Search

Test equating is a statistical procedure to ensure that scores from different test forms can be used interchangeably. There are several methodologies available to perform equating, some of which are based on the Classical Test Theory (CTT) framework and others are based on the Item Response Theory (IRT) framework. This article compares equating transformations originated from three different frameworks, namely IRT Observed-Score Equating (IRTOSE), Kernel Equating (KE), and IRT Kernel Equating (IRTKE). The comparisons were made under different data-generating scenarios, which include the development of a novel data-generation procedure that allows the simulation of test data without relying on IRT parameters while still providing control over some test score properties such as distribution skewness and item difficulty. Our results suggest that IRT methods tend to provide better results than KE even when the data are not generated from IRT processes. KE might be able to provide satisfactory results if a proper pre-smoothing solution can be found, while also being much faster than IRT methods. For daily applications, we recommend observing the sensibility of the results to the equating method, minding the importance of good model fit and meeting the assumptions of the framework.

Symbolic boundaries—the conceptual markers people use to differentiate themselves from others—are at the root of intergroup social boundaries. When the social boundaries between groups are breached, the tendency for people to erect and maintain symbolic boundaries intensifies. Drawing on extant perspectives on boundary maintenance, we distinguish between two strategies that people pursue in maintaining symbolic boundaries: boundary retention—entrenching themselves in pre-existing symbolic distinctions—and boundary reformation—innovating new forms of symbolic distinction. Traditional approaches to measuring symbolic boundaries—interviews, participant- observation, and self-reports—are ill-suited to detecting fine-grained variation in these two forms of boundary maintenance. To overcome this limitation, we use the tools of computational linguistics and machine learning to develop a novel approach to measuring symbolic boundaries based on interactional language use between group members before and after they come into contact with one another. We construct measures of boundary retention and reformation using random forest classifiers that quantify group differences based on pre- and post-contact linguistic styles. We demonstrate the utility of this method by applying it to a corpus of email communications from a mid-sized financial services firm that acquired and integrated two smaller firms. We find that: (a) the persistence of symbolic boundaries can be detected for up to 18 months after a merger; (b) acquired employees exhibit more boundary reformation and less boundary retention than their counterparts from the acquiring firm; and (c) individuals engage in more boundary retention, but not reformation, when their local work environment is more densely populated by ingroup members. We discuss implications of these findings for the study of culture in a wide range of intergroup contexts and for computational approaches to measuring culture.

Two papers have appeared evaluating interferences in glucose meters. These studies are method comparisons with the added information of the medication(s) taken by the subjects. This paper contrasts a traditional interference study with the method comparison protocols. Unlike the advice in CLSI EP7, a substance that interferes should be reported even if the level of interference is clinically acceptable. The evidence of no clinically important interference in the method comparison protocol is very weak, and there is no possibility to detect statistically significant interferences. I provide an example where vitamin C at a therapeutic level was within clinical error limits, but when the concentration was at levels used to treat cancer, there was bias well above clinically acceptable limits.

The partial potential impact fraction describes the proportion of disease cases that can be prevented if the distribution of modifiable continuous exposures is shifted in a population, while other risk factors are not modified. It is a useful quantity for evaluating the burden of disease in epidemiologic and public health studies. When exposures are measured with error, the partial potential impact fraction estimates may be biased, which necessitates methods to correct for the exposure measurement error. Motivated by the health professionals follow-up study, we develop a Bayesian approach to adjust for exposure measurement error when estimating the partial potential impact fraction under the main study/internal validation study design. We adopt the reclassification approach that leverages the strength of the main study/internal validation study design and clarifies transportability assumptions for valid inference. We assess the finite-sample performance of both the point and credible interval estimators via extensive simulations and apply the proposed approach in the health professionals follow-up study to estimate the partial potential impact fraction for colorectal cancer incidence under interventions exploring shifting the distributions of red meat, alcohol, and/or folate intake.

Background Misinterpretations of the p-value in null-hypothesis statistical testing are common. We aimed to determine the implications of observed p-values in critical care randomized controlled trials (RCTs). Methods We included three cohorts of published RCTs: Adult-RCTs reporting a mortality outcome, Pediatric-RCTs reporting a mortality outcome, and recent Consecutive-RCTs reporting p-value ≤.10 in six higher-impact journals. We recorded descriptive information from RCTs. Reverse Bayesian implications of obtained p-values were calculated, reported as percentages with inter-quartile ranges. Results Obtained p-value was ≤.005 in 11/216 (5.1%) Adult-RCTs, 2/120 (1.7%) Pediatric-RCTs, and 37/90 (41.1%) Consecutive-RCTs. An obtained p-value .05–.0051 had high False Positive Rates; in Adult-RCTs, minimum (assuming prior probability of the alternative hypothesis was 50%) and realistic (assuming prior probability of the alternative hypothesis was 10%) False Positive Rates were 16.7% [11.2, 21.8] and 64.3% [53.2, 71.4]. An obtained p-value ≤.005 had lower False Positive Rates; in Adult-RCTs the realistic False Positive Rate was 7.7% [7.7, 16.0]. The realistic probability of the alternative hypothesis for obtained p-value .05–.0051 (ie, Positive Predictive Value) was 28.0% [24.1, 34.8], 30.6% [27.7, 48.5], 29.3% [24.3, 41.0], and 32.7% [24.1, 43.5] for Adult-RCTs, Pediatric-RCTs, Consecutive-RCTs primary and secondary outcome, respectively. The maximum Positive Predictive Value for p-value category .05–.0051 was median 77.8%, 79.8%, 78.8%, and 81.4% respectively. To have maximum or realistic Positive Predictive Value >90% or >80%, RCTs needed to have obtained p-value ≤.005. The credibility of p-value .05–.0051 findings were easy to challenge, and the credibility to rule-out an effect with p-value >.05 to .10 was low. The probability that a replication study would obtain p-value ≤.05 did not approach 90% unless the obtained p-value was ≤.005. Conclusions Unless the obtained p-value was ≤.005, the False Positive Rate was high, and the Positive Predictive Value and probability of replication of “statistically significant” findings were low.

Minimization is among the most common methods for controlling baseline covariate imbalance at the randomization phase of clinical trials. Previous studies have found that minimization does not preserve allocation randomness as well as other methods, such as minimal sufficient balance, making it more vulnerable to allocation predictability and selection bias. Additionally, minimization has been shown in simulation studies to inadequately control serious covariate imbalances when modest biased coin probabilities (≤0.65) are used. This current study extends the investigation of randomization methods to the analysis phase, comparing the impact of treatment allocation methods on power and bias in estimating treatment effects on a binary outcome using logistic regression. Power and bias in the estimation of treatment effect was found to be comparable across complete randomization, minimization, and minimal sufficient balance in unadjusted analyses. Further, minimal sufficient balance was found to have the most modest impact on power and the least bias in covariate-adjusted analyses. The minimal sufficient balance method is recommended for use in clinical trials as an alternative to minimization when covariate-adaptive subject randomization takes place.

Using the lumbar vertebra for age estimation is helpful in cases when skeletal remains are incomplete and typical skeletal age indicators are absent. This study aimed to apply an image analysis method in extracting black pixel variables for age estimation by using the radiographic images of lumbar vertebra in a Thai population. All lumbar vertebrae L1–L5 of 220 (110 males and 110 females) from Thai individuals of known sex and ages were studied. The variables of Total Percentage of black pixels (TP), Mean Percentage of black pixels (MP), and Ratio of black to white pixels (BW), were calculated to assess the relationship between black pixel variables and aging. Equations were formulated using linear regression analysis. The results of this study indicated three variables of the lumbar vertebrae had significantly positive correlations with age. The correlation between parameters with age in males ranged 0.211–0.419, while the range in females was 0.219–0.458. The appropriate linear regression equation with the total and mean percentages of black pixel variables shows Age = −1.348+0.871 (TP) +0.514 (MP) of L4 for males (SEE; 15.4 years), and Age = 5.338 +0.316 (TP) +0.952 (MP) of L1 for females (SEE; 13.8 years). Age estimation using an image analysis method is an alternative to investigating the trabecular structure. The black pixel variable is not the actual value of bone density. However, it is useful to study its relationship with aging.

Experimental research by political scientists on elites has grown dramatically in recent years. Experimenting on and with elites raises important questions, both practical and ethical. Elites are busy people, doing important work under public scrutiny. Therefore, any experiments that use up political elites’ time, risk impairing their ability to do their jobs as well as possible, or put at risk the larger research community’s access to elites should be avoided. Nevertheless, despite these risks and challenges, we argue experimenting with elites has enough benefits both to the research community and to elites themselves, that it should still be done. The relevant question then becomes how should we think about doing experiments with political elites? We propose a framework of value-added and transparent experiments. Our framework is guided by the following two simple rules: Elite subjects should individually benefit from the process of doing the experiment. It should add value to their role as representatives. Second, the identity of the researchers and purposes of the experiment should be transparent. As we argue, these two combined features can still accommodate a large range of experiments, can creatively spark researchers to think up new designs and can protect access to elites for future research. We review two such examples at the end of this essay.

Generalised pseudo-values have been suggested to evaluate the impact of allogeneic stem cell transplantation on childhood leukaemia. The approach compares long-term survival of two cohorts defined by the availability or non-availability of suitable donors for stem cell transplantation. A patient's cohort membership becomes known only after completed donor search with or without an identified donor. If a patient suffers an event during donor search, stem cell transplantation will no longer be indicated. In such a case, donor search will be ceased and cohort membership will remain unknown. The generalised pseudo-values approach considers donor identification as binary time-dependent covariate and uses inverse-probability-of-censoring weighting to adjust for non-identified donors. The approach leads to time-consuming computations due to multiple redefinitions of the risk set for pseudo-value calculation and an explicit adjustment for waiting-time bias. Here, the problem is looked at from a different angle. By considering the probability that a donor would have been identified after ceasing of donor search, weights for common pseudo-values are defined. This leads to a faster alternative approach as only a single risk set is necessary. Extensive computer simulations show that both, the generalised and the new weighted pseudo-values approach, provide approximately unbiased estimates. Confidence interval coverage is satisfactory for typical clinical scenarios. In situations, where donor identification takes considerably longer than usual, the weighted pseudo-values approach is preferable. Both approaches complement each other as they have different potential in addressing further aspects of the underlying medical question.

The current study was planned to test the validity and reliability of the Turkish version of the COVID-19 Literacy Scale. The sample of the study was taken from 473 individuals. In this study, language validity, content validity and construct validity were examined to determine the validity of the scale. Its reliability was evaluated by internal consistency, split-half reliability, and test-retest reliability method. It was defined that the scale has a two-factor structure as a result of EFA and its factor loadings are in the appropriate range (0.852–0.324). According to the CFA result, it was determined that the model-data fit was at a good level. The Cronbach values for the whole scale and subscales were .92, .90, and .87, respectively. It was observed that the test-retest value was .95. It was concluded that the Turkish form of the COVID-19 Literacy Scale is a reliable and valid tool.

The International Civil Aviation Organization identifies departure and arrival punctuality as on-time key performance indicators. However, these metrics assume a flight’s delay is a result of either the origin or destination airport, providing limited information on where delay should be mitigated in the U.S. National Airspace System (NAS). This study evaluates the relationship between delay propagation magnitude, delay causal factor, airport size, and charged facility (airport or Air Route Traffic Control Center), to examine if certain delays take longer to dissipate. First, using flights from July 2018, results show that most delay propagation chains originate at large-hub airports. However, these delays were the quickest to recover. Second, this study presents a regression model, predicting total propagated delay using fixed effects based on the weather region where the original delay occurred. Each additional flight affected by downstream delay adds 18.7 min on average to total arrival delay in a propagation chain. Additionally, if weather was the original causal factor, total propagated delay increased by 11.6 min compared with non-weather delays. Lastly, this study compares delay propagation in July 2018 and July 2020. Results show uneven impacts of the coronavirus disease 2019 (COVID-19) across the large-hub airports. Some of the investigated airports did not witness large improvements in average delay per delayed flight, warranting further research in the future. While delay and delay propagation have not been completely eradicated in the NAS during the COVID-19 pandemic, findings suggest that both have significantly declined on average.

In general, the change point problem considers inference of a change in distribution for a set of time-ordered observations. This has applications in a large variety of fields, and can also apply to survival data. In survival analysis, most existing methods compare two treatment groups for the entirety of the study period. Some treatments may take a length of time to show effects in subjects. This has been called the time-lag effect in the literature, and in cases where time-lag effect is considerable, such methods may not be appropriate to detect significant differences between two groups. In this paper, we propose a novel non-parametric approach for estimating the point of treatment time-lag effect by using an empirical divergence measure. Theoretical properties of the estimator are studied. The results from the simulated data and the applications to real data examples support our proposed method.

When a garment is given a certain amount of ease, the body shape characteristics and matching degree of air gap distribution determine the aesthetic fit of garment sculpt. The purpose of this study is to investigate the relationship between the aesthetic fit and air gap distribution of the bust and waist sections. Three factors, the ratio of the horizontal radius vector to the bust and waist sections ( HrvB, HrvW) and the location and proportion of darts ( DL, DP), have been considered in this analysis. Ten female participants with different Hrv (including HrvB and HrvW) were recruited and asked to wear 10 sample blouses with different DL and DP. Samples worn by participants are observed at different angles, and evaluated with scores by 30 experts. The air gap thickness (THA) between the garment and skin are measured by a TC2 scanner and Qualisys three-dimensional motion capture system. The results show that Hrv is the most important factor affecting the aesthetic fit, while DL and DP have significant influence on the formation of garment wrinkles. A round body shape has higher scores when wearing sample garments whose waist dart is close to the front and middle (samples L2, L3) and smaller back middle dart and front waist dart (samples P1, P2), while a flat body shape has higher scores in the opposite condition (sample L5, P5). In terms of air gap distribution, there is a significant positive correlation between HrvB and THA in the front area (132–180°). Here, HrvW was negatively correlated with THA in the back side area. The correlation coefficients are all above 0.6. The DL has a great influence on THA in the side area of the bust section and front side area of the waist section, while DP has a great influence on THA in the front and back areas of the bust section and the back side area of the waist section. In a comparative analysis, this paper proved that the smaller fluctuation of THA and the uniform ease distribution are more likely to present an aesthetic and fit dressing appearance. Although the relationship between THA and the three factors was not significant, the regularity of its distribution is accompanied by a significant change of dressing score.

The main objective of the present study was to investigate the effect of storage temperature on aerobically stored chicken meat spoilage using the two-step and one-step modelling approaches involving different primary models namely the modified Gompertz, logistic, Baranyi and Huang models. For this purpose, growth data points of Pseudomonas spp. were collected from published studies conducted in aerobically stored chicken meat product. Temperature-dependent kinetic parameters (maximum specific growth rate ‘µ max’ and lag phase duration ‘ λ’) were described as a function of storage temperature through the Ratkowsky model based on the different primary models. Then, the fitting capability of both modelling approaches was compared taking into account root mean square error, adjusted coefficient of determination (adjusted-R2) and corrected Akaike information criterion. The one-step modelling approach showed considerably improved fitting capability regardless of the used primary model. Finally, models developed from the one-step modelling approach were validated for the maximum growth rate data extracted from independent published literature using the statistical indexes Bias (Bf) and Accuracy (Af) factors. The best prediction capability was obtained for the Baranyi model with Bf and Af being very close to 1. The shelf-life of chicken meat as a function of storage temperature was predicted using both modelling approaches for the Baranyi model.

We begin with an overview on variance stabilizing transformations (VST) along with three classical examples for completeness: the arcsine, square-root and Fisher's z-transformations (Examples 1–3). Then, we construct three new examples (Examples 4–6) of VST-based and central limit theorem (CLT)’based large-sample confidence interval methodologies. These are special examples in the sense that in each situation, we also have an exact confidence interval procedure for the parameter of interest. Tables 1–3 obtained exclusively under Examples 4–6 via exact calculations show that the VST-based (a) large-sample confidence interval methodology wins over the CLT-based large-sample confidence interval methodology, (b) confidence intervals’ exact coverage probabilities are better than or nearly same as those associated with the exact confidence intervals and (c) intervals are never wider (in the log-scale) than the CLT-based intervals across the board. A possibility of such a surprising behaviour of the VST-based confidence intervals over the exact intervals was not on our radar when we began this investigation. Indeed the VST-based inference methodologies may do extremely well, much more so than the existing literature reveals as evidenced by the new Examples 4–6. AMS subject classifications: 62E20; 62F25; 62F12

Haven’t all of us dreamt of concluding that our results be statistically significant, that is, characterized by a p-value lying below an arbitrary threshold, most often [Formula: see text]? In this article, we, first, deplore that p has been largely misunderstood, and that its misinterpretation has entailed a fallacious dichotomization and an understatement of the uncertainty prevailing about the effect tested. Next, we introduce and explain a brand-new – direct – measure of the plausibility of the effect under study. Then, we illustrate the relevance of this indicator by revisiting a recently published marketing research case. We also insist on the necessity to contextualize it, using complementary credibility intervals graphically contrasted. Beyond making researchers aware of the exact meaning of test-related probabilities, the delineated approach invites them to formulate their inferences with prudence and modesty acknowledging how uncertain these are.

Perimenopause is a time in a woman's life where fertility may vary depending upon her age and her reproductive stage and has been defined as the transition period prior to menopause that is characterized by irregular menses, hormonal changes, vasomotor symptoms, and declining fertility (Casper, 2020). Fertility tracking during this time in a woman's reproductive stage has not been widely studied. Employing the use of Luteinizing Hormone Urine Assay sticks, an electronic hormonal monitor device or mucus, we propose a set of guidelines to determine the potentially fertile times of a woman's cycle based on staging according to the Stages of Reproductive Aging Workshop (STRAW) criteria and illustrate their application with three case reports.

Background/Aims When participants in individually randomized group treatment trials are treated by multiple clinicians or in multiple group treatment sessions throughout the trial, this induces partially nested clusters which can affect the power of a trial. We investigate this issue in the Whole Health Options and Pain Education trial, a three-arm pragmatic, individually randomized clinical trial. We evaluate whether partial clusters due to multiple visits delivered by different clinicians in the Whole Health Team arm and dynamic participant groups due to changing group leaders and/or participants across treatment sessions during treatment delivery in the Primary Care Group Education arm may impact the power of the trial. We also present a Bayesian approach to estimate the intraclass correlation coefficients. Methods We present statistical models for each treatment arm of Whole Health Options and Pain Education trial in which power is estimated under different intraclass correlation coefficients and mapping matrices between participants and clinicians or treatment sessions. Power calculations are based on pairwise comparisons. In practice, sample size calculations depend on estimates of the intraclass correlation coefficients at the treatment sessions and clinician levels. To accommodate such complexities, we present a Bayesian framework for the estimation of intraclass correlation coefficients under different participant-to-session and participant-to-clinician mapping scenarios. We simulated continuous outcome data based on various clinical scenarios in Whole Health Options and Pain Education trial using a range of intraclass correlation coefficients and mapping matrices and used Gibbs samplers with conjugate priors to obtain posteriors of the intraclass correlation coefficients under those different scenarios. Posterior means and medians and their biases are calculated for the intraclass correlation coefficients to evaluate the operating characteristics of the Bayesian intraclass correlation coefficient estimators. Results Power for Whole Health Team versus Primary Care Group Education is sensitive to the intraclass correlation coefficient in the Whole Health Team arm. In these two arms, an increased number of clinicians, more evenly distributed workload of clinicians, or more homogeneous treatment group sizes leads to increased power. Our simulation study for the intraclass correlation coefficient estimation indicates that the posterior mean intraclass correlation coefficient estimator has less bias when the true intraclass correlation coefficients are large (i.e. 0.10), but when the intraclass correlation coefficient is small (i.e. 0.01), the posterior median intraclass correlation coefficient estimator is less biased. Conclusion Knowledge of intraclass correlation coefficients and the structure of clustering are critical to the design of individually randomized group treatment trials with partially nested clusters. We demonstrate that the intraclass correlation coefficient of the Whole Health Team arm can affect power in the Whole Health Options and Pain Education trial. A Bayesian approach provides a flexible procedure for estimating the intraclass correlation coefficients under complex scenarios. More work is needed to educate the research community about the individually randomized group treatment design and encourage publication of intraclass correlation coefficients to help inform future trial designs.

Background The size of the margin strongly influences the required sample size in non-inferiority and equivalence trials. What is sometimes ignored, however, is that for trials with binary outcomes, the scale of the margin – risk difference, risk ratio or odds ratio – also has a large impact on power and thus on sample size requirement. When considering several scales at the design stage of a trial, these sample size consequences should be taken into account. Sometimes, changing the scale may be needed at a later stage of a trial, for example, when the event proportion in the control arm turns out different from expected. Also after completion of a trial, a switch to another scale is sometimes made, for example, when using a regression model in a secondary analysis or when combining study results in a meta-analysis that requires unifying scales. The exact consequences of such switches are currently unknown. Methods and Results This article first outlines sample size consequences for different choices of analysis scale at the design stage of a trial. We add a new result on sample size requirement comparing the risk difference scale with the risk ratio scale. Then, we study two different approaches to changing the analysis scale after the trial has commenced: (1) mapping the original non-inferiority margin using the event proportion in the control arm that was anticipated at the design stage or (2) mapping the original non-inferiority margin using the observed event proportion in the control arm. We use simulations to illustrate consequences on type I and type II error rates. Methods are illustrated on the INES trial, a non-inferiority trial that compared single birth rates in subfertile couples after different fertility treatments. Our results demonstrate large differences in required sample size when choosing between risk difference, risk ratio and odds ratio scales at the design stage of non-inferiority trials. In some cases, the sample size requirement is twice as large on one scale compared with another. Changing the scale after commencing the trial using anticipated proportions mainly impacts type II error rate, whereas switching using observed proportions is not advised due to not maintaining type I error rate. Differences were more pronounced with larger margins. Conclusions Trialists should be aware that the analysis scale can have large impact on type I and type II error rates in non-inferiority trials.

The log transformation is often used to reduce skewness of a measurement variable. If, after transformation, the distribution is symmetric, then the Welch t-test might be used to compare groups. If, also, the distribution becomes close to normal, then a reference interval might be determined.

In longitudinal studies involving laboratory-based outcomes, repeated measurements can be censored due to assay detection limits. Linear mixed-effects (LMEs) models are a powerful tool to model the relationship between a response variable and covariates in longitudinal studies. However, the linear parametric form of linear mixed-effect models is often too restrictive to characterize the complex relationship between a response variable and covariates. More general and robust modeling tools, such as nonparametric and semiparametric regression models, have become increasingly popular in the last decade. In this article, we use semiparametric mixed models to analyze censored longitudinal data with irregularly observed repeated measures. The proposed model extends the censored linear mixed-effect model and provides more flexible modeling schemes by allowing the time effect to vary nonparametrically over time. We develop an Expectation-Maximization (EM) algorithm for maximum penalized likelihood estimation of model parameters and the nonparametric component. Further, as a byproduct of the EM algorithm, the smoothing parameter is estimated using a modified linear mixed-effects model, which is faster than alternative methods such as the restricted maximum likelihood approach. Finally, the performance of the proposed approaches is evaluated through extensive simulation studies as well as applications to data sets from acquired immune deficiency syndrome studies.

Whereas the theory of confirmatory adaptive designs is well understood for uncensored data, implementation of adaptive designs in the context of survival trials remains challenging. Commonly used adaptive survival tests are based on the independent increments structure of the log-rank statistic. This implies some relevant limitations: On the one hand, essentially only the interim log-rank statistic may be used for design modifications (such as data-dependent sample size recalculation). Furthermore, the treatment arm allocation ratio in these classical methods is assumed to be constant throughout the trial period. Here, we propose an extension of the independent increments approach to adaptive survival tests that addresses some of these limitations. We present a confirmatory adaptive two-sample log-rank test that allows rejection regions and sample size recalculation rules to be based not only on the interim log-rank statistic, but also on point-wise survival rate estimates, simultaneously. In addition, the possibility is opened to adapt the treatment arm allocation ratio after each interim analysis in a data-dependent way. The ability to include point-wise survival rate estimators in the rejection region of a test for comparing survival curves might be attractive, e.g., for seamless phase II/III designs. Data-dependent adaptation of the allocation ratio could be helpful in multi-arm trials in order to successively steer recruitment into the study arms with the greatest chances of success. The methodology is motivated by the LOGGIC Europe Trial from pediatric oncology. Distributional properties are derived using martingale techniques in the large sample limit. Small sample properties are studied by simulation.

An underlying threat to the validity of reliability measures is the introduction of systematic variance in examinee scores from unintended constructs that differ from those assessed. One construct-irrelevant behavior that has gained increased attention in the literature is rapid guessing (RG), which occurs when examinees answer quickly with intentional disregard for item content. To examine the degree of distortion in coefficient alpha due to RG, this study compared alpha estimates between conditions in which simulees engaged in full solution (i.e., do not engage in RG) versus partial RG behavior. This was done by conducting a simulation study in which the percentage and ability characteristics of rapid responders as well as the percentage and pattern of RG were manipulated. After controlling for test length and difficulty, the average degree of distortion in estimates of coefficient alpha due to RG ranged from −.04 to .02 across 144 conditions. Although slight differences were noted between conditions differing in RG pattern and RG responder ability, the findings from this study suggest that estimates of coefficient alpha are largely robust to the presence of RG due to cognitive fatigue and a low perceived probability of success.

Recent minimum sample size formula (Riley et al.) for developing clinical prediction models help ensure that development datasets are of sufficient size to minimise overfitting. While these criteria are known to avoid excessive overfitting on average, the extent of variability in overfitting at recommended sample sizes is unknown. We investigated this through a simulation study and empirical example to develop logistic regression clinical prediction models using unpenalised maximum likelihood estimation, and various post-estimation shrinkage or penalisation methods. While the mean calibration slope was close to the ideal value of one for all methods, penalisation further reduced the level of overfitting, on average, compared to unpenalised methods. This came at the cost of higher variability in predictive performance for penalisation methods in external data. We recommend that penalisation methods are used in data that meet, or surpass, minimum sample size requirements to further mitigate overfitting, and that the variability in predictive performance and any tuning parameters should always be examined as part of the model development process, since this provides additional information over average (optimism-adjusted) performance alone. Lower variability would give reassurance that the developed clinical prediction model will perform well in new individuals from the same population as was used for model development.

In cluster-randomized trials, sometimes the effect of the intervention being studied differs between clusters, commonly referred to as treatment effect heterogeneity. In the analysis of stepped wedge and cluster-randomized crossover trials, it is possible to include terms in outcome regression models to allow for such treatment effect heterogeneity yet this is not frequently considered. Outside of some simulation studies of specific cases where the outcome is binary, the impact of failing to include terms for treatment effect heterogeneity on the variance of the treatment effect estimator is unknown. We analytically examine the impact of failing to include terms for treatment effect heterogeneity on the variance of the treatment effect estimator, when outcomes are continuous. Using analysis of variance and feasible generalized least squares we provide expressions for this variance. For both the cluster-randomized crossover design and the stepped wedge design, our analytic derivations indicate that failing to include treatment effect heterogeneity results in the estimates for variance of the treatment effect that are too small, leading to inflation of type I error rates. We therefore recommend assessing the sensitivity of sample size calculations and conclusions drawn from the analysis of cluster randomized trials to the inclusion of treatment effect heterogeneity.

Computer-based and web-based testing have become increasingly popular in recent years. Their popularity has dramatically expanded the availability of response time data. Compared to the conventional item response data that are often dichotomous or polytomous, response time has the advantage of being continuous and can be collected in an unobstrusive manner. It therefore has great potential to improve many measurement activities. In this paper, we propose a change point analysis (CPA) procedure to detect test speededness using response time data. Specifically, two test statistics based on CPA, the likelihood ratio test and Wald test, are proposed to detect test speededness. A simulation study has been conducted to evaluate the performance of the proposed CPA procedure, as well as the use of asymptotic and empirical critical values. Results indicate that the proposed procedure leads to high power in detecting test speededness, while keeping the false positive rate under control, even when simplistic and liberal critical values are used. Accuracy of the estimation of the actual change point, however, is highly dependent on the true change point. A real data example is also provided to illustrate the utility of the proposed procedure and its contrast to the response-only procedure. Implications of the findings are discussed at the end.

The 2016 safety Final Rule requires states to have access to annual average daily traffic (AADT) for all public paved roads, including non-Federal aid-system (NFAS) roads. The latter account approximately for 75% of the total roadway mileage in the country making it difficult for agencies to collect traffic data on these roads. Many agencies use stratified sampling procedures to develop default AADT estimates for uncounted segments; however, there is limited guidance and information about how to stratify the network effectively. The goal of this paper is to enhance transportation agencies’ ability to improve existing stratification schemes, design new schemes, and ultimately develop more accurate AADT estimates for NFAS roads. The paper presents the results from five pilot studies that validated and compared the performance of current, updated, and new (traditional and decision-tree-based) schemes using readily available data. According to the results, the median absolute percent error of existing AADT estimates, developed by state agencies, ranged between 71% and 120%. Updating these schemes using recent counts resulted in an AADT accuracy improvement of 25%. The best-performing schemes were developed using DTs that improved the AADT accuracy of existing schemes by 41%. Overall, having more strata and very homogenous strata is better than having fewer strata and more samples within each stratum. The analysis revealed that a key to selecting an effective scheme is to determine a critical point, beyond which creating more strata improves the AADT accuracy marginally but increases the required sample size exponentially.

This paper analyzes the 2018 Logistics Performance Index (LPI) from the World Bank to determine the spatial effects of countries’ logistics performance. Although the standardized ordinary least square (OLS) models show good results, the spatial lags and Moran’s I of LPI suggest the OLS assumptions are violated. Consequently, an improved geographically weighted regression (IGWR) model using multivariate kernel functions (MKF) is implemented. Through the analysis of the Moran scatter plot, the authors identified the countries that have different logistics performance development trends in the four quadrants representing the relationship between the spatial lags and the LPI. Using trade activity (i.e., import/export) in the MKF, the authors compared different MKF types and bandwidths to ensure the model’s predictability and accuracy and found that the adaptive Gaussian MKF is suitable. Finally, the IGWR model indicates both positive and negative influencing factors on LPI overall score. Specifically, the improvements of LPI are more associated to economic variables in mid- and low-income countries around the world, and are more related to import of construction equipment in the Middle East. Also, business environment is more important in Latin America and the Pacific. European countries are more sensitive to customs efficiency, whereas Pacific-Asian countries are more sensitive to quality of infrastructure and have higher coefficients than African and American countries. This spatial heterogeneity is related to the specific factors that promote the development of their logistics performance.

Sample size calculations for cluster-randomised trials require inclusion of an inflation factor taking into account the intra-cluster correlation coefficient. Often, estimates of the intra-cluster correlation coefficient are taken from pilot trials, which are known to have uncertainty about their estimation. Given that the value of the intra-cluster correlation coefficient has a considerable influence on the calculated sample size for a main trial, the uncertainty in the estimate can have a large impact on the ultimate sample size and consequently, the power of a main trial. As such, it is important to account for the uncertainty in the estimate of the intra-cluster correlation coefficient. While a commonly adopted approach is to utilise the upper confidence limit in the sample size calculation, this is a largely inefficient method which can result in overpowered main trials. In this paper, we present a method of estimating the sample size for a main cluster-randomised trial with a continuous outcome, using numerical methods to account for the uncertainty in the intra-cluster correlation coefficient estimate. Despite limitations with this initial study, the findings and recommendations in this paper can help to improve sample size estimations for cluster randomised controlled trials by accounting for uncertainty in the estimate of the intra-cluster correlation coefficient. We recommend this approach be applied to all trials where there is uncertainty in the intra-cluster correlation coefficient estimate, in conjunction with additional sources of information to guide the estimation of the intra-cluster correlation coefficient.

Background. Difference-in-Difference makes a critical assumption that the changes in the outcomes, over the post-treatment period, are similar between the treated and control groups—the parallel trends assumption. Evaluation of this assumption is often done either by graphical examination or by statistical tests in the pre-treatment period. They result in a binary conclusion about the validity of the assumption. Purpose. This paper proposes a sensitivity analysis that quantifies the departure from parallel trends necessary to meaningfully change the estimated treatment effect. Results. Sensitivity analyses have an advantage over traditional parallel trends tests: they use all available data and thereby work even if only one pre-period is available, and they quantify the strength of unobserved confounder(s) required to change the conclusions of a study. Conclusions. We apply the sensitivity analysis metrics developed by Cinelli and Hazlett (2020) and illustrate them on two studies.

Signal detection analyses often attribute the vigilance decrement to a combination of bias shifts and sensitivity losses. In many vigilance experiments, however, false alarm rates are at or near zero, complicating the analysis of sensitivity. Here, we report Monte Carlo simulations comparing three measures of sensitivity that can be calculated even with extreme hit and false alarm rates: A’, an estimate of the area under the curve that is commonly but mistakenly described as nonparametric; Az calculated using the log-linear correction, a statistic that adjusts individual observers’ data to protect against low false alarm rates; and, 4z estimated using a Bayesian hierarchical procedure, a measure that protects against extreme false alarm rates by sharing information between observers. Results confirm that bias shifts produce spurious changes in A’, and demonstrate that, 4z estimated with either a log-linear correction or through hierarchical Bayesian modeling is more robust against low false alarm rates.

Social scientists frequently rely on the cardinal comparability of test scores to assess achievement gaps between population subgroups and their evolution over time. This approach has been criticized because of the ordinal nature of test scores and the sensitivity of results to order-preserving transformations that are theoretically plausible. Bond and Lang (2013, Review of Economics and Statistics 95: 1468–1479) document the sensitivity of measured ability to scaling choices and develop a method to assess the robustness of changes in ability over time to scaling choices. In this article, I present the scale_transformation command, which expands the Bond and Lang (2013) method to more general cases and optimizes their algorithm to work with large datasets. The command assesses the robustness of an achievement gap between two subgroups to any arbitrary choice of scale by finding bounds for the original gap estimation. Additionally, it finds scale transformations that are very likely and unlikely to benchmark against the results obtained. Finally, it also allows the user to measure how much gap growth coefficients change when including controls in their specifications.

Bayesian regression has emerged as a viable alternative for the estimation of curriculum-based measurement (CBM) growth slopes. Preliminary findings suggest such methods may yield improved efficiency relative to other linear estimators and can be embedded into data management programs for high-frequency use. However, additional research is needed, as Bayesian estimators require multiple specifications of the prior distributions. The current study evaluates the accuracy of several combinations of prior values, including three distributions of the residuals, two values of the expected growth rate, and three possible values for the precision of slope when using Bayesian simple linear regression to estimate fluency growth slopes for reading CBM. We also included traditional ordinary least squares (OLS) as a baseline contrast. Findings suggest that the prior specification for the residual distribution had, on average, a trivial effect on the accuracy of the slope. However, specifications for growth rate and precision of slope were influential, and virtually all variants of Bayesian regression evaluated were superior to OLS. Converging evidence from both simulated and observed data now suggests Bayesian methods outperform OLS for estimating CBM growth slopes and should be strongly considered in research and practice.

Inter-rater agreement measures are used to estimate the degree of agreement between two or more assessors. When the agreement table is ordinal, different weight functions that incorporate row and column scores are used along with the agreement measures. The selection of row and column scores is effectual on the estimated degree of agreement. The weighted measures are prone to the anomalies frequently seen in agreement tables such as unbalanced table structures or grey zones due to the assessment behaviour of the raters. In this study, Bayesian approaches for the estimation of inter-rater agreement measures are proposed. The Bayesian approaches make it possible to include prior information on the assessment behaviour of the raters in the analysis and impose order restrictions on the row and column scores. In this way, we improve the accuracy of the agreement measures and mitigate the impact of the anomalies in the estimation of the strength of agreement between the raters. The elicitation of prior distributions is described theoretically and practically for the Bayesian estimation of five agreement measures with three different weights using an agreement table having two grey zones. A Monte Carlo simulation study is conducted to assess the classification accuracy of the Bayesian and classical approaches for the considered agreement measures for a given level of agreement. Recommendations for the selection of the highest performing agreement measure and weight combination are made in the breakdown of the table structure and sample size.

While electronic health records data provide unique opportunities for research, numerous methodological issues must be considered. Among these, selection bias due to incomplete/missing data has received far less attention than other issues. Unfortunately, standard missing data approaches (e.g. inverse-probability weighting and multiple imputation) generally fail to acknowledge the complex interplay of heterogeneous decisions made by patients, providers, and health systems that govern whether specific data elements in the electronic health records are observed. This, in turn, renders the missing-at-random assumption difficult to believe in standard approaches. In the clinical literature, the collection of decisions that gives rise to the observed data is referred to as the data provenance. Building on a recently-proposed framework for modularizing the data provenance, we develop a general and scalable framework for estimation and inference with respect to regression models based on inverse-probability weighting that allows for a hierarchy of missingness mechanisms to better align with the complex nature of electronic health records data. We show that the proposed estimator is consistent and asymptotically Normal, derive the form of the asymptotic variance, and propose two consistent estimators. Simulations show that naïve application of standard methods may yield biased point estimates, that the proposed estimators have good small-sample properties, and that researchers may have to contend with a bias-variance trade-off as they consider how to handle missing data. The proposed methods are motivated by an on-going, electronic health records-based study of bariatric surgery.

It is known that the estimating equations for quantile regression (QR) can be solved using an EM algorithm in which the M-step is computed via weighted least squares, with weights computed at the E-step as the expectation of independent generalized inverse-Gaussian variables. This fact is exploited here to extend QR to allow for random effects in the linear predictor. Convergence of the algorithm in this setting is established by showing that it is a generalized alternating minimization (GAM) procedure. Another modification of the EM algorithm also allows us to adapt a recently proposed method for variable selection in mean regression models to the QR setting. Simulations show the resulting method significantly outperforms variable selection in QR models using the lasso penalty. Applications to real data include a frailty QR analysis of hospital stays, and variable selection for age at onset of lung cancer and for riboflavin production rate using high-dimensional gene expression arrays for prediction., arXiv admin note: text overlap with arXiv:1910.11479

The purpose of the current study was to investigate the factor structure of the Anxiety Sensitivity Index-3 (ASI-3) in a Turkey sample and to determine measurement invariance of the ASI-3 across gender and age groups. Confirmatory factor analysis was performed on four different models to determine the best fit model for the structure. After the best structure was determined, different models were tested for measurement invariance across gender and age groups. To determine the reliability of the ASI-3, the hierarchical omega coefficient and correlations between the scores obtained from different scales for convergent validity were calculated. It has been determined that the bifactor model is the model that best fits the data, and this model shows invariance across gender and age groups. Besides, evidence regarding the reliability and convergent validity of the ASI-3 was also provided in the study. Current findings show that anxiety sensitivity consists of a general factor (anxiety sensitivity) and three independent specific factors (physical, cognitive, and social concerns). It was concluded that the general factor of anxiety sensitivity constitutes a dominant factor and special factors have a relatively low effect on explaining the structure. Considering the dominance of the general factor, it is recommended to use the ASI-3 total score as a measure of general anxiety sensitivity.

In cricket, one-day-international (ODI) batsmen have traditionally been compared on the dimensions of batting average (BA) and strike rate (SR). The conventional method of computing BA assumes that runs scored by a batsman follow an exponential or geometric distribution. This results in unreasonably equating batting inconsistency with batting mean. Our study shows that a Weibull distribution model gives a very sensible assessment of a batsman’s inconsistency, independent of his BA. It also provides a superior fit to batting scores of ODI batsmen. We also introduce a measure for ‘quality-runs’ scored by a batsman which takes into account the difficulty level of opposition. Additionally, longevity index and opposition diversity index are defined to make comparisons more holistic. A substantial amount of data engineering effort is made in segregating available data into home, away and neutral matches. The measures proposed in this paper are more comprehensive and granular than those found in the literature. Various combinations of these six criteria are used to rank a select group of great ODI batsmen by assigning objective weights derived from principal component analysis. Finally, multivariate statistical outlier detection procedure produces different lists of outstanding players corresponding to different combinations of criteria. Our proposed methodology may be gainfully used by a team management to select best batsmen in a given situation.

This paper presents the results of an analysis focusing on large truck-involved work zone fatal crashes using seven-year crash data in the State of Florida. Decision tree/random forest models were applied to specifically detect critical crash patterns that result in a fatality outcome. Because of the imbalanced nature of crash severity data (very low frequency of fatal crashes compared with property damage only or injury), data were treated using random and systematic over-sampling techniques. Marginal effects were addressed using Shapley values to increase model explainability. From a methodological perspective, results showed that the combination of over-sampling techniques with ensemble random forests could significantly improve model performance in predicting fatal crashes (compared with conventional logistic regression models). Primary contributors included pedestrian involvement, lighting conditions, safety equipment, driver condition, driver age, and work zone locations. For pedestrian crashes, factors such as dark-not lighted conditions, distracted truck driver, and driver’s age (young drivers outside city limits, senior drivers inside city limits) were highly likely to be fatal. For non-pedestrian crashes, the combination of front airbag deployment with any restraint system other than shoulder and belt was quite likely to be fatal. Also, abnormal driver conditions increased the risk of a fatal outcome. Additionally, the presence of female drivers (as the second driver in multiple vehicle crashes) highly decreased crash severity, probably because females typically drive more carefully than males. Interestingly, truck driver actions and maneuvers as well as roadway design and other physical environment features (i.e., number of lanes, median type, roadway grade, and alignment) did not show significant contribution to the model.

This paper addresses the issue of detecting dominating failure modes of a system from a two-dimensional warranty data set by analyzing conditional failure profile of the system. Two testing procedures have been proposed to test whether any of the failure modes is dominating at a particular time interval and whether there is a change of the failure profile from one time interval to another disjoint time interval, conditioning on a given usage layer. Detecting the problematic failure modes early from the conditional failure profile and taking appropriate actions to reduce the conditional failure probability of the system can significantly reduce both tangible and intangible costs of poor reliability in any manufacturing industry. On the other hand, the study of possible changes of conditional failure profiles has a significant role to assess the field performance of items from one time interval to another time interval for a particular choice of usage layer. The utility of this study is explored with the help of a real-life data set.

Mobile media, which comprise the main features of other media, can potentially influence many social issues. This time-series study aims to investigate the relationship between the mobile penetration rate and the growing divorce rate in Iran from 1995 to 2019. To specify the relationship, women’s participation in the labor force as a powerful social variable affecting the divorce rate was considered and modeled in the analysis. More specifically, the autoregressive distributed lag (ARDL) method was employed to measure the short and long-term relationships. The results indicated a significant positive relationship between the mobile penetration rate and the divorce rate in both short- and long-term periods; however, women’s participation in the labor force was not associated with the divorce rate.

Background The change in estimate is a popular approach for selecting confounders in epidemiology. It is recommended in epidemiologic textbooks and articles over significance test of coefficients, but concerns have been raised concerning its validity. Few simulation studies have been conducted to investigate its performance. Methods An extensive simulation study was realized to compare different implementations of the change in estimate method. The implementations were also compared when estimating the association of body mass index with diastolic blood pressure in the PROspective Québec Study on Work and Health. Results All methods were susceptible to introduce important bias and to produce confidence intervals that included the true effect much less often than expected in at least some scenarios. Overall mixed results were obtained regarding the accuracy of estimators, as measured by the mean squared error. No implementation adequately differentiated confounders from non-confounders. In the real data analysis, none of the implementation decreased the estimated standard error. Conclusion Based on these results, it is questionable whether change in estimate methods are beneficial in general, considering their low ability to improve the precision of estimates without introducing bias and inability to yield valid confidence intervals or to identify true confounders.

The prevalence of human trafficking has remained as elusive as the method of producing its estimation is contested. There are significant variations in the way prevalence estimation is produced, with some methods garnering more attention than others. To complicate the issue further, the hidden nature of human trafficking makes it difficult to apply conventional probability-based sampling strategies, without which for reference purposes one cannot easily assess the merits of alternative estimation techniques. This special issue represents the most recent development and applications of one particular method, the multiple systems estimation (MSE) method. Although we remain biased towards primary data for prevalence estimation, MSE represents a cost-effective alternative for the purposes of advocacy, policymaking, and victim services.

Background/Aims: The focus of Alzheimer’s disease studies has shifted to earlier disease stages, including mild cognitive impairment. Biomarker inclusion criteria are often incorporated into mild cognitive impairment clinical trials to identify individuals with “prodromal Alzheimer’s disease” to ensure appropriate drug targets and enrich for participants likely to develop Alzheimer’s disease dementia. The use of these eligibility criteria may affect study power. Methods: We investigated outcome variability and study power in the setting of proof-of-concept prodromal Alzheimer’s disease trials that incorporate cerebrospinal fluid levels of total tau (t-tau) and phosphorylated (p-tau) as primary outcomes and how differing biomarker inclusion criteria affect power. We used data from the Alzheimer’s Disease Neuroimaging Initiative to model trial scenarios and to estimate the variance and within-subject correlation of total and phosphorylated tau. These estimates were then used to investigate the differences in study power for trials considering these two surrogate outcomes. Results: Patient characteristics were similar for all eligibility criteria. The lowest outcome variance and highest within-subject correlation were obtained when phosphorylated tau was used as an eligibility criterion, compared to amyloid beta or total tau, regardless of whether total tau or phosphorylated tau were used as primary outcomes. Power increased when eligibility criteria were broadened to allow for enrollment of subjects with either low amyloid beta or high phosphorylated tau. Conclusion: Specific biomarker inclusion criteria may impact statistical power in trials using total tau or phosphorylated tau as the primary outcome. In concert with other important considerations such as treatment target and population of clinical interest, these results may have implications to the integrity and efficiency of prodromal Alzheimer’s disease trial designs.

This work identifies factors that influence crash occurrence within a traffic analysis zone (TAZ) by accounting for location-specific effects and serial correlation in longitudinal crash data. This is accomplished by applying a random effect negative binomial (RENB) model. Unlike commonly used count models such as Poisson and negative binomial (NB), RENB accounts for heterogeneity and serial correlation in crash occurrence. An RENB was applied to 15 years of crash data in Arkansas with 1,817 TAZs. Four models were developed for total crashes and by severity (property damage only (PDO), injury, and fatal). RENB-estimated impacts were measured using the incidence rate ratio (IRR). The significant causal factors found to increase in observed crashes include: (i) average precipitation (a one-unit increase in average precipitation results in a 134% increase in total monthly crashes for a TAZ); (ii) average wind speed (16%); (iii) urban designation (7%); (iv) traffic volume (2%); and (v) total roadway mileage (1% for each functional class). Snow depth and days of sunshine were found to decrease the number of accidents by 15% and 2%, respectively. Employment and total population had no impact on crash occurrence. Goodness-of-fit comparisons show that RENB provides the best fit among Poisson and NB formulations. All four model diagnostics confirm the presence of over-dispersion and serial correlation indicating the necessity of RENB model estimation. The main contribution of this work is the identification of crash causal factors at the TAZ level for longitudinal data, which supports data-driven performance measurement requirements of recent federal legislation.

Correlated color temperature (CCT) is a one-dimensional metric that aims to quantify the perceived visual quality of nominal white light sources. It is often used as a proxy for the color quality of light sources due to its ease of use. However, CCT lacks the accuracy in communicating color information for research purposes. Two light sources with identical CCTs can appear perceptually different, and these differences are not estimated by CCT due to the loss of information caused by reducing spectral power distribution of light sources into a one-dimensional metric. Using supplemental metrics in addition to CCT, providing the absolute spectral power distribution of light sources in graphical and tabular form, and documenting and accounting for potential confounding factors, such as chromatic adaptation, can increase the validity of research results, improve the repeatability of studies, and help address replication concerns.

For transportation system analysis in a new space dimension with respect to individual trips’ remaining distances, vehicle trips demand has two main components: the departure time and the trip distance. In particular, the trip distance distribution (TDD) is a direct input to the bathtub model in the new space dimension, and is a very important variable to consider in many applications, such as the development of distance-based congestion pricing strategies or mileage tax. For a good understanding of the demand pattern, both the distribution of trip initiation and trip distance should be calibrated from real data. In this paper, it is assumed that the demand pattern can be described by the joint distribution of trip distance and departure time. In other words, TDD is assumed to be time-dependent, and a calibration and validation methodology of the joint probability is proposed, based on log-likelihood maximization and the Kolmogorov–Smirnov test. The calibration method is applied to empirical for-hire vehicle trips in Chicago, and it is concluded that TDD varies more within a day than across weekdays. The hypothesis that TDD follows a negative exponential, log-normal, or Gamma distribution is rejected. However, the best fit is systematically observed for the time-dependent log-normal probability density function. In the future, other trip distributions should be considered and also non-parametric probability density estimation should be explored for a better understanding of the demand pattern.

Two-lane highways represent the majority of highways in the U.S. and their safety is of crucial concern. Even though road safety researchers intensively evaluated two-lane highway safety, past studies were challenged by a methodological hindrance, namely that of correlated random parameters (CRP) modeling methods. Random parameters models capture unobserved heterogeneity effects of crash contributing factors, while CRP models offer the additional benefit of capturing correlations among variables inducing such unobserved heterogeneity effects. However, CRP models do not permit specifying pairs of regressors, with statistically insignificant correlations, to be uncorrelated. In this research, it was demonstrated that the conventional uncorrelated random parameters ordinal probit (URPOP) structure with interaction effects outperformed the correlated random parameters ordinal probit (CRPOP) structure when modeling injury severity risks of two-lane highway crashes in Wyoming. As per the former model’s results, speeding, head-on collisions, sideswipe opposite-direction collisions, intersecting-direction collisions, motorcycle involvement, impaired driving, distracted driving, the interaction effect of speeding with motorcycle involvement, that of head-on collisions with impaired driving, and that of head-on collisions with commercial vehicle involvement all raised the likelihood of sustaining severe injuries. Conversely, leaving the crash scene, proper seat belt use, wet road surfaces, and the interaction effect of impaired driving with motorcycle involvement alleviated the risk of incurring severe injuries. The superiority of the proposed model and its reduced computation time warrant its recommendation for implementation in future studies. Also, from a practical perspective, safety mitigation measures are suggested based on this research’s findings.