Brooke E. Magnus

Vaccination confidence and parental refusal/delay of early childhood vaccines

Objective To support efforts to address parental hesitancy towards early childhood vaccination, we sought to validate the Vaccination Confidence Scale using data from a large, population-based sample of U.S. parents. Methods We used weighted data from 9,354 parents who completed the 2011 National Immunization Survey. Parents reported on the immunization history of a 19- to 35-month-old child in their households. Healthcare providers then verified children’s vaccination status for vaccines including measles, mumps, and rubella (MMR), varicella, and seasonal flu. We used separate multivariable logistic regression models to assess associations between parents’ mean scores on the 8-item Vaccination Confidence Scale and vaccine refusal, vaccine delay, and vaccination status. Results A substantial minority of parents reported a history of vaccine refusal (15%) or delay (27%). Vaccination confidence was negatively associated with refusal of any vaccine (odds ratio [OR] = 0.58, 95% confidence interval [CI], 0.54–0.63) as well as refusal of MMR, varicella, and flu vaccines specifically. Negative associations between vaccination confidence and measures of vaccine delay were more moderate, including delay of any vaccine (OR = 0.81, 95% CI, 0.76–0.86). Vaccination confidence was positively associated with having received vaccines, including MMR (OR = 1.53, 95% CI, 1.40–1.68), varicella (OR = 1.54, 95% CI, 1.42–1.66), and flu vaccines (OR = 1.32, 95% CI, 1.23–1.42). Conclusions Vaccination confidence was consistently associated with early childhood vaccination behavior across multiple vaccine types. Our findings support expanding the application of the Vaccination Confidence Scale to measure vaccination beliefs among parents of young children.

Developmental Delays in Executive Function from 3 to 5 Years of Age Predict Kindergarten Academic Readiness

Substantial evidence has established that individual differences in executive function (EF) in early childhood are uniquely predictive of children’s academic readiness at school entry. The current study tested whether growth trajectories of EF across the early childhood period could be used to identify a subset of children who were at pronounced risk for academic impairment in kindergarten. Using data that were collected at the age 3, 4, and 5 home assessments in the Family Life Project (N = 1,120), growth mixture models were used to identify 9% of children who exhibited impaired EF performance (i.e., persistently low levels of EF that did not show expected improvements across time). Compared to children who exhibited typical trajectories of EF, the delayed group exhibited substantial impairments in multiple indicators of academic readiness in kindergarten (Cohen’s ds = 0.9–2.7; odds ratios = 9.8–23.8). Although reduced in magnitude following control for a range of socioeconomic and cognitive (general intelligence screener, receptive vocabulary) covariates, moderate-sized group differences remained (Cohen’s ds = 0.2–2.4; odds ratios = 3.9–5.4). Results are discussed with respect to the use of repeated measures of EF as a method of early identification, as well as the resulting translational implications of doing so.

Using item response theory to enrich and expand the PROMIS® pediatric self report banks.

BackgroundThe primary objective was to enhance the content coverage of some of the pediatric self-report item banks for ages 8-17 years from the National Institutes of Health (NIH) Patient Reported Outcomes Measurement Information System (PROMIS®), and extend the range of precise measurement to higher levels of physical functioning.MethodsData from 1,419 pediatric patients with cancer, chronic kidney disease, obesity, rehabilitation needs, rheumatic disease, and sickle cell disease were combined with item responses from the original standardization sample of 3,048 children to calibrate new items for the pediatric PROMIS Anger, Anxiety, Depressive Symptoms, Pain Interference, Fatigue, and physical functioning Upper Extremity and Mobility scales. Simultaneous or concurrent calibration using the graded item response theory model placed all of the items on the same scale.ResultsTwenty-two of 28 potential new items were added across the seven scales. A recommended short form was proposed for the Anger scale, and the recommended short forms for the Anxiety and Depressive Symptoms scales were revised. Unfortunately, we were not particularly successful at extending the range of measurement for the physical functioning banks.ConclusionsThe present study expanded PROMIS pediatric item banks to add new content and to increase the range of measurement. Using item response theory, the banks were revised and expanded without changing the underlying scale of measurement. For Anger, Anxiety, and Depressive Symptoms, we successfully added new content that may render those banks more robust and flexible.

Mode effects between computer self-administration and telephone interviewer-administration of the PROMIS® pediatric measures, self- and proxy report

ObjectiveTo test equivalence of scores obtained with the PROMIS® pediatric Depressive Symptoms, Fatigue, and Mobility measures across two modes of administration: computer self-administration and telephone interviewer-administration. If mode effects are found, to estimate the magnitude and direction of the mode effects.MethodsRespondents from an internet survey panel completed the child self-report and parent proxy-report versions of the PROMIS® pediatric Depressive Symptoms, Fatigue, and Mobility measures using both computer self-administration and telephone interviewer-administration in a crossed counterbalanced design. Pearson correlations and multivariate analysis of variance were used to examine the effects of mode of administration as well as order and form effects.ResultsCorrelations between scores obtained with the two modes of administration were high. Scores were generally comparable across modes of administration, but there were some small significant effects involving mode of administration; significant differences in scores between the two modes ranged from 1.24 to 4.36 points.ConclusionsScores for these pediatric PROMIS measures are generally comparable across modes of administration. Studies planning to use multiple modes (e.g., self-administration and interviewer-administration) should exercise good study design principles to minimize possible confounding effects from mixed modes.

The benefits of adding a brief measure of simple reaction time to the assessment of executive function skills in early childhood

Early childhood represents a period of rapid cognitive developmental change in executive function (EF) skills along with a variety of related cognitive processes, including processing speed. This leads to interpretational challenges in that childrens performance on EF tasks reflects more than EF skills per se. We tested whether the inclusion of a brief measure of simple reaction time (SRT) during EF assessments could help to partially address this challenge. Data were drawn from a cross-sectional convenience sample of 830 preschool-aged children. Individual differences in SRT were significantly associated with performance on all tasks (R2s = .09-.26); slower performance on the SRT task was associated with poorer performance on each EF task. Age-related differences in individual EF tasks were reduced by approximately one half after accounting for age-related differences in SRT, and EF task scores were less coherent (i.e., less strongly intercorrelated with each other) after the removal of SRT. Age-related differences in EF were smaller (Cohen ds = 1.36 vs. 0.78), and poverty-related differences in EF were larger (Cohen ds = 0.30 vs. 0.46) after accounting for SRT-related variation. Finally, consistent with previous studies, SRT-related differences in fluid reasoning were mediated by EF skills. Results are discussed with respect to using a brief measure of SRT to partially address the problem of measurement impurity at the level of individual EF tasks.

Providing feedback following Leadership WalkRounds is associated with better patient safety culture, higher employee engagement and lower burnout

Background There is a poorly understood relationship between Leadership WalkRounds (WR) and domains such as safety culture, employee engagement, burnout and work-life balance. Methods This cross-sectional survey study evaluated associations between receiving feedback about actions taken as a result of WR and healthcare worker assessments of patient safety culture, employee engagement, burnout and work-life balance, across 829 work settings. Results 16 797 of 23 853 administered surveys were returned (70.4%). 5497 (32.7% of total) reported that they had participated in WR, and 4074 (24.3%) reported that they participated in WR with feedback. Work settings reporting more WR with feedback had substantially higher safety culture domain scores (first vs fourth quartile Cohen’s d range: 0.34–0.84; % increase range: 15–27) and significantly higher engagement scores for four of its six domains (first vs fourth quartile Cohen’s d range: 0.02–0.76; % increase range: 0.48–0.70). Conclusion This WR study of patient safety and organisational outcomes tested relationships with a comprehensive set of safety culture and engagement metrics in the largest sample of hospitals and respondents to date. Beyond measuring simply whether WRs occur, we examine WR with feedback, as WR being done well. We suggest that when WRs are conducted, acted on, and the results are fed back to those involved, the work setting is a better place to deliver and receive care as assessed across a broad range of metrics, including teamwork, safety, leadership, growth opportunities, participation in decision-making and the emotional exhaustion component of burnout. Whether WR with feedback is a manifestation of better norms, or a cause of these norms, is unknown, but the link is demonstrably potent.

Psychometric evaluation and design of patient-centered communication measures for cancer care settings

OBJECTIVE To evaluate the psychometric properties of questions that assess patient perceptions of patient-provider communication and design measures of patient-centered communication (PCC). METHODS Participants (adults with colon or rectal cancer living in North Carolina) completed a survey at 2 to 3 months post-diagnosis. The survey included 87 questions in six PCC Functions: Exchanging Information, Fostering Health Relationships, Making Decisions, Responding to Emotions, Enabling Patient Self-Management, and Managing Uncertainty. For each Function we conducted factor analyses, item response theory modeling, and tests for differential item functioning, and assessed reliability and construct validity. RESULTS Participants included 501 respondents; 46% had a high school education or less. Reliability within each Function ranged from 0.90 to 0.96. The PCC-Ca-36 (36-question survey; reliability=0.94) and PCC-Ca-6 (6-question survey; reliability=0.92) measures differentiated between individuals with poor and good health (i.e., known-groups validity) and were highly correlated with the HINTS communication scale (i.e., convergent validity). CONCLUSION This study provides theory-grounded PCC measures found to be reliable and valid in colorectal cancer patients in North Carolina. Future work should evaluate measure validity over time and in other cancer populations. PRACTICE IMPLICATIONS The PCC-Ca-36 and PCC-Ca-6 measures may be used for surveillance, intervention research, and quality improvement initiatives.

Modeling and Testing Differential Item Functioning in Unidimensional Binary Item Response Models with a Single Continuous Covariate: A Functional Data Analysis Approach

Differential item functioning (DIF), referring to between-group variation in item characteristics above and beyond the group-level disparity in the latent variable of interest, has long been regarded as an important item-level diagnostic. The presence of DIF impairs the fit of the single-group item response model being used, and calls for either model modification or item deletion in practice, depending on the mode of analysis. Methods for testing DIF with continuous covariates, rather than categorical grouping variables, have been developed; however, they are restrictive in parametric forms, and thus are not sufficiently flexible to describe complex interaction among latent variables and covariates. In the current study, we formulate the probability of endorsing each test item as a general bivariate function of a unidimensional latent trait and a single covariate, which is then approximated by a two-dimensional smoothing spline. The accuracy and precision of the proposed procedure is evaluated via Monte Carlo simulations. If anchor items are available, we proposed an extended model that simultaneously estimates item characteristic functions (ICFs) for anchor items, ICFs conditional on the covariate for non-anchor items, and the latent variable density conditional on the covariate—all using regression splines. A permutation DIF test is developed, and its performance is compared to the conventional parametric approach in a simulation study. We also illustrate the proposed semiparametric DIF testing procedure with an empirical example.

Item Response Modeling of Multivariate Count Data with Zero Inflation, Maximum Inflation, and Heaping.

Questionnaires that include items eliciting count responses are becoming increasingly common in psychology. This study proposes methodological techniques to overcome some of the challenges associated with analyzing multivariate item response data that exhibit zero inflation, maximum inflation, and heaping at preferred digits. The modeling framework combines approaches from three literatures: item response theory (IRT) models for multivariate count data, latent variable models for heaping and extreme responding, and mixture IRT models. Data from the Behavioral Risk Factor Surveillance System are used as a motivating example. Practical implications are discussed, and recommendations are provided for researchers who may wish to use count items on questionnaires.

Extending the Use of Multidimensional IRT Calibration as Projection: Many-to-One Linking and Linear Computation of Projected Scores

Two methods to make inferences about scores that would have been obtained on one test using responses obtained with a different test are scale aligning and projection. If both tests measure the same construct, scale aligning may be accomplished using the results of simultaneous calibration of the items from both tests with a unidimensional IRT model. If the tests measure distinct but related constructs, an alternative is the use of regression to predict scores on one test from scores on the other; when the score distribution is predicted, this is projection. Calibrated projection combines those two methods, using a multidimensional IRT (MIRT) model to simultaneously calibrate the items comprising two tests onto scales representing distinct constructs, and estimating the parameters describing the relation between the two scales. Then projection is done within the MIRT model. This presentation describes two extensions of calibrated projection: (1) the use of linear models to compute the projected scores and their error variances, and (2) projection from more than one test to a single test. The procedures are illustrated using data obtained with scales measuring closely related quality of life constructs.