Allison, J.J., Calhoun, J.W., Wall, T.C., and others (2000). "Optimal reporting of health care process measures: Inferential statistics as help or hindrance?" (AHRQ grant HS08843). Managed Care Quarterly 8(4), pp. 1-10.
Measurement of specific aspects of medical care provides the starting point for quality improvement. Often this measurement takes the form of a "practice profile," which compares performance patterns of physicians, physician groups, health care organizations, or even larger aggregations such as geographic regions. The authors of this paper discuss the appropriate application of inferential statistics to practice profiles and other measures of care. They describe the relative merits of measuring three well-recognized domains of medical quality: structure, process, and outcome. Next, they discuss inferential statistics as used in quality improvement. Finally, they describe several common circumstances that arise in the measurement of medical care, focusing on the application of inferential statistics to each situation.
Asmussen, L., Olson, L.M., Grant, E.N., and others. (2000). "Use of the child health questionnaire in a sample of moderate and low-income inner-city children with asthma." (AHRQ grant HS08368). American Journal of Respiratory and Critical Care Medicine 162, pp. 1215-1221.
The Child Health Questionnaire (CHQ-PF50) is one of several recent efforts to gauge pediatric, health-related quality of life from the patient's (or parent's) perspective. Although the CHQ has been tested extensively with healthy children, more information is needed about its performance among children with chronic conditions such as asthma. Seventy-four adult caregivers of children with asthma completed the CHQ. Tests of validity found CHQ scales better at distinguishing levels of disease severity as defined by symptoms than medication use or pulmonary function tests. Performance of the CHQ in a sample of low income to moderate income inner-city parents of children with asthma presented mixed results. Some scales were better than others in assessing the health status of children at highest risk for asthma morbidity. Future efforts should focus on comparison of condition-specific and generic instruments.
Calhoun, P.S., Earnst, K.S., and Tucker, D.T. (2000). "Feigning combat-related posttraumatic stress disorder on the personality assessment inventory." (AHRQ National Research Service Award training grant T32 HS00079). Journal of Personality Assessment 75(2), pp. 338-350.
To avoid prosecution or gain financial compensation (via personal injury or workman's compensation claims), some individuals exaggerate their symptoms, which can complicate the diagnosis of combat-related posttraumatic stress disorder (PTSD). These researchers examined whether individuals who were instructed about the criteria for PTSD could feign PTSD on the Personality Assessment Inventory (PAI). They also studied whether PAI indexes of symptom exaggeration—the Negative Impression Management (NIM) scale and the Malingering Index—could identify individuals feigning PTSD. The diagnostic rule for PTSD was applied to profile a group of 23 veterans with combat-related PTSD and 23 male college students instructed to feign PTSD. Seventy percent of the student malingerers produced profiles that received diagnostic consideration for PTSD. The vulnerability of all psychological measures to exaggeration or faking underscores the importance of obtaining information from multiple sources in the assessment of PTSD.
Dalton, K., and Norton, E.C. (2000). "Revisiting Rogowski and Newhouse on the indirect costs of teaching: A note on functional form and retransformation in Medicare's payment formulas." (National Research Service Award training grant T32 HS00032). Journal of Health Economics 19, pp. 1027-1046.
In 1992 Rogowski and Newhouse identified errors in functional form and retransformation in the econometric model that underlies Medicare's payments to teaching hospitals. These authors re-estimate the original model and expand on the work of Rogowski and Newhouse using data from the following decade. They found that the functional form imposed by the Health Care Financing Administration's original specification of the teaching variable was supported by the data. There was no evidence of a threshold effect when the teaching intensity variable was appropriately specified, and there was no need to incorporate re-transformation factors into the payment formula. The authors attribute their findings to secular changes in the hospital industry and improvements in variable measurement.
Orlando, M., Sherbourne, C.D., and Thissen, D. (2000). "Summed-score linking using item response theory: Application to depression measurement." (AHRQ grant HS08349). Psychological Assessment 12(3), pp. 354-359.
Item response theory (IRT) comprises a collection of modeling techniques to analyze items, tests, and people. When the assumptions of the IRT model are met, this collection of techniques offers many advantages over traditional test theory and can be a powerful tool for test construction. In this study, the researchers demonstrate an IRT approach to test linking based on summed scores by calibrating a modified 23-item version of the Center for Epidemiologic Studies Depression Scale (CES-D) to the standard 20-item CES-D. Responses to items on both the original and modified versions were calibrated simultaneously using F. Samejima's graded IRT model. The two scales were linked on the basis of derived summed-score-to-IRT-score translation tables. The established cut score of 16 on the standard CES-D corresponded most closely to a summed score of 20 on the modified version. The authors conclude that the IRT summed-score approach to test linking is a straightforward, valid, and practical method that can be applied in a variety of situations.
Return to Contents
Current as of February 2001
AHRQ Publication No. 01-0019
Internet Citation:
Research Activities newsletter. February 2001, No. 246. AHRQ Publication No. 01-0019. Agency for Healthcare Research and Quality, Rockville, MD. http://www.ahrq.gov/research/feb01/
540 Gaither Road Rockville, MD 20850