1,720,987 research outputs found
Determination of the threshold in cutoff sampling using response burden with an application to Intrastat
No full textStatistical offices frequently use cutoff sampling to determine which businesses in a population should be surveyed. Examples include business surveys about international trade, production, innovation, ICT usage and so on. Cutoff thresholds are typically set in terms of key variables of interest and aim to satisfy a minimum coverage ratio-the share of aggregate values of reporting units. In this article we propose a simple cost-benefit approach to determination of the sampling cutoff by taking into account the response burden. In line with existing practice, we use the coverage ratio as our measure of accuracy and provide either analytical or numerical solutions to cutoff determination. Using a business survey on response burden of reporting trade flows within the EU (Intrastat), we present an application that illustrates our approach to cutoff determination. An important practical implication is the possibility to set industry-contingent cutoffs.</p
Development and testing of business survey questionnaires: use of qualitative methods in national statistical institutes
No full textQualitative research methods are regarded as an important tool to develop and test survey questionnaires, as they provide useful information for identifying and understanding errors in the response process. However, little is known about how these methods are implemented in practice, especially in the context of establishment surveys. This paper aims to give more insight into whether and how statistical agencies use qualitative methods for the development of establishment survey questionnaires. The paper presents the results of an international survey of national statistical institutes. The survey addressed several aspects of the use of qualitative methods for developing establishment survey questionnaires, including sampling and recruitment procedures, methods for the collection and analysis of the data, and documentation of the results
Qualitative testing for official establishment survey questionnaires
Get PDFBest practice research for testing establishment (businesses and other organisations) survey questionnaires is largely the province of official statistics and has developed more slowly than the corresponding research in household surveys. With a focus on the development and testing of establishment survey question(naire)s, this paper: reviews what we know; makes recommendations;reports survey results on the practical application in National Statistical Institutes; and assesses the levels of maturity in the application of approaches
Data visualisation: the case of Chamber of Commerce of Slovenia
No full textPrikazovanje podatkov je uporaba grafičnih predstavitev kot načina podajanja oz. predajanja informacij in podatkov. Obstaja nekaj nasprotujočih si mnenj in praks na področju prikazovanja podatkov. Nekateri strokovnjaki in raziskovalci zagovarjajo minimalističen ter enostaven pristop prikazovanja, drugi trdijo, da bralci preferirajo prikaze z več komponentami in okraski oziroma obogatitvami. Standardni pristopi preučevanih komponent so generični naslovi, prikazovanje celotne navpične osi, ki se začne z nič, uporaba standardnih barv brez posebnega pomena in prikazovanje podatkov brez prikazovanja negotovosti. Uporabljeni alternativni sodobni pristopi so bili informativni naslovi, odrezana navpična os, drugačne barvne sheme in prikazovanje podatkov z intervali zaupanja.
Namen magistrskega dela je izboljšati grafične prikaze TZS z uporabo sodobnih pristopov prikazovanja podatkov. V prvi raziskavi sem na vzorcu članov TZS preveril razumevanje grafičnih prikazov in preference glede rabe komponent. Primerjavo sem izvedel z dvema anketnima vprašalnikoma, v katerih so vsi sodelujoči odgovarjali na vprašanja o razumevanju prikazov ter o preglednosti, privlačnosti in enostavnosti prikazov. Vprašalnika sta se med seboj razlikovala v načinu uporabe komponent. Odgovore v obeh vprašalnikih sem primerjal med seboj. Na podlagi pregleda teorije in obeh raziskav sem podal priporočila za prikazovanje podatkov TZS. Priporočam prilagajanje prikazov bralcem: če so ti bolj strokovni, kot na primeru TZS, so primernejši enostavni prikazi brez okraskov. Intervale zaupanja so sodelujoči sicer razumeli, a so za odgovarjanje na vprašanja o njih potrebovali več časa in jih tudi ocenili kot manj jasne in zahtevnejše za razumevanje, zato je pri njihovi zasnovi potrebna previdnost. Odrezana os je sicer nekoliko izboljšala natačnost ocene, a so bile pogostejše tudi velike napake ocene, zato njene uporabe ne priporočam. Pri različni uporabi naslovov in barv ni bilo statistično značilnih razlik. V drugi raziskavi pa sem naredil pregled sodobnega prikazovanja podatkov Sursa, Eurostata in TZS v praksi. Ugotovil, da je uradna statistika do alternativnih načinov rabe komponent v splošnem zadržana, se pa njeni prikazi precej razlikujejo med različnimi mediji komuniciranja.Data visualisation is the use of graphical representations to convey information and data. There are some conflicting opinions and practices in the field of data visualization. Some experts and researchers advocate for a minimalist and simple approach to visualization, while others argue that readers prefer visual displays with more components and embellishments. The standard approaches for the examined components are generic titles, displaying the entire vertical axis starting from zero, using standard nonmeaningful colours, and presenting data without displaying uncertainty. The alternative modern approaches used in the study were informative titles, truncated vertical axes, alternative colour schemes, and displaying data with confidence intervals.
The purpose of this master’s thesis was to improve the displays of the Chamber of Commerce of Slovenia (TZS) using modern data visualization approaches. In the first study, I examined the understanding of charts and preferences regarding component usage among members of the TZS. I created two similar survey questionnaires, in which all participants answered questions about their understanding of charts, as well as the clarity, attractiveness, and simplicity of charts. The questionnaires differed in how they utilized components. I compared the responses in both questionnaires. Based on the theory review and both studies, I formulated recommendations for data visualization at TZS. I recommend adapting diagrams to the audience: if they are more specialized, as in the case of TZS, simple charts without embellishments are more suitable. While participants understood confidence intervals, they needed more time to answer the questions about them and found them somewhat more complicated and less clear, which calls for caution when designing such charts. Truncating the axis slightly improved accuracy but also resulted in more frequent large errors in estimation, so I do not recommend its use. Regarding the use of titles and colours, there were no statistically significant differences. In the second study, I conducted a review of modern data visualization practices used by the Statistical Office of the Republic of Slovenia (Surs), Eurostat, and the TZS. I found that official statistics are generally reserved towards alternative component usage, but their charts differ among different communication media
Primerjava popisa prebivalstva in centralnega registra prebivalstva z empirično analizo na ravni občin
No full text
- …
