Occupational wage Inequality and Devaluation: A Cautionary Tale of Measurement Error

2000 ◽  
Vol 105 (6) ◽  
pp. 1752-1760 ◽  
Author(s):  
Tony Tam
ILR Review ◽  
2007 ◽  
Vol 60 (4) ◽  
pp. 522-543 ◽  
Author(s):  
Arindrajit Dube ◽  
Suresh Naidu ◽  
Michael Reich

This paper presents the first study of the economic effects of a citywide minimum wage—San Francisco's adoption of an indexed minimum wage, set at $8.50 in 2004 and $9.14 by 2007. Compared to earlier benchmark studies by Card and Krueger and by Neumark and Wascher, this study surveys table-service as well as fast-food restaurants, includes more control groups, and collects data for more outcomes. The authors find that the policy increased worker pay and compressed wage inequality, but did not create any detectable employment loss among affected restaurants. The authors also find smaller amounts of measurement error than characterized the earlier studies, and so they can reject previous negative employment estimates with greater confidence. Fast-food and table-service restaurants responded differently to the policy, with a small price increase and substantial increases in job tenure and in the proportion of full-time workers among fast-food restaurants, but not among table-service restaurants.


2017 ◽  
Vol 49 (1) ◽  
pp. 43-78 ◽  
Author(s):  
S. C. Noah Uhrig ◽  
Nicole Watson

Test–retest reliability assessments rarely investigate whether reliability itself is stable or change in reliability affects findings from substantive models. Research across the social sciences often recognizes that measurement error could influence results, yet it rarely applies established error correction methods. Focusing on gender wage inequality, we address two questions. First, to what extent does reliability vary over time, across genders and across measurement protocols? Second, does correcting for measurement error influence substantive conclusions about gender wage inequality? Comparing British and Australian panel data, we find little temporal variability in reliability; however, measurement error effects are variable and sometimes substantial.


1999 ◽  
Vol 15 (2) ◽  
pp. 91-98 ◽  
Author(s):  
Lutz F. Hornke

Summary: Item parameters for several hundreds of items were estimated based on empirical data from several thousands of subjects. The logistic one-parameter (1PL) and two-parameter (2PL) model estimates were evaluated. However, model fit showed that only a subset of items complied sufficiently, so that the remaining ones were assembled in well-fitting item banks. In several simulation studies 5000 simulated responses were generated in accordance with a computerized adaptive test procedure along with person parameters. A general reliability of .80 or a standard error of measurement of .44 was used as a stopping rule to end CAT testing. We also recorded how often each item was used by all simulees. Person-parameter estimates based on CAT correlated higher than .90 with true values simulated. For all 1PL fitting item banks most simulees used more than 20 items but less than 30 items to reach the pre-set level of measurement error. However, testing based on item banks that complied to the 2PL revealed that, on average, only 10 items were sufficient to end testing at the same measurement error level. Both clearly demonstrate the precision and economy of computerized adaptive testing. Empirical evaluations from everyday uses will show whether these trends will hold up in practice. If so, CAT will become possible and reasonable with some 150 well-calibrated 2PL items.


2003 ◽  
Author(s):  
Gerard J. Solan ◽  
Jean M. Casey

Sign in / Sign up

Export Citation Format

Share Document