First-Order Learning Models With the GDINA: Estimation With the EM Algorithm and Applications.

In learning environments, understanding the longitudinal path of learning is one of the main goals. Cognitive diagnostic models (CDMs) for measurement combined with a transition model for mastery may be beneficial for providing fine-grained information about students' knowledge profiles over time. An efficient algorithm to estimate model parameters would augment the practicality of this combination. In this study, the Expectation-Maximization (EM) algorithm is presented for the estimation of student learning trajectories with the GDINA (generalized deterministic inputs, noisy, "and" gate) and some of its submodels for the measurement component, and a first-order Markov model for learning transitions is implemented. A simulation study is conducted to investigate the efficiency of the algorithm in estimation accuracy of student and model parameters under several factors-sample size, number of attributes, number of time points in a test, and complexity of the measurement model. Attribute- and vector-level agreement rates as well as the root mean square error rates of the model parameters are investigated. In addition, the computer run times for converging are recorded. The result shows that for a majority of the conditions, the accuracy rates of the parameters are quite promising in conjunction with relatively short computation times. Only for the conditions with relatively low sample sizes and high numbers of attributes, the computation time increases with a reduction parameter recovery rate. An application using spatial reasoning data is given. Based on the Bayesian information criterion (BIC), the model fit analysis shows that the DINA (deterministic inputs, noisy, "and" gate) model is preferable to the GDINA with these data.

Case-control study of cervical cancer and gynecologic screening: A SEER-Medicare analysis.

OBJECTIVE: To determine the association between Pap smear and pelvic examination screenings and the development of invasive cervical cancer in a Medicare population using a matched case-control design. METHODS: Matched case-control data sets were constructed from the SEER-Medicare database that links the Surveillance Epidemiology End Results (SEER) cancer registry data and Medicare enrollment and claims data of subjects who received care between the years 1991 and 1999 aged 65years or older. The study identified 1267 cervical cancer cases. Controls (N=10.137) were matched to cases representing up to eight matched controls (on age and registry geographic location) for a single case. The association between gynecologic screenings and the development of invasive cervical cancer was ascertained using conditional logistic regression analysis. RESULTS: Having had a Pap smear during the PIDP (pre-invasive detectable phase - 2 to 7years prior to diagnosis) was significantly negatively associated with the development of invasive cervical cancer (OR=0.64, 95% CI=0.53-0.78) which was reduced after taking into account the estimated prevalence of hysterectomy among controls (OR=0.38, 95% CI=0.32-0.46). The negative association between Pap smear screenings and cervical cancer was strongest for squamous tumors (OR=0.48, 95% CI=0.37-0.61). Restricting the subjects to those 72 and over did not affect risk. CONCLUSIONS: There is a reduction in risk for invasive cervical cancer when women over age 65 are screened. This suggests that cervical cancer screening in the aged population may be beneficial.

The linear transformation model with frailties for the analysis of item response times.

The item response times (RTs) collected from computerized testing represent an underutilized source of information about items and examinees. In addition to knowing the examinees' responses to each item, we can investigate the amount of time examinees spend on each item. In this paper, we propose a semi-parametric model for RTs, the linear transformation model with a latent speed covariate, which combines the flexibility of non-parametric modelling and the brevity as well as interpretability of parametric modelling. In this new model, the RTs, after some non-parametric monotone transformation, become a linear model with latent speed as covariate plus an error term. The distribution of the error term implicitly defines the relationship between the RT and examinees' latent speeds; whereas the non-parametric transformation is able to describe various shapes of RT distributions. The linear transformation model represents a rich family of models that includes the Cox proportional hazards model, the Box-Cox normal model, and many other models as special cases. This new model is embedded in a hierarchical framework so that both RTs and responses are modelled simultaneously. A two-stage estimation method is proposed. In the first stage, the Markov chain Monte Carlo method is employed to estimate the parametric part of the model. In the second stage, an estimating equation method with a recursive algorithm is adopted to estimate the non-parametric transformation. Applicability of the new model is demonstrated with a simulation study and a real data application. Finally, methods to evaluate the model fit are suggested.

Collection of the BD SurePath Pap Test with a broom device plus endocervical brush improves disease detection when compared to the broom device alone or the spatula plus endocervical brush combination.

OBJECTIVE: Here we examine the diagnostic utility of the US Food And Drug Administration (FDA) approved Spatula + endocervical brush combination for the BD SurePath Pap Test (SPPT) and compare it to SPPT collection with the broom alone or to an off-label combination of broom + EC brush. This question is important due to lingering concerns over the value of EC detection to a satisfactory Pap test. METHODS: 20,125 SPPT vials were examined for the collection devices contained. The SPPT collection device combinations allowed were: Rovers Cervex-Brush (broom, FDA approved), Medscand Pap Perfect Spatula + Medscand CytoBrush Plus GT (spatula + GT brush, FDA approved) or Rovers Cervex-Brush + Surgipath C-E Brush (broom + CE brush, off label). RESULTS: Examination of SPPT vials revealed 11,130 collected with the broom, 4,687 collected with the spatula + GT brush and 2,921 collected with the broom + CE brush. Absence of an endocervical/transformation zone was seen in 22.86% of broom cases, 13.10% of spatula + GT brush cases (p= 0.00005 vs broom) and 10.17% of broom + CE brush cases (p= 0.00005 vs broom, p= 0.00005 vs spatula + GT brush). Importantly, LSIL detection was: broom 2.99%; spatula + GT brush 2.45% (p= 0.053 vs broom); broom + CE brush 4.18% (p= 0.034 vs broom, p= 0.0001 vs spatula + GT brush). CONCLUSION: When broom + brush combination is compared to broom alone or to spatula + GT brush, the broom + CE brush combination better sampled the endocervical/transformation zone and increased LSIL detection.

Quality of life of children with cystic fibrosis.

OBJECTIVE: To review health-related quality of life (QOL) and associated issues and to describe a study investigating "Child Health Questionnaire" (CHQ) scores in relationship to newborn screening (NBS) for cystic fibrosis (CF) and markers of disease severity. METHODS: A total of 36 patients from 10-15.5 years old who were enrolled in the screened or control group of the Wisconsin CF Neonatal Screening Project completed the CHQ. Scale scores comprised the dependent variables. Independent variables included study group and measures of disease severity. Analyses included Fisher's exact, 2-sample Wilcoxon, and t tests. RESULTS: QOL did not differ significantly between the screened and control groups for any of the scales. None of the comparisons of CHQ scale scores across measures of disease severity were significant in this small sample, but the CHQ and power were limiting. CONCLUSIONS: Our results did not demonstrate a benefit of CF NBS on QOL; however, the CHQ may not be adequately sensitive to QOL in children with CF with disease severity comparable to our sample. The Cystic Fibrosis Questionnaire, a recently validated CF-specific QOL measure for pediatric samples, is likely to provide a more informative evaluation of the effects of CF NBS on patients' QOL.