We draw attention to two problems associated with the use of instrumental variables (IV), the importance of which for empirical work has not been fully appreciated. First, the use of instruments that explain little of the variation in the endogenous explanatory variables can lead to large inconsistencies in the IV estimates even if only a weak relationship exists between the instruments and the error in the structural equation. Second, in finite samples, IV estimates are biased in the same direction as ordinary least squares (OLS) estimates. The magnitude of the bias of IV estimates approaches that of OLS estimates as the R 2 between the instruments and the endogenous explanatory variable approaches 0. To illustrate these problems, we reexamine the results of a recent paper by Angrist and Krueger, who used large samples from the U.S. Census to estimate wage equations in which quarter of birth is used as an instrument for educational attainment. We find evidence that, despite huge sample sizes, th...

https://www.jstor.org/stable/pdfplus/2291055.pdf

Problems with Instrumental Variables Estimation when the Correlation between the Instruments and the Endogenous Explanatory Variable is Weak

This classic volume outlines, for both students and professionals, the mathematical theories and equations that are necessary for evaluating a test and for quantifying its characteristics. The author utilizes formulas that evaluate both the reliability and the validity of tests. He also provides the means for evaluating the reliability and validity of total test scores and individual item analysis. The work remains one of the only books on classical test theory to discuss applications, "true score" theory, the effect of test length on reliability and validity, and the effects of univariate and multivariate selection on validity.

Theory of mental tests

The measurement and appraisal of adult intelligence, 4th ed.

The relation of bilingualism to intelligence.

This study was conducted to compare the Performance Scale 1Q's and Performance subtest scaled scores of deaf children who had been tested on the Wechsler Intel l igence Scale for Children (WISC) and the Wechsler Intel l igence Scale for Children-Revised (WISC-R) The study investigated whether the original test (WISC) and i ts revision (WISC-R) would show signif icant differences between the Performance Scale IQ's and Performance subtest scaled scores when both tests were given to the same group of deaf children All 73 subjects were students in one of three state residential schools for the deaf located in California, Arizona and Colorado The research group was hi boys and 31 gir ls with ages ranging from ten through f i f teen Children were selected as subjects i f they had been tested with either a WISC or WISC-R longer than four months prior to but less than two years before the t ime of the present investigation Depending on which test (WISC or WISC-R) was reported in the child's psychometric f i le, he was given the other test for the comparative purpose of this study Sixty-six children had previous testing with the WISC-R and, therefore, were administered the WISC; seven children had had the WISC and were given the WISC-R Mean differences in the IQ's and subtest scaled scores between the two tests were analyzed by t-tests to detect signif icant differences between scores

A comparative study of performance scale iq's and subtest scores of deaf children on the wechsler intelligence scale for children and the wechsler intelligence scale for children-revised

Rudolf Pintner

Papers

A scale of performance tests

The psychology of the physically handicapped

A measurement of the language ability of deaf children.

A comparison of deaf and hearing children in visual memory for digits

Four retests of a personality inventory.