Table 1 - uploaded by Carsten Schwemmer
Content may be subject to copyright.
Context in source publication
Context 1
... all of these samples, fabricated interviews have been detected and archived. The analysis in this work are restricted to the first waves of sample A/B and F and the first and second wave of sample E. Table 1 shows all fabrications, the interviewer id's of cheating interviewers as well as the number of fabricated interviews for each interviewer. Due to undertaken quality checks of the SOEP mentioned in section 2, only one interviewer with id 249289 was able to fabricate interviews in two subsequent waves. ...
Similar publications
Two-dimensional shape-morphing networks are common in biological systems and have garnered attention due to their nontrivial physical properties that emanate from their cellular nature. Here, we present the fabrication and...
![Fig. 2: Hyperledger Fabric transaction processing protocol [4].](profile/Alysson-Bessani/publication/326567051/figure/fig1/AS:685619709743104@1540475885197/Hyperledger-Fabric-transaction-processing-protocol-4_Q320.jpg)
D-shape Si3N4 waveguides are fabricated by dielectric lift-off process. We measure ultra-low loss for a 90nm-thick core of 2.42 dB/m at 1550 nm and a loaded Q-factor of 1.12×10 6 for a 0.8 mm radius resonator.
Citations
... Given the importance of good data, effective methods are needed to sanitize survey data before conducting any meaningful empirical research or making decisions. Several methods have been proposed to detect bad answers in surveys, which involve re-interviewing respondents, recording and analyzing interviews with respondents, or analyzing statistical features of the responses [7]. However, the application of such verification checks incurs high costs. ...
Surveys are one of the most common ways of collecting data on individuals. Such data are of great value for economic and social research. However, the quality of the decisions and research results based on survey data depends on the ability to detect and filter out bad answers. The most common source of bad data are the respondents, who might provide imprecise or fabricated answers due to several reasons. In this paper we present a method to sanitize survey data that relies on combining the classification outcomes of three unsupervised machine learning algorithms (DBSCAN, PCA and IForest) aimed at detecting bad answers. Empirical results on real data show that our approach is able to improve the detection of both completely and partially bad answers with respect to the results provided by each algorithm independently.
