scholarly journals Towards Providing Automated Feedback on the Quality of Inferences from Synthetic Datasets

2012 ◽  
Vol 4 (1) ◽  
Author(s):  
David R. McClure ◽  
Jerome P. Reiter
Keyword(s):  
Synthetic Data ◽  
Stochastic Perturbation ◽  
Secondary Data ◽  
Quality Measures ◽  
Individual Level ◽  
The Public ◽  
Level Data ◽  
Synthetic Datasets ◽  
Automated Feedback

When releasing individual-level data to the public, statistical agencies typically alter data values to protect the confidentiality of individuals’ identities and sensitive attributes. When data undergo substantial perturbation, secondary data analysts’ inferences can be distorted in ways that they typically cannot determine from the released data alone. This is problematic, in that analysts have no idea if they should trust the results based on the altered data.To ameliorate this problem, agencies can establish verification servers, which are remote computers that analysts query for measures of the quality of inferences obtained from disclosure-protected data. The reported quality measures reflect the similarity between the analysis done with the altered data and the analysis done with the confidential data. However, quality measures can leak information about the confidential values, so that they too must be subject to disclosure protections. In this article, we discuss several approaches to releasing quality measures for verification servers when the public use data are generated via multiple imputation, also known as synthetic data. The methods can be modified for other stochastic perturbation methods.

Conclusion: What academia can contribute to refugee policy

2018 ◽  
Vol 56 (1) ◽  
pp. 146-151 ◽  
Author(s):  
Idean Salehyan
Keyword(s):  
Academic Research ◽  
Forced Migration ◽  
Humanitarian Assistance ◽  
Future Research ◽  
Security Risks ◽  
Individual Level ◽  
The Public ◽  
Level Data ◽  
Potential Risks

This conclusion to the special issue highlights the role of scholars in advancing the public discussion about forced migration. As countries around the world are adopting increasing restrictions on the entry of refugees, academic research can help to dispel some of the myths and apprehensions regarding the risks that forced migration entails. While refugees may be linked to conflict and violence in limited circumstances, the research generally demonstrates that robust international cooperation to manage refugee settlements, provide adequate humanitarian assistance, and integrate refugees into host communities, among other policies, can help to mitigate potential risks. Directions for future research and analysis are also discussed. Forced migration scholars should endeavor to collect more individual-level data; seek to understand factors that exacerbate or reduce security risks associated with cross-border militancy; conduct research on the long-term integration of refugees; and seek to understand the causes and consequences of resettlement and repatriation policies.

scholarly journals Holdout-Based Empirical Assessment of Mixed-Type Synthetic Data

2021 ◽  
Vol 4 ◽  
Author(s):  
Michael Platzer ◽  
Thomas Reutterer
Keyword(s):  
Mixed Type ◽  
Synthetic Data ◽  
Training Data ◽  
Privacy Risk ◽  
Individual Level ◽  
Empirical Assessment ◽  
Model Free ◽  
Private Data ◽  
Synthetic Datasets ◽  
The Individual

AI-based data synthesis has seen rapid progress over the last several years and is increasingly recognized for its promise to enable privacy-respecting high-fidelity data sharing. This is reflected by the growing availability of both commercial and open-sourced software solutions for synthesizing private data. However, despite these recent advances, adequately evaluating the quality of generated synthetic datasets is still an open challenge. We aim to close this gap and introduce a novel holdout-based empirical assessment framework for quantifying the fidelity as well as the privacy risk of synthetic data solutions for mixed-type tabular data. Measuring fidelity is based on statistical distances of lower-dimensional marginal distributions, which provide a model-free and easy-to-communicate empirical metric for the representativeness of a synthetic dataset. Privacy risk is assessed by calculating the individual-level distances to closest record with respect to the training data. By showing that the synthetic samples are just as close to the training as to the holdout data, we yield strong evidence that the synthesizer indeed learned to generalize patterns and is independent of individual training records. We empirically demonstrate the presented framework for seven distinct synthetic data solutions across four mixed-type datasets and compare these then to traditional data perturbation techniques. Both a Python-based implementation of the proposed metrics and the demonstration study setup is made available open-source. The results highlight the need to systematically assess the fidelity just as well as the privacy of these emerging class of synthetic data generators.

scholarly journals The closer to the Europe Union headquarters, the higher risk of COVID-19? Cautions regarding ecological studies of COVID-19

2020 ◽  
Author(s):  
Shuai Li ◽  
Xinyang Hua
Keyword(s):  
European Country ◽  
Ecological Study ◽  
Ecological Fallacy ◽  
Group Level ◽  
Ecological Studies ◽  
Public Concern ◽  
Individual Level ◽  
The Public ◽  
Country Level ◽  
Level Data

AbstractSeveral ecological studies of the coronavirus disease 2019 (COVID-19) have reported correlations between group-level aggregated exposures and COVID-19 outcomes. While some studies might be helpful in generating new hypotheses related to COVID-19, results of such type of studies should be interpreted with cautions. To illustrate how ecological studies and results could be biased, we conducted an ecological study of COVID-19 outcomes and the distance to Brussels using European country-level data. We found that, the distance was negatively correlated with COVID-19 outcomes; every 100 km away from Brussels was associated with approximately 6% to 17% reductions (all P<0.01) in COVID-19 cases and deaths in Europe. Without cautions, such results could be interpreted as the closer to the Europe Union headquarters, the higher risk of COVID-19 in Europe. However, these results are more likely to reflect the differences in the timing of and the responding to the outbreak, etc. between European countries, rather than the ‘effect’ of the distance to Brussels itself. Associations observed at the group level have limitations to reflect individual-level associations – the so-called ecological fallacy. Given the public concern over COVID-19, ecological studies should be conducted and interpreted with great cautions, in case the results would be mistakenly understood.

FAKTOR-FAKTOR YANG MEMPENGARUHI AUDIT DELAY PADA PERUSAHAAN MANUFAKTUR YANG GO PUBLIK DI BEI

2015 ◽  
Vol 11 (2) ◽  
pp. 117
Author(s):  
Astuti Yuli Setyani
Keyword(s):  
Stock Exchange ◽  
Secondary Data ◽  
Financial Statements ◽  
Test Results ◽  
Public Accounting ◽  
Variable Size ◽  
Accounting Firms ◽  
Accounting Firm ◽  
The Public

"> This study aims to examine empirically the effect of firm size, solvency, profitability, and thequality of public accounting firms (KAP) to the audit delay on manufacturing companieslisted in Indonesia Stock Exchange. This study focuses on companies listed on the IndonesiaStock Exchange. The data used are secondary data, the audited financial statements of 47companies listed in Indonesia Stock Exchange in 2009-2012. To test the hypothesis,performed multiple regression analysis that begins classic assumption test includingnormality, linearity, multicollinearity, heteroscedasticity and autocorrelation. The data usedhas met all the classical assumptions. Partial test results show that the variable size andvariable quality of the public accounting firm (KAP) that affect audit delay, while variablesolvency and profitability variable does not affect the audit delay.Keywords: audit delay, KAP, company’s size, profitability, solvency

scholarly journals INOVASI PELAYANAN PUBLIK DI BADAN PENANAMAN MODAL DAN PELAYANAN TERPADU (BPMPT) KABUPATEN KUBU RAYA (PUBLIC SERVICES INNOVATION IN REGIONAL BOARD OF INVESTMENT AND INTEGRATED SERVICES (BPMPT) AT KUBU RAYA REGENCY)

1969 ◽  
Vol 10 (2) ◽  
Author(s):  
Maria Agustini Permata Sari
Keyword(s):  
Business Process ◽  
Public Services ◽  
Secondary Data ◽  
Integrated Services ◽  
The Public ◽  
Increasing Trend ◽  
Descriptive Approach ◽  
Services Innovation ◽  
Regional Board

As a relatively new area, Kubu Raya district has managed to implement good public services especially in the field of licensing, this is evidenced by the numerous awards achieved and the increasing trend of the realization of a permit issued by the permitting Regional Board Of Investment And Integrated Services (BPMPT) as organizers each year. This study aims to determine what innovations have been carried out by BPMPT Kubu Raya and to identify what factors into supporting or occurrence of such innovations. This study used a qualitative method with a descriptive approach . Data were collected through interviews with the Head BPMPT and secondary data. The success of the public service is a direct and indirect impact of the innovation made by BPMPT. Innovation has been done by BPMPT Kubu Raya is simplifying the number of permits, licenses and restrictions touts business process simplification. Factors driving the birth of innovation undertaken by BPMPT Kubu Raya is the commitment and leadership of Regents BPMPT in improving the quality of licensing services, and human resources BPMT, who has high morale. While the issue is a barrier in the birth of innovation is movingstaff.Keywords: Innovation, Public ServicesSebagai daerah yang masih terhitung baru, Kabupaten Kubu Raya sudah berhasil melaksanakan pelayanan publik yang baik khususnya di bidang perijinan, hal ini dibuktikan antara lain dengan diraihnya berbagai penghargaan dan meningkatnya tren realisasi ijin yang diterbitkan oleh Badan Penanaman Modal dan Pelayanan Terpadu (BPMPT) setiap tahunnya. Studi ini bertujuan untuk mengetahui inovasi apa saja yang sudah dilakukan oleh BPMPT Kabupaten Kubu Raya serta untuk mengidentifikasi faktor apa saja yang menjadi pendorong maupun penghambat terjadinya inovasi tersebut. Studi ini menggunakan metode kualitatif dengan pendekatan deskriptif. Data dikumpulkan melalui wawancara dengan Kepala BPMPT serta data sekunder. Hasil studi ini menyimpulkan bahwa inovasi yang sudah dilakukan oleh BPMPT Kubu Raya adalah penyederhanaan jumlah ijin, pembatasan calo perijinan dan penyederhanaan business process. Faktor pendorong lahirnya inovasi yang dilakukan oleh BPMPT Kubu Raya adalah komitmen Bupati dan pimpinan BPMPT dalam memperbaiki kualitas pelayanan perijinan, serta sumber daya manusia BPMT yang memiliki semangat kerja tinggi. Sedangkan masalah yang menjadi faktor penghambat lahirnya inovasi adalah mutasipegawai.Kata Kunci: Inovasi, Pelayanan Publik

scholarly journals Kualitas Pelayanan Pemasangan Listrik Prabayar Pada PT. PLN (Persero) Area Pelayanan Banyumanik Semarang

2019 ◽  
Vol 3 (2) ◽  
pp. 227-232
Author(s):  
Dini Setyorini
Keyword(s):  
Quality Of Service ◽  
Service Quality ◽  
Public Service ◽  
Direct Evidence ◽  
Secondary Data ◽  
Service Area ◽  
Quality Service ◽  
The Public ◽  
Score Interpretation

Abstract – It cannot be denied that at present the public service is a concern of the public. Ordinary public service come from agencies that serve the community for the needs of every community. This study aims to determine quality of service for prepaid electricity installation at PT. PLN (Persero) Banyumanik Semarang service area. Analysis of the data used is a score interpretation (IS) obtained from respondents. Respondents numbered 80 people using purposive sampling. While to complete this research, the author also uses secondary data obtained from various existing sources. Based on the results of the research conducted it can be concluded that the dimensions that show service quality include tangibles ( direct evidence), reliability, responsiveness, assurance and emphaty show a strong interpretation where customers feel satisfied with the quality service of PT. PLN (Persero) Banyumanik Semarang service area.Key words : quality, service, satisfaction

scholarly journals Drivers of Customer Centricity: Role of Environmental-level, Organization-level and Department-level Variables

2017 ◽  
Vol 20 (2) ◽  
pp. 1-10
Author(s):  
Goran Vlašić ◽  
Emanuel Tutek
Keyword(s):  
Marketing Capabilities ◽  
Individual Level ◽  
Organization Level ◽  
Level Data ◽  
The Right ◽  
High Level ◽  
Customer Centricity ◽  
Environmental Level

Abstract Customer centricity is gaining importance as companies are gaining access to increasing amount and quality of individual-level data on identifiable customers. However, efforts to enhance customer centricity often face challenges as they imply organization-wide effort. This paper explores the role of environment-level factors, organization-level factors (in terms of structure, influence and culture) and department-level factors (in terms of integration, power and capabilities) in driving customer centricity of a firm. Results indicate that, while within-category competition stimulates customer centricity, the cross-category competitive intensity limits it. Moreover, marketing competences exhibit highly significant impact which even diminishes the role of inter-departmental integration. Lastly, results show that firms with high level of marketing capabilities and the right culture (in terms of tolerance for failure and availability of slack resources) are likely to exhibit higher levels of customer centricity.

PENGARUH JUMLAH DANA PIHAK KETIGA (DPK) NON PERFOMING FINANCING (NPF) DAN SERTIFIKAT BANK INDONESIA SYARI’AH (SBIS) TERHADAP PENYALURAN PEMBIAYAAN PERBANKAN SYARI’AH DI INDONESIA

2019 ◽  
Vol 2 (2) ◽  
pp. 1-21
Author(s):  
Arif Rijal Anshori
Keyword(s):  
Statistical Tests ◽  
Secondary Data ◽  
Third Party ◽  
Islamic Banking ◽  
Islamic Banks ◽  
The Public ◽  
Normality Test ◽  
Source Data ◽  
Scientific Truth

Banking is a very important part in the economy, one of them as intermediary institutions whose duty to collect funds from the public and then channel them back in the form of financing.This study aims to determine the effect Number of DPK, NPF and SBIS partially to finance portfolio of Islamic banking in Indonesia, and to determine the effect Number of DPK, NPF and SBIS simultaneously to the finance portfolio of Islamic banking in Indonesia.This study proceed from the assumption that (1) the size distribution of the funds offered by Islamic banks is very influenced by the size DPK means that the higher the number of third-party funds collected, the higher also finance portfolio, (2) the higher non-performing financing the worse the quality of banking assets, (3) the higher the bonus level set SBIS Indonesian bank will lower the financing undertaken by the banking Shari'ah. But based on data from Islamic banking statistics from the years 2008-2014 there is a gap between theory and facts on the ground. These assumptions are tested empirically so that the truth can be scientifically recognized. When there is a justification or rejection of these assumptions, then this is a scientific truth that can be considered Islamic banking in Indonesia.Quantitative research methods in this study using research formats explanation, source data used in this research is secondary data, then the type of data used in this research is quantitative data time series, the quarterly data of financing, deposits, NPF and SBIS Islamic banking in Indonesia from 2008 to 2014. Data were then processed by means of statistical analysis using Eviews 7, which comprises the classical assumption of them: normality test, heteroscedasticity, multicollinearity test, autocorrelation test. statistical tests include: regression, t test, F test and R2.The conclusion that can be drawn from this study that partially, DPK variable is positive and significant effect on the financing, NPF variable is negative but not significant effect on the financing, while SBIS is negative and significant effect on the financing. Then simultaneously the number of DPK, NPF and SBIS significant effect on the distribution of funding. Those variables could explain freely by 99.45% and the remaining 0.55% can be explained by other variables not examined.

scholarly journals Drug Innovations and Welfare Measures Computed from Market Demand: The Case of Anti-Cholesterol Drugs

2012 ◽  
Vol 4 (3) ◽  
pp. 167-189 ◽  
Author(s):  
Abe Dunn
Keyword(s):  
Price Index ◽  
Market Demand ◽  
Individual Level ◽  
Drug Products ◽  
New Product Introductions ◽  
Level Data ◽  
Substantial Investment ◽  
Constant Quality ◽  
Price Measurement

The pharmaceutical industry is characterized as having substantial investment in R&D and a large number of new product introductions, which poses special problems for price measurement caused by the quality of drug products changing over time. This paper applies recent demand estimation techniques to individual-level data to construct a constant-quality price index for anti-cholesterol drugs. Although the average price for anti-cholesterol drugs does not change over the sample period, I find that the constant-quality price index drops by 27 percent, a pace more in line with our expectations in such a dynamic segment of the industry. (JEL C43, L11, L65, O31)

scholarly journals Explaining the Varieties of Volunteering in Europe: A Capability Approach

2021 ◽  
Author(s):  
Bernard Enjolras
Keyword(s):  
Capability Approach ◽  
Ad Hoc ◽  
Theoretical Explanation ◽  
Data Sets ◽  
Individual Level ◽  
Oxford University ◽  
Level Data ◽  
The Individual ◽  
Structural Indicators

AbstractVolunteer rates vary greatly across Europe despite the voluntary sector’s common history and tradition. This contribution advances a theoretical explanation for the variation in volunteering across Europe—the capability approach—and tests this approach by adopting a two-step strategy for modeling contextual effects. This approach, referring to the concept of capability introduced by Sen (Choice, welfare and measurement, Oxford University Press, 1980/1982), is based on the claim that the demand and supply sides of the voluntary sector can be expected to vary according to collective and individual capabilities to engage in volunteering. To empirically test the approach, the study relied on two data sources—the 2015 European Union (EU) Survey on Income and Living Conditions (EU-SILC), including an ad hoc module on volunteering at the individual level, and the Quality of Government Institute and PEW Research Center macro-level data sets—to operationalize economic, human, political, social, and religious contextual factors and assess their effects on individuals’ capability to volunteer. The results support the capability hypothesis at both levels. At the individual level, indicators of human, economic, and social resources have a positive effect on the likelihood of volunteering. At the contextual level, macro-structural indicators of economic, political, social, and religious contexts affect individuals’ ability to transform resources into functioning—that is, volunteering.

Sign in / Sign up

Export Citation Format

Share Document