Timothy N. Ansley

An Examination of the Characteristics of Unidimensional IRT Parameter Estimates Derived From Two-Dimensional Data

The purpose of this investigation was to study the nature of the item and ability estimates obtained when the modified three-parameter logistic model is used with two-dimensional data. To examine the effects of two-dimensional data on unidimensional parameter es timates, the relative potency of the two dimensions was systematically varied by changing the correlations between the two ability dimensions. Data sets based on correlations of .0, .3, .6, .9, and .95 were gener ated for each of four combinations of sample size and test length. Also, for each of these four combinations, five unidimensional data sets were simulated for com parison purposes. Relative to the nature of the unidi mensional estimates, it was found that the â value seemed best considered as the average of the true a values. The b value seemed best thought of as an overestimate of the true b 1 values. The θ value seemed best considered as the average of the true ability pa rameters. Although there was a consistent trend for these relationships to strengthen as the ability dimen sions became more highly correlated, there was al ways a substantial disparity between the magnitudes of these values and of those derived from the unidimen sional data. Sample size and test length had very little effect on these relationships.

The Comparative Effects of Compensatory and Noncompensatory Two-Dimensional Data on Unidimensional IRT Estimates

This study compared the effects of using a unidi mensional IRT model with two-dimensional data gener ated by noncompensatory and compensatory multidi mensional IRT models. Within each model, simulated datasets differed according to the degree of correlation between two vectors of θ parameters, ranging from 0 to .95. Results showed that the number-correct distri butions for each group of datasets were generally comparable, although factor analyses of tetrachoric correlations suggested that differences existed in the structure of the data from the two models. For the uni dimensional parameter estimates, it was found that the â values from the noncompensatory model appeared to be averages of the a 1 and a 2 values, while the â values from the compensatory model were best considered as an estimate of the sum of the a 1 and a 2 values. Con versely, the b values for the noncompensatory data were consistently greater than the b 1 values, while the b values from the compensatory model were best con sidered as the average of the b 1 and b 2 values. For both models the θ estimates were most highly related to the average of the two θ parameters. However, for the noncompensatory model there was a general in crease in the strength of this relationship with in creases in ρ(θ1,θ 2). For the compensatory model, the strength of this relationship did not show a great deal of change with differences in ρ(θ1,θ 2). Index terms: Compensatory multidimensional IRT models, Item response theory, Multidimensional IRT models, Noncompensatory multidimensional IRT models, Pa rameter estimation, Violations of unidimensionality.

Academic Achievement of Children and Adolescents With Oral Clefts

BACKGROUND AND OBJECTIVE: Previous studies of academic achievement of children with oral clefts have mostly relied on small, clinic-based samples prone to ascertainment bias. In the first study in the United States to use a population-based sample with direct assessment, we evaluated the academic achievement of children with oral clefts relative to their classmates. METHODS: Children born with isolated oral clefts in Iowa from 1983 to 2003 were identified from the Iowa Registry for Congenital and Inherited Disorders and matched to unaffected classmates by gender, school/school district, and month and year of birth. Academic achievement was assessed by using standardized tests of academic progress developed by the Iowa Testing Programs. Iowa Testing Programs data were linked to birth certificates for all children. Regression models controlled for household demographic and socioeconomic factors. The analytical sample included 588 children with clefts contributing 3735 child-grade observations and 1874 classmates contributing 13 159 child-grade observations. RESULTS: Children with oral clefts had lower scores than their classmates across all domains and school levels, with a 5-percentile difference in the overall composite score. Children with clefts were approximately one-half grade level behind their classmates and had higher rates of academic underachievement and use of special education services by 8 percentage points. Group differences were slightly lower but remained large and significant after adjusting for many background characteristics. CONCLUSIONS: Children with oral clefts underperformed across all academic areas and grade levels compared with their classmates. The results support a model of early testing and intervention among affected children to identify and reduce academic deficits.

Children with oral clefts are at greater risk for persistent low achievement in school than classmates

Objectives To examine trajectories in academic achievement for children with oral clefts versus unaffected classmates and explore predictors of persistently low achievement among children with oral clefts. Design Longitudinal cohort study of academic achievement in a population-based sample. Setting and participants Children born from 1983 through 2003 with oral clefts were identified from the Iowa Registry for Congenital and Inherited Disorders and matched to unaffected classmates by sex, school/school district and month and year of birth. Main outcome measures Academic achievement was measured from Iowa Testing Programs data. Outcomes included achievement scores in reading, language and mathematics. Results Academic achievement data were available for 586 children with oral clefts and 1873 unaffected classmates. Achievement trajectories were stable for both groups. Children with oral clefts were more likely than their classmates to be classified into persistent low achievement trajectories, including when adjusting for socioeconomic differences: OR=1.63, 95% CI 1.23 to 2.16 for reading; OR=1.73, 95% CI 1.29 to 2.31 for language; OR=1.45, 95% CI 1.05 to 1.99 for math. Predictors of low achievement were cleft palate only (vs other cleft types), adolescent mothers, low maternal education and less frequent use of prenatal care. Conclusions Most children have steady academic trajectories and children with oral clefts are at greater risk for persistent low achievement in school than unaffected classmates. These findings support the need for routine, early screening for academic deficits in this population. Cleft palate only, low parental education and adolescent mothers are associated with increased risk for persistent low achievement.

The Predictive Relationship of ITBS and ITED to Measures of Academic Success.

This study investigated the relationship between achievement test scores on the Iowa Tests of Basic Skills, the Iowa Tests of Educational Development, and academic success, as measured by high school and first-year college grade point averages (GPA). The population consisted of 1,147 students who entered the University of Iowa as freshmen in 1991. Achievement test scores obtained in Grades 3 through 12 were available for a substantial portion of the population, along with high school and college GPAs. The correlational analyses indicated that there were significant relationships between 3rd- through 12th-grade achievement test measures and GPA. However, the magnitudes of these relationships, contrary to previous findings, were surprisingly low.

Comparing the Visual Analogue Scale and the Pediatric Quality of Life Inventory for measuring health-related quality of life in children with oral clefts.

Objectives: To evaluate the performance of the Visual Analogue Scale (VAS), in measuring overall health-related Quality of Life (HRQoL) in children with oral clefts relative to the Pediatric Quality of Life Inventory 4.0 (PedsQLTM) Generic Core Scales, one of the most validated and commonly used methods to measure pediatric HRQoL. Methods: The study included a population-based sample of 307 children aged 5 to 10 years who were born in Iowa, New York, and Arkansas with non-syndromic oral clefts. Data on HRQoL were obtained using a VAS and PedsQLTM via self-administered interviews with the parents. We evaluated the correlations between the VAS and PedsQLTM total scores, and the correlations of each of these two scales with a series of child health and wellbeing indicators. Results: The VAS and PedsQLTM scores were well-correlated (r = 0.67). There were no prominent differences between the correlations of VAS and PedsQLTM with the selected indicators of child health and wellbeing; differences in correlations were less than 0.1. Differences in HRQoL by cleft type were more pronounced on the PedsQLTM. Conclusions: Our study finds the VAS to perform relatively well in measuring overall HRQoL among children with oral clefts. The VAS may be useful as a screening tool to identify children with oral clefts at risk of low HRQoL for referral into more comprehensive evaluations and for measuring average HRQoL across a sample of children.

Laterality of Oral Clefts and Academic Achievement

BACKGROUND AND OBJECTIVES: Children with isolated oral clefts have lower academic performance when compared with unaffected peers, yet few studies have examined specific attributes of clefts that may modify this risk. Oral clefts have nonrandom laterality, with left-sided clefts being more common than right-sided clefts, a pattern that may be genetically or environmentally influenced. The objective of this study was to evaluate the association between cleft laterality and academic achievement in a population-based sample of children with and without isolated oral clefts. METHODS: The study included 292 children with isolated unilateral cleft lip with or without cleft palate identified by using the Iowa Registry for Congenital and Inherited Disorders matched with 908 unaffected classmates. This group provided 1953 child-grade observations for cases and 6829 for classmates. Academic achievement was evaluated by using high-quality standardized test data on multiple academic domains as well as use of special education. RESULTS: We found that children with right-sided clefts had similar achievement scores and usage of special education services compared with their unaffected classmates. Children with left-sided clefts had lower reading scores than children with right-sided clefts by nearly 7 percentiles (P < .05). They also had lower scores on all evaluated domains by 4 to 6 percentiles and greater use of special education services by 6 percentage points than their classmates. CONCLUSIONS: Children with left-sided clefts had poorer academic performance than their classmates or children with right-sided clefts, who showed similar academic achievement compared with their unaffected classmates.

Relationship of elementary and secondary school achievement test scores to college performance

This study investigated the relationship between achievement test scores on the ITBS and ITED and academic success in college. The basic population consisted of approximately 2000 students who entered the University of Iowa as freshmen in 1977. Achievement test scores obtained in grades 4, 6, 8, 9, 10, 11, and 12 were available for a substantial portion of the population. Three measures of academic success in college were used: (1) first semester grade point average (December, 1977); (2) grade point average as of December, 1982; (3) graduation status (graduated/not graduated) as of December, 1982. Correlations between the achievement test scores and measures of college performance were similar to those reported for tests of the college entrance type. This study provides support for the predictive validity of the ITBS and ITED achievement test batteries.

The Importance of Computational Skill for Answering Items in a Mathematics Problem Solving Test: Implications for Construct Validity

The primary purpose of this study was to investigate the importance of computational skill for answering items in the Quantitative Thinking subtest (Test Q) of the Iowa Tests of Educational Development (ITED). Nine matched pairs of schools participated in the study. One school from each pair allowed students to use calculators when taking Test Q, while the other school did not allow calculators to be employed. The difficulty levels of the items in Test Q were calculated for both test conditions. In general, the differences in p values were very small. On the basis of these results, it was concluded that computational skill is not a major factor contributing to an examinees score on Test Q and thus that the use of Test Q as a measure of problem solving ability is not compromised by its computational requirements.

An Empirical Investigation of Methods for Assessing Item Fit for Mixed Format Tests

Empirical information regarding performance of model-fit procedures has been a persistent need in measurement practice. Statistical procedures for evaluating item fit were applied to real test examples that consist of both dichotomously and polytomously scored items. The item fit statistics used in this study included the PARSCALEs , Orlando and Thissens (2000) and , and Stones (2000) and . The results of this study indicated that the fit of an individual item was affected by the choice of model-fit analyses. The performance of fit indices appeared to vary depending on item response theory (IRT) model mixtures used for calibration, sample size, and test length. In terms of consistency among the fit indices, the statistics based on the same approach (e.g., and ) showed considerably higher agreement in detecting misfitting items than the statistics based on different approaches (e.g., and ). Consistent and inconsistent findings compared to previous research are discussed along with practical implications.