计量经济分析 = Econometric analysis

25. Multiple Imputation for Nonresponse in Surveys. By D. B. Rubin. ISBN 0 471 08705 X. Wiley, Chichester, 1987. 258 pp. £30.25.

Multiple Imputation for Nonresponse in Surveys

The Bootstrap and Edgeworth Expansion

Importance It is important to estimate the burden of and trends for violence, crime, and abuse in the lives of children. Objective To provide health care professionals, policy makers, and parents with current estimates of exposure to violence, crime, and abuse across childhood and at different developmental stages. Design, Setting, and Participants The National Survey of Children’s Exposure to Violence (NatSCEV) includes a representative sample of US telephone numbers from August 28, 2013, to April 30, 2014. Via telephone interviews, information was obtained on 4000 children 0 to 17 years old, with information about exposure to violence, crime, and abuse provided by youth 10 to 17 years old and by caregivers for children 0 to 9 years old. Main Outcome and Measure Exposure to violence, crime, and abuse using the Juvenile Victimization Questionnaire. Results In total, 37.3% of youth experienced a physical assault in the study year, and 9.3% of youth experienced an assault-related injury. Two percent of girls experienced sexual assault or sexual abuse in the study year, while the rate was 4.6% for girls 14 to 17 years old. Overall, 15.2% of children and youth experienced maltreatment by a caregiver, including 5.0% who experienced physical abuse. In total, 5.8% witnessed an assault between parents. Only 2 significant rate changes could be detected compared with the last survey in 2011, namely, declines in past-year exposure to dating violence and lifetime exposure to household theft. Conclusions and Relevance Children and youth are exposed to violence, abuse, and crime in varied and extensive ways, which justifies continued monitoring and prevention efforts.

/pdf/prevalence-of-childhood-exposure-to-violence-crime-and-abuse-4ch7j13yv6.pdf

Prevalence of Childhood Exposure to Violence, Crime, and Abuse: Results From the National Survey of Children’s Exposure to Violence

The American political science review

When the economy in a single country contracts, voters often punish the government. When many economies contract, voters turn against their governments much less frequently. This suggests that the international context matters for the domestic vote, yet most research on electoral accountability assumes that voters treat their national economies as autarkic. We decompose two key economic aggregates—growth in real gross domestic product and unemployment—into their international and domestic components and demonstrate that voters hold incumbents more electorally accountable for the domestic than for the international component of growth. Voters in a wide variety of democracies benchmark national economic growth against that abroad, punishing (rewarding) incumbents for national outcomes that underperform (outperform) an international comparison. Tests suggest that this effect arises not from highly informed voters making direct comparisons but from “pre-benchmarking” by the media when reporting on the economy. The effect of benchmarked growth exceeds that of aggregate national growth by up to a factor of two and outstrips the international component of growth by an even larger margin, implying that previous research may have underestimated the strength of the economy on the vote.

Benchmarking across Borders: Electoral Accountability and the Necessity of Comparison

Traditional accounts of clientelism typically focused on patron–client relations with minimal scope for citizen autonomy. Despite the heightened agency of many contemporary citizens, most studies c...

Request Fulfilling: When Citizens Demand Clientelist Benefits:

All surveys with less than full response potentially suffer from nonresponse bias. Poststratification weights can only correct for selection into the sample based on observables whose distribution is known in the population. Variables such as gender, race, income, and region satisfy this requirement because they are available from the U.S. Census Bureau, but poststratification based on these variables may not eliminate nonresponse bias. I develop an approach for correcting for nonignorable nonresponse bias. Survey respondents can be classified by their “response propensity.” Proxies for response propensity include the number of attempted phone calls, indicators of temporary refusal, and interviewer-coded measures of cooperativeness. We can then learn about the population of nonrespondents by extrapolating from the low-propensity respondents. I apply this new estimator to correct for unit nonresponse bias in the American National Election Study and in a CBS / New York Times preelection poll. I find that no...

Correcting for Survey Nonresponse Using Variable Response Propensity

Theories of lawmaking generate predictions for the policy outcome as a function of the status quo. These theories are difficult to test because the widely applied ideal point estimation techniques do not recover the locations of proposals or status quos. Instead, such techniques only recover cutpoints. This limitation has meant that most existing tests of theories of lawmaking have been indirect in nature. I propose a method of directly measuring ideal points, proposal locations, and status quo locations on the same scale, by employing a combination of voting data, bill and amendment cosponsorship data, and the congressional record. My approach works as follows. First, we can identify the locations of legislative proposals (bills and amendments) on the same scale as voter ideal points by jointly scaling voting and cosponsorship data. Next, we can identify the location of the final form of the bill using the location of the last successful amendment (which we already know). If the bill was not amended, the...

Estimating Proposal and Status Quo Locations Using Voting and Cosponsorship Data

We study the targeting of political advertising by congressional candidates on television. Targeting strategies for television dier from targeting strategies for direct mail advertising or get out the vote eorts because candidates cannot target voters individually. Instead, candidates must target television programs with viewers most similar to the desired target voters. Thus, for targeted advertising to have value, the audiences for television programs must dier in mean

Michael Peress

Papers

Benchmarking across Borders: Electoral Accountability and the Necessity of Comparison

Request Fulfilling: When Citizens Demand Clientelist Benefits:

Correcting for Survey Nonresponse Using Variable Response Propensity

Estimating Proposal and Status Quo Locations Using Voting and Cosponsorship Data

Targeting Political Advertising on Television