Social and Behavioral Sciences Commons^™

A Positive Trait Item Response Model, Joseph F. Lucke

Joseph Lucke

All current models from item response theory (IRT) assume the latent trait follows a standard normal distribution. While this assumption is appropriate for traits such as ability or attitude, it creates both conceptual and technical problems traits such as addiction (alcohol, drugs, gambling). The distribution of an addiction trait is better assumed to be anchored at zero (no addiction) and positively skewed. A small change to the usual IRT model yields a class of positive-trait item response models (PTIRMs). I discuss PTIRMs and present one model in detail, including item characteristic curves and item information curves. I present an example …

A Critique Of The False-Positive Report Probability, Joseph Lucke

Joseph Lucke

The false positive report probability (FPRP) was proposed as a Bayesian prophylactic against false reports of significant associations. Unfortunately, the derivation of the FPRP is unsound. A heuristic derivation fails to make its point, and a formal derivation reveals a probabilistic misrepresentation of an observation. As a result, the FPRP can yield serious inferential errors. In particular, the FPRP can use an observation that is many times more likely under the null hypothesis than under the alternative to infer that the null hypothesis is far less probable than the alternative. Contrary to its intended purpose, the FPRP can promote false …

"Rassling The Hog": The Influence Of Correlated Item Error On Internal Consistency, Classical Reliability, And Congeneric Reliability, Joseph F. Lucke

Joseph Lucke

The properties of internal consistency ($\alpha$), classical reliability ($\rho$), and congeneric reliability ($\omega$) for a composite test with correlated item error were analytically investigated. Possible sources of correlated item error are contextual effects, item bundles, and item models that ignore additional attributes or higher-order attributes. The relation between reliability and internal consistency is determined by the deviance from true-score equivalence. Reliability (classical or congeneric) is internal consistency plus the relative deviance from true-score equivalence. The influence of correlated item error on $\alpha$, $\rho$, and $\omega$ is conveyed strictly through the total item error covariance. As the total item error covariance …

Benchmarking Patient Outcomes, Ellen B. Rudy, Joseph F. Lucke, Gayle R. Whitman, Lynda J. Davidson

Joseph Lucke

Purpose: To examine the usefulness of three types of benchmarking for interpreting patient outcome data.

Design: This study was part of a multiyear, multihospital longitudinal survey of 10 patient outcomes. The patient outcome used for this methodologic presentation was central line infections (CLI). The sample included eight hospitals in an integrated healthcare system, with a range in size from 144 to 861 beds. The unit of analysis for CLI was the number of line days, with the CLI rate defined as the number of infections per 1,000 patient-line days per month.

Methods: Data on each outcome were collected at the …

Intracellular Coexpression Of Epidermal Growth Factor Receptor, Her-2/Neu, And P21ras In Human Breast Cancers: Evidence For The Existence Of Distinctive Patterns Of Genetic Evolution That Are Common To Tumors From Different Patients, Stanley E. Shackney, Agnese A. Pollice, Charles A. Smith, Laura E. Janocko, Lillian Sweeney, Kathryn A. Brown, Sarita G. Singh, Lingping Gu, Robert Yakulis, Joseph F. Lucke

Joseph Lucke

Multiparameter flow cytometry studies were performed on cells from the primary tumors of 94 patients with breast cancer. Correlated cellular measurements of cell DNA content, Her-2/neu, epidermal growth factor receptor (EGFR), and p21ras levels were performed on each of 5,000 to 100,000 cells from each tumor. When criteria for positivity were matched with those in common use for immunohistochemical studies, 28 of 94 (30\%) breast cancers were classified as positive for Her-2/neu overexpression. When similar criteria were applied to the EGFR measurements, 23 of 94 (24\%) cases were classified as positive for EGFR overexpression. Similarly, 23 of 94 (24\%) cases …

Neuroendocrine Aspects Of Primary Endogenous Depression Xv. Mathematical Modeling Of Nocturnal Melatonin Secretion In Major Depressives And Normal Controls, L. Kathleen Sekula, Joseph F. Lucke, E. Kevin Heist, R. Kenneth Czambel, Robert T. Rubin

Joseph Lucke

We previously reported a trend toward a higher mean nocturnal serum melatonin (MEL) concentration, based on 30-min blood sampling over 24 h, in 23 female definite endogenous depressives compared to 23 matched normal female control subjects, and no significant difference in 15 male depressives compared to their controls (Rubin et al., 1992). In both groups of patients vs. their controls, there also were trends toward an earlier MEL rise time, by about 30 min, and a later MEL peak time, by about 90 min. Because the offset of MEL secretion was not estimated in that study, the total duration of …

Student's T-Test And The Glasgow Coma Scale, Joseph Lucke

Joseph Lucke

Study Objective: To explore how Student's t test, which assumes normal errors, is affected by the nonnormal distribution of Glasgow Coma Scale (GCS) scores.

Methods: A sample of 145,295 GCS scores from the Pennsylvania Trauma Systems Foundation was assumed to represent the true GCS distribution. Four Monte Carlo simulations, each based on 40,000 replications, were conducted to approximate the distribution of t values arising from samples drawn from the GCS distribution, using sample sizes of 10, 30, 60, and 100 per group.

Results: The histograms of t values derived from the GCS distribution resembled the corresponding Student t distributions for …

Seizure Threshold In Electroconvulsive Therapy: I. Initial Seizure Threshold, C. Edward Coffey, Joseph Lucke, Richard D. Weiner, Andrew D. Krystal, Michael Aque

Joseph Lucke

We measured initial seizure threshold by means of a structured stimulus dosage titration procedure in a clinical sample of 111 depressed patients undergoing brief-pulse, constantcurrent electroconvulsive therapy (ECT). Initial seizure threshold was approximately 60 millicoumbs (mc) (10 Joules) on average, but varied widely (6-fold) across patients. Initial seizure threshold was predicted by four variables: electrode placement (higher with bilateral), gender (higher in men), age (higher with increasing age), and dynamic impedance (inverse relationship). Use of neuroleptic medication was associated with a lower seizure threshold. EEG seizure duration was inversely related to initial seizure threshold, but no other relations with seizure …

Seizure Threshold In Electroconvulsive Therapy (Ect): Ii. The Anticonvulsant Effect Of Ect, C. Edward Coffey, Joseph Lucke, Richard D. Weiner, Andrew D. Krystal, Michael Aque

Joseph Lucke

To measure the anticonvulsant effects of a course of electroconvulsive therapy (ECT), we used a flexible stimulus dosage titration procedure to estimate seizure threshold at the first and sixth ECT treatments in 62 patients with depression who were undergoing a course of brief pulse, constant current ECT given at moderately suprathreshold stimulus intensity. Seizure threshold increased by approximately 47% on average, but only 35 (56%) of the 62 patients showed a rise in seizure threshold. The rise in seizure threshold was associated with increasing age, but not with gender, stimulus electrode placement, or initial seizure threshold. Dynamic impedance decreased by …

Assessing Sequential Oncogene Amplification In Human Breast Cancer, Laura E. Janocko, Joseph F. Lucke, David W. Groft, Kathryn A. Brown, Charles A. Smith, Agnese A. Pollice, Sarita G. Singh, Robert Yakulis, Robert J. Hartsock, Stanley E. Shackney

Joseph Lucke

Studies of amplification and/or overexpression of c-myc, HER-2/neu, and H-ras in breast cancer have shown that each is associated with a poor prognosis. The purpose of this study was to explore the possibility that there is a preferred sequence of amplification of these oncogenes in breast cancer. The frequencies of amplification and patterns of co-amplification of c-myc, HER-2/neu, and H-ras were studied in a group of 84 breast cancers. The data suggested a preferred sequence of amplification that consisted of c-myc amplification-HER-2/neu amplification-H-ras amplification. This model was supported by loglinear analysis. In addition, the levels of amplification of JC-A, a …

Cirrhosis In The Trauma Victim --- Effect On Mortality-Rates, Glen Tinkoff, Michael Rhodes, Daniel Diamond, Joseph F. Lucke

Joseph Lucke

To evaluate the impact cirrhosis has on survival the records of 40 cirrhotic trauma victims from the registries of two Level 1 trauma centers were reviewed and probability of survival calculated using the TRISS methodology. Mechanism of injury, anatomic location, involvement of single or multiple sites, presence of ascites, elevations in serum glutamic oxaloacetic transaminase (SGOT), alkaline phosphatase, serum bilirubin, prothrombin time (PT), and hypoalbuminemia were tabulated for each patient. Contingency tables were created for injury and hepatic parameters, as related to survival, and subjected to chi square analysis. Loglinear analysis was performed on all significant parameters to evaluate the …

The Biases And Mean Squared Errors Of Estimators Of Multinormal Squared Multiple Correlation, Joseph F. Lucke, Susan E. Embretson

Joseph Lucke

The sample squared multiple correlation coefficient, $R^{2}$ is known to have certain unsatisfactory properties as an estimator of the population squared multiple correlation. Hence, numerous adjusted estimators based on functions of $1-R^{2}$ have been proposed. We examine the biases and mean squared errors of five adjusted estimators as well as $R^{2}$. General results are given for estimators linear in $1-R^{2}$, and four such estimators are examined in detail. In addition, a quadratic estimator and the minimum variance unbiased estimator are examined. Comparisons among these estimators are made in terms of absolute bias and mean squared error.