Trust in Government: Personal Ties that Bind?

Objective . This research note compares the views of the federal government held by federal government workers, their family members, their close friends, and state and local government workers to the views held by other U.S. citizens. Methods . We analyze data from a 2000 survey of Washington, D.C. metropolitan-area residents. Results . Respondents employed at any level of government—not only federal but also state and local—trust the federal government more than respondents with no ties to government. Being the family member or friend of a federal government employee has no impact on trust in government. Conclusions . A confidence gap divides government employees from the rest of the public.     

The Symmetry Rule: A Seven‐Year Study of Symptoms and Explanatory Labels Among Gulf War Veterans

Noticing medical symptoms can cause one to search for explanatory labels such as “ate bad food” or even “exposed to anthrax,” and perhaps these labels may cause new symptom reports. The present study examined whether there is empirical support for this symptom‐label “symmetry rule.” We interviewed veterans (N= 362) from the Gulf War Registry in 1995 and 2002 about their medical symptoms and about their exposure to war‐related hazards and stressors. Health symptom reports were strongly correlated between the two time periods and showed relatively stable mean levels, whereas recall of war‐related exposures was notably unstable. Veterans starting with fewer medical symptoms recalled fewer war‐related exposures seven years later. Initial recollection of chemical and biological warfare exposure (but not other exposures) longitudinally predicted novel medical symptoms. The findings generally support the symmetry rule hypotheses, although the evidence for the label to symptom link was less strong. The findings account for some variability in symptoms and exposure recall over time, but they do not, on their own, account for the Gulf War veterans' elevated number of unexplained medical symptoms.     

Attitudes Toward Married Persons’ Surnames in Twenty-First Century Japan

Through Article 750 of the Japanese Civil Code, Japan is the only developed country to require that a married couple must choose either the husband’s or the wife’s surname upon marriage. We examine how traditional gender ideology and preference for the three-generation family household are associated with the level of support for conjugal surname sharing, from full support for the wife taking her husband’s surname to support for neither the wife or husband changing their name. We estimate generalized ordered logit models with data from the 2000–2003, 2006, and 2010 Japanese General Social Survey. Findings indicate that those who hold more traditional gender ideology are more likely to endorse surname sharing at all levels. Those who prefer the traditional extended family household are more likely to acknowledge at least some merit in a married couple sharing a surname, but they are less likely to say that the wife should take her husband’s surname without question. Attitudes toward conjugal surname sharing may have important symbolic implications for gender equality as well as potential impact on the surname law.     

Measures and tests of heaping in discrete quantitative distributions

Heaping is often found in discrete quantitative data based on subject responses to open-ended interview questions or observer assessments. Heaping occurs when subjects or observers prefer some set of numbers as responses (e.g. multiples of 5) simply because of the features of this set. Although heaping represents a common type of measurement error, apparently no prior general measure of heaping exists. We present simple measures and tests of heaping in discrete quantitative data, illustrate them with data from an epidemiologic study, and evaluate the bias of these statistics. These techniques permit formal measurement of heaping and facilitate comparisons of the degree of heaping in data from different samples, substantive domains, and data collection methods.     

IS THE ASSUMPTION OF UNIFORM INTRA-CLASS CORRELATION EVER NEEDED?

When modelling a finite population it is sometimes assumed that the residuals from the regression model expectations are distributed with a uniform non-zero intra-class correlation. It is shown that if a certain vector is spanned by the columns of the design matrix (in the homoskedastic case this vector corresponds to the inclusion of a constant term) then such a model is underidentified and the assumption of a known non-zero correlation has almost no impact on the results of the regression analysis. When this vector is not spanned by the columns of the design matrix, a simpler alternative model can usually be fitted equally well to observations from any single population. The only exception occurs when the the intra-class correlation required is negative in sign.