Measuring Cognitive Function and Cognitive Decline with Response Time Data in NSHAP.

OBJECTIVES: Scholarly, clinical, and policy interest in cognitive function has grown over the last several decades in part due to large increases in Alzheimer's Disease and related dementias as populations age. However, adequate measures of cognitive function have not been available in many research data sets. We argue that a wealth of previously unexploited survey data exists to model cognition and cognitive decline. METHODS: We use metadata of the time it takes older respondents in the National Social Life, Health and Aging Survey, which we label response times (RT), to answer questions in a standard cognitive assessment. We compare several measures of RT to a survey-adapted form of the Montreal Cognitive Assessment (MoCA). RESULTS: We show that RT predict both concurrent and future MoCA scores. Our results show that longer and more varied RT at baseline predict lower MoCA scores five year later, net of baseline scores and controls. We also show that the effect of RT measures on predicting current MoCA differ for individuals of different races and ages, but are not different by gender. DISCUSSION: Our paper demonstrates that RT constitute a separate powerful measure of cognitive functioning. RT may be remarkably useful both to clinicians and social scientists because they can increase accuracy of cognitive assessment without increasing the time it takes to administer the assessment.

The Methuselah Effect: The Pernicious Impact of Unreported Deaths on Old-Age Mortality Estimates.

We examine inferences about old-age mortality that arise when researchers use survey data matched to death records. We show that even small rates of failure to match respondents can lead to substantial bias in the measurement of mortality rates at older ages. This type of measurement error is consequential for three strands in the demographic literature: (1) the deceleration in mortality rates at old ages; (2) the black-white mortality crossover; and (3) the relatively low rate of old-age mortality among Hispanics, often called the "Hispanic paradox." Using the National Longitudinal Survey of Older Men matched to death records in both the U.S. Vital Statistics system and the Social Security Death Index, we demonstrate that even small rates of missing mortality matching plausibly lead to an appearance of mortality deceleration when none exists and can generate a spurious black-white mortality crossover. We confirm these findings using data from the National Health Interview Survey matched to the U.S. Vital Statistics system, a data set known as the "gold standard" (Cowper et al. 2002) for estimating age-specific mortality. Moreover, with these data, we show that the Hispanic paradox is also plausibly explained by a similar undercount.

Predictive Inference Using Latent Variables with Covariates.

Plausible values (PVs) are a standard multiple imputation tool for analysis of large education survey data, which measures latent proficiency variables. When latent proficiency is the dependent variable, we reconsider the standard institutionally generated PV methodology and find it applies with greater generality than shown previously. When latent proficiency is an independent variable, we show that the standard institutional PV methodology produces biased inference because the institutional conditioning model places restrictions on the form of the secondary analysts' model. We offer an alternative approach that avoids these biases based on the mixed effects structural equations model of Schofield (Modeling measurement error when using cognitive test scores in social science research. Doctoral dissertation. Department of Statistics and Heinz College of Public Policy. Pittsburgh, PA: Carnegie Mellon University, 2008).

Effect of a home intervention program on pediatric asthma in an environmental justice community.

Asthma prevalence rates are at an all-time high in the United States with over 25 million persons diagnosed with asthma. African Americans and other minorities have higher asthma prevalence and higher exposure to environmental factors that worsen asthma as compared to Caucasians. This article describes the evaluation of an inner-city home-based asthma education and environmental remediation program that addressed both indoor and outdoor triggers through collaboration between a health system and local environmental justice organization. The program enrolled 132 children older than 2.5 years and centers on a 4- to 6-week intervention with peer counselors using the U.S. Environmental Protection Agency Asthma Home Environment Checklist and the You Can Control Asthma curriculum. Families receive asthma-friendly environmental home kits. Peer counselors reinforce key asthma management messages and facilitate the completion of Asthma Action Plans. The environmental justice community partner organized block cleanups to reduce outdoor triggers. The evaluation used a pretest-posttest design to assess changes in client behavior and asthma symptoms. Data were collected at baseline and during a 6-month postintervention period. Participants saw enhanced conditions on asthma severity and control. The improvement was greatest for children whose asthma was considered "severe" based on the validated Asthma Control Test. Other positive results include the following: greater completion of Asthma Action Plans, significant reduction in the number of emergency room visits (p = .006), and substantial decreases in school absenteeism (p = .008) and use of rescue medications (p = .049). The evaluation suggests that the program was effective in improving asthma self-management in a high-risk population living within an environmental justice community.

CORRECTING FOR MEASUREMENT ERROR IN LATENT VARIABLES USED AS PREDICTORS.

This paper represents a methodological-substantive synergy. A new model, the Mixed Effects Structural Equations (MESE) model which combines structural equations modeling and item response theory is introduced to attend to measurement error bias when using several latent variables as predictors in generalized linear models. The paper investigates racial and gender disparities in STEM retention in higher education. Using the MESE model with 1997 National Longitudinal Survey of Youth data, I find prior mathematics proficiency and personality have been previously underestimated in the STEM retention literature. Pre-college mathematics proficiency and personality explain large portions of the racial and gender gaps. The findings have implications for those who design interventions aimed at increasing the rates of STEM persistence among women and under-represented minorities.

Measurement Error in the AFQT in the NLSY79.

Many promising efforts in the social sciences aim to measure future outcomes (such as wages or health outcomes) given some base level of human capital or ability. They typically fail to recognize the proxies for human capital are all measured with error, creating bias in regression analysis. Here I show how item level data offers the opportunity to improve a broad range of economic, social and psychometric studies; an opportunity now enhanced significantly by the new release of item response level data for the Armed Forces Qualifying Test in the 1979 National Longitudinal Survey of Youth.

The use of cognitive ability measures as explanatory variables in regression analysis.

Cognitive ability measures are often taken as explanatory variables in regression analysis, e.g., as a factor affecting a market outcome such as an individual's wage, or a decision such as an individual's education acquisition. Cognitive ability is a latent construct; its true value is unobserved. Nonetheless, researchers often assume that a test score, constructed via standard psychometric practice from individuals' responses to test items, can be safely used in regression analysis. We examine problems that can arise, and suggest that an alternative approach, a "mixed effects structural equations" (MESE) model, may be more appropriate in many circumstances.