Proxy (statistics)

About: Proxy (statistics) is a research topic. Over the lifetime, 5257 publications have been published within this topic receiving 94504 citations. The topic is also known as: proxy variable & proxy measurement.

Using Embeddings to Correct for Unobserved Confounding in Networks

Abstract: We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connecting the units. For example, the link structure of a social network carries information about its members. We show how to effectively use the proxy to do causal inference. The main idea is to reduce the causal estimation problem to a semi-supervised prediction of both the treatments and outcomes. Networks admit high-quality embedding models that can be used for this semi-supervised prediction. We show that the method yields valid inferences under suitable (weak) conditions on the quality of the predictive model. We validate the method with experiments on a semi-synthetic social network dataset. Code is available at this http URL.

Estimating Production Functions with Heterogeneous Firms

Abstract: We present a new approach to the estimation of production functions that allows for richer patterns of firm heterogeneity than can be accommodated under the proxy variable methods of and Olley/Pakes and Levinsohn/Petrin. In particular, we show that the economics of the firms static input choice contains the necessary identifying information to control for the endogeneity problem in the production function. From an econometric point of view, our estimation proceeds in a single GMM step, and thus standard asymptotic standard errors are available. We consider the identification and estimation of models with heterogeneity in both input and output prices, as well as heterogeneity in factor specific productivity. Our empirical results show that we control for more of the endogeneity problem than the proxy variable approach, resulting in estimates of labor productivity nearly half as small.

Improved Non-Repudiable Threshold Proxy Signature Scheme with Known Signers

Abstract: In 2001, Hsu et al. proposed a non-repudiable threshold proxy signature with known signers. In their scheme, the proxy group cannot deny having signed the proxy signature if they did. However, Hsu et al.'s scheme is vulnerable to some attacks. A malicious original signer or malicious proxy signer can impersonate some other proxy signers to generate proxy signatures. In this article, we shall present our cryptanalysis of the Hsu et al.'s scheme. After that, we shall propose a new threshold proxy signature that can overcome the weaknesses.

Measuring children's self-efficacy and proxy efficacy related to fruit and vegetable consumption.

Abstract: BACKGROUND: Social cognitive theory describes self-efficacy and proxy efficacy as influences on fruit and vegetable consumption (FVC). Proxy efficacy was defined as a child’s confidence in his or her skills and abilities to get others to act in one’s interests to provide fruit and vegetable (FV) opportunities. The purpose of this study was to develop a scale assessing children’s self-efficacy and proxy efficacy for FVC at after-school programs and at home. METHODS: Elementary-aged children (n = 184) attending 7 after-school programs completed a self-efficacy questionnaire relevant to FVC. Questionnaire validity was investigated with exploratory factor analysis and mixed-model analysis of covariance. Internal consistency reliability and readability were also assessed. RESULTS: The questionnaire assessed 4 constructs: self-efficacy expectations for fruit consumption, self-efficacy expectations for vegetable consumption, proxy efficacy to influence parents to make FV available, and proxy efficacy to influence after-school staff to make FV available. Children perceiving FV opportunities in after-school had greater self-efficacy expectations for FVC and greater proxy efficacy to influence after-school staff compared to students who did not perceive FV opportunities. Children attending schools of higher socioeconomic status (SES) and less diversity were more confident they could influence their parents to make FV available than students attending lower SES and less diverse schools. Adequate internal consistency and test-retest reliabilities were established. CONCLUSIONS: Self-efficacy is a multicomponent construct that can be assessed in children using the reliable and valid instrument evaluated by the current study.