflicting', meaning that one is significant and the other is not, in one third of the cases if there is a true effect. A replication can therefore not be interpreted as having failed only because it is nonsignificant. Many apparent replication failures may thus reflect faulty judgment based on significance thresholds rather than a crisis of unreplicable research. Reliable conclusions on replicability and practical importance of a finding can only be drawn using cumulative evidence from multiple independent studies. However, applying significance thresholds makes cumulative knowledge unreliable. One reason is that with anything but ideal statistical power, significant effect sizes will be biased upwards. Interpreting inflated significant results while ignoring nonsignificant results will thus lead to wrong conclusions. But current incentives to hunt for significance lead to selective reporting and to publication bias against nonsignificant findings. Data dredging, p-hacking, and publication bias should be addressed by removing fixed significance thresholds. Consistent with the recommendations of the late Ronald Fisher, p-values should be interpreted as graded measures of the strength of evidence against the null hypothesis. Also larger p-values offer some evidence against the null hypothesis, and they cannot be interpreted as supporting the null hypothesis, falsely concluding that 'there is no effect'. Information on possible true effect sizes that are compatible with the data must be obtained from the point estimate, e.g., from a sample average, and from the interval estimate, such as a confidence interval. We review how confusion about interpretation of larger p-values can be traced back to historical disputes among the founders of modern statistics. We further discuss potential arguments against removing significance thresholds, for example that decision rules should rather be more stringent, that sample sizes could decrease, or that p-values should better be completely abandoned. We conclude that whatever method of statistical inference we use, dichotomous threshold thinking must give way to non-automated informed judgment.

scholarly journals Are Most Published Research Findings False In A Continuous Universe?

2021 ◽  
Author(s):  
Kleber Neves ◽  
Pedro Batista Tan ◽  
Olavo Bohrer Amaral
Keyword(s):  
Publication Bias ◽  
Effect Size ◽  
Statistical Power ◽  
Statistical Significance ◽  
Significance Test ◽  
Effect Sizes ◽  
Diagnostic Screening ◽  
Research Findings ◽  
Published Research ◽  
Effect Size Distribution

Diagnostic screening models for the interpretation of null hypothesis significance test (NHST) results have been influential in highlighting the effect of selective publication on the reproducibility of the published literature, leading to John Ioannidis’ much-cited claim that most published research findings are false. These models, however, are typically based on the assumption that hypotheses are dichotomously true or false, without considering that effect sizes for different hypotheses are not the same. To address this limitation, we develop a simulation model that overcomes this by modeling effect sizes explicitly using different continuous distributions, while retaining other aspects of previous models such as publication bias and the pursuit of statistical significance. Our results show that the combination of selective publication, bias, low statistical power and unlikely hypotheses consistently leads to high proportions of false positives, irrespective of the effect size distribution assumed. Using continuous effect sizes also allows us to evaluate the degree of effect size overestimation and prevalence of estimates with the wrong signal in the literature, showing that the same factors that drive false-positive results also lead to errors in estimating effect size direction and magnitude. Nevertheless, the relative influence of these factors on different metrics varies depending on the distribution assumed for effect sizes. The model is made available as an R ShinyApp interface, allowing one to explore features of the literature in various scenarios.

Sample-Size Planning for More Accurate Statistical Power: A Method Adjusting Sample Effect Sizes for Publication Bias and Uncertainty

2017 ◽  
Vol 28 (11) ◽  
pp. 1547-1562 ◽  
Author(s):  
Samantha F. Anderson ◽  
Ken Kelley ◽  
Scott E. Maxwell
Keyword(s):  
Sample Size ◽  
Publication Bias ◽  
Effect Size ◽  
Statistical Power ◽  
Web Applications ◽  
R Package ◽  
Effect Sizes ◽  
Alternative Approach ◽  
Sample Size Planning ◽  
User Friendly

The sample size necessary to obtain a desired level of statistical power depends in part on the population value of the effect size, which is, by definition, unknown. A common approach to sample-size planning uses the sample effect size from a prior study as an estimate of the population value of the effect to be detected in the future study. Although this strategy is intuitively appealing, effect-size estimates, taken at face value, are typically not accurate estimates of the population effect size because of publication bias and uncertainty. We show that the use of this approach often results in underpowered studies, sometimes to an alarming degree. We present an alternative approach that adjusts sample effect sizes for bias and uncertainty, and we demonstrate its effectiveness for several experimental designs. Furthermore, we discuss an open-source R package, BUCSS, and user-friendly Web applications that we have made available to researchers so that they can easily implement our suggested methods.

scholarly journals The Empirical Status of Mindfulness-Based Interventions: A Systematic Review of 44 Meta-Analyses of Randomized Controlled Trials

2021 ◽  
pp. 174569162096877
Author(s):  
Simon B. Goldberg ◽  
Kevin M. Riordan ◽  
Shufang Sun ◽  
Richard J. Davidson
Keyword(s):  
Adverse Effects ◽  
Randomized Controlled Trials ◽  
Publication Bias ◽  
Statistical Power ◽  
Effect Sizes ◽  
Controlled Trials ◽  
Randomized Controlled ◽  
Wide Range ◽  
Meta Analyses ◽  
Active Controls

In response to questions regarding the scientific basis for mindfulness-based interventions (MBIs), we evaluated their empirical status by systematically reviewing meta-analyses of randomized controlled trials (RCTs). We searched six databases for effect sizes based on four or more trials that did not combine passive and active controls. Heterogeneity, moderators, tests of publication bias, risk of bias, and adverse effects were also extracted. Representative effect sizes based on the largest number of studies were identified across a wide range of populations, problems, interventions, comparisons, and outcomes (PICOS). A total of 160 effect sizes were reported in 44 meta-analyses ( k = 336 RCTs, N = 30,483 participants). MBIs showed superiority to passive controls across most PICOS ( ds = 0.10–0.89). Effects were typically smaller and less often statistically significant compared with active controls. MBIs were similar or superior to specific active controls and evidence-based treatments. Heterogeneity was typically moderate. Few consistent moderators were found. Results were generally robust to publication bias, although other important sources of bias were identified. Reporting of adverse effects was inconsistent. Statistical power may be lacking in meta-analyses, particularly for comparisons with active controls. Because MBIs show promise across some PICOS, future RCTs and meta-analyses should build on identified strengths and limitations of this literature.

scholarly journals The earth is flat (p>0.05): Significance thresholds and the crisis of unreplicable research

2017 ◽  
Author(s):  
Valentin Amrhein ◽  
Fränzi Korner-Nievergelt ◽  
Tobias Roth
Keyword(s):  
Publication Bias ◽  
Null Hypothesis ◽  
Statistical Power ◽  
Statistical Significance ◽  
Practical Importance ◽  
Effect Sizes ◽  
Selective Reporting ◽  
Interval Estimate ◽  
P Values ◽  
True Effect

The widespread use of 'statistical significance' as a license for making a claim of a scientific finding leads to considerable distortion of the scientific process (according to the American Statistical Association). We review why degrading p-values into 'significant' and 'nonsignificant' contributes to making studies irreproducible, or to making them seem irreproducible. A major problem is that we tend to take small p-values at face value, but mistrust results with larger p-values. In either case, p-values tell little about reliability of research, because they are hardly replicable even if an alternative hypothesis is true. Also significance (p≤0.05) is hardly replicable: at a good statistical power of 80%, two studies will be 'conflicting', meaning that one is significant and the other is not, in one third of the cases if there is a true effect. A replication can therefore not be interpreted as having failed only because it is nonsignificant. Many apparent replication failures may thus reflect faulty judgment based on significance thresholds rather than a crisis of unreplicable research. Reliable conclusions on replicability and practical importance of a finding can only be drawn using cumulative evidence from multiple independent studies. However, applying significance thresholds makes cumulative knowledge unreliable. One reason is that with anything but ideal statistical power, significant effect sizes will be biased upwards. Interpreting inflated significant results while ignoring nonsignificant results will thus lead to wrong conclusions. But current incentives to hunt for significance lead to selective reporting and to publication bias against nonsignificant findings. Data dredging, p-hacking, and publication bias should be addressed by removing fixed significance thresholds. Consistent with the recommendations of the late Ronald Fisher, p-values should be interpreted as graded measures of the strength of evidence against the null hypothesis. Also larger p-values offer some evidence against the null hypothesis, and they cannot be interpreted as supporting the null hypothesis, falsely concluding that 'there is no effect'. Information on possible true effect sizes that are compatible with the data must be obtained from the point estimate, e.g., from a sample average, and from the interval estimate, such as a confidence interval. We review how confusion about interpretation of larger p-values can be traced back to historical disputes among the founders of modern statistics. We further discuss potential arguments against removing significance thresholds, for example that decision rules should rather be more stringent, that sample sizes could decrease, or that p-values should better be completely abandoned. We conclude that whatever method of statistical inference we use, dichotomous threshold thinking must give way to non-automated informed judgment.

How to Detect Publication Bias in Psychological Research

2019 ◽  
Vol 227 (4) ◽  
pp. 261-279 ◽  
Author(s):  
Frank Renkewitz ◽  
Melanie Keiner
Keyword(s):  
Publication Bias ◽  
Effect Size ◽  
Statistical Power ◽  
Type I Error ◽  
Psychological Research ◽  
Type I ◽  
True Effect Size ◽  
Questionable Research Practices ◽  
True Effect ◽  
Meta Analyses

Abstract. Publication biases and questionable research practices are assumed to be two of the main causes of low replication rates. Both of these problems lead to severely inflated effect size estimates in meta-analyses. Methodologists have proposed a number of statistical tools to detect such bias in meta-analytic results. We present an evaluation of the performance of six of these tools. To assess the Type I error rate and the statistical power of these methods, we simulated a large variety of literatures that differed with regard to true effect size, heterogeneity, number of available primary studies, and sample sizes of these primary studies; furthermore, simulated studies were subjected to different degrees of publication bias. Our results show that across all simulated conditions, no method consistently outperformed the others. Additionally, all methods performed poorly when true effect sizes were heterogeneous or primary studies had a small chance of being published, irrespective of their results. This suggests that in many actual meta-analyses in psychology, bias will remain undiscovered no matter which detection method is used.

The Limits of Ego Depletion

2019 ◽  
Vol 50 (5-6) ◽  
pp. 292-304 ◽  
Author(s):  
Mario Wenzel ◽  
Marina Lind ◽  
Zarah Rowland ◽  
Daniela Zahn ◽  
Thomas Kubiak
Keyword(s):  
Research Agenda ◽  
Statistical Power ◽  
Interindividual Variability ◽  
Ego Depletion ◽  
Crossover Design ◽  
Effect Sizes ◽  
Future Research ◽  
Future Research Agenda ◽  
Depletion Effect ◽  
Within Subjects

Abstract. Evidence on the existence of the ego depletion phenomena as well as the size of the effects and potential moderators and mediators are ambiguous. Building on a crossover design that enables superior statistical power within a single study, we investigated the robustness of the ego depletion effect between and within subjects and moderating and mediating influences of the ego depletion manipulation checks. Our results, based on a sample of 187 participants, demonstrated that (a) the between- and within-subject ego depletion effects only had negligible effect sizes and that there was (b) large interindividual variability that (c) could not be explained by differences in ego depletion manipulation checks. We discuss the implications of these results and outline a future research agenda.

Identification of and Correction for Publication Bias: Comment

2019 ◽  
Author(s):  
Amanda Kvarven ◽  
Eirik Strømland ◽  
Magnus Johannesson
Keyword(s):  
Publication Bias ◽  
False Positive ◽  
Large Scale ◽  
Meta Analysis ◽  
False Positive Rate ◽  
Effect Sizes ◽  
Replication Studies ◽  
Moderate Reduction ◽  
Positive Rate ◽  
Meta Analyses

Andrews & Kasy (2019) propose an approach for adjusting effect sizes in meta-analysis for publication bias. We use the Andrews-Kasy estimator to adjust the result of 15 meta-analyses and compare the adjusted results to 15 large-scale multiple labs replication studies estimating the same effects. The pre-registered replications provide precisely estimated effect sizes, which do not suffer from publication bias. The Andrews-Kasy approach leads to a moderate reduction of the inflated effect sizes in the meta-analyses. However, the approach still overestimates effect sizes by a factor of about two or more and has an estimated false positive rate of between 57% and 100%.

Sign in / Sign up

Export Citation Format

Share Document