Search results
Page 1 of 4
Piet Daas endowed professor of Big Data at TU/e
Creating big data statistics is very different from creating statistics based on surveys
The use of within-subject experiments for estimating measurement effects in mixed-mode surveys
The estimation of measurement effects (MEs) of survey modes in the presence of selection bias poses a great problem to methodologists. We present a new method to estimate MEs by means of...
Is undesirable answer behaviour consistent?
This paper investigates whether answer behavior that points at increased risk of measurement error is consistent across surveys, i.e. whether it is a trait of respondents.
CBS and VU Amsterdam: progress through cooperation
techniques such as ‘distributed analytics’ for collective analysis of multiple data sources
Removing the Gap between Annual and Sub-Annual Statistics
Statistical methods for reconciling data that are published at different frequencies (e.g. monthly and quarterly).
Divide-and-Conquer solutions for estimating large consistent table sets
Consistent estimation of a set coherent frequency tables
Analysing response differences in VAT
Analysing response differences between sample survey and VAT turnover
Correcting for linkage errors in the multiple capture
Correcting for linkage errors in the multiple - recapture method for population size estimation.
Bootstrapping structural time series models
A resample method to compute standard errors of estimates based on a structural time series model.
Impact of linkage errors and erroneous captures
Capture-recapture methods and violation of the assumptions of perfect linkage and no erroneous captures
Measuring discontinuities due to survey process redesigns
This paper presents statistical methods to measure the impact due to a survey process redesign to avoid interruption of time series.
Filtering in the Fourier domain
Filtering in the Fourier domain: a new set of filters for seasonal adjustment of time series and its evaluation
Complexity and simplification of networks
Quantification of the complexity of networks and methods to simplify networks by focusing on their essence.
New methods and sources for Big Data research
The objective of the seminar was to bring together researchers from statistical offices and academic scientists in order to exchange knowledge and present the latest methods and techniques in the...
Geographic location estimation of mobile devices
A working paper in which a modular Bayesian framework is proposed to estimate the geographic location of mobile devices from mobile phone network data.
New data sources and inference methods for statistics
Methodological issues with non-probability data for official statistics.
Fair algorithms in context
Decisions in our society are increasingly supported by Artificial Intelligence (AI). In this work we refer to AI as computers doing ‘intelligent’ tasks. This can for example be determining good moves...
CBS, The Hague University of Applied Sciences work on big data
In September 2016, Statistics Netherlands (CBS) established the Center for Big Data Statistics (CBDS).
Use sensors to improve Dutch people’s health
How can we make smarter use of technology in Dutch health research.
Development of a survival model for unexpectedly long hospital stays
Survival model for the indicator for unexpectedly long hospital stays.
How data determine who are the people of Europe
How data determine who are the people of Europe
The accuracy of growth rates with classification errors
Evaluating the accuracy of growth rates in the presence of classification errors.
Bootstrapping the SPAR index
This paper discusses a bootstrap method to estimate the variance of price indices of houses.
Big data and methodological challenges
Big data and methodological challenges