Statistical Matching

D’Orazio, Marcello; Zio, Marco Di; Scanu, Mauro

doi:10.1002/0470023554

Cited by 209 publications

(107 citation statements)

References 0 publications

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…Two main approaches can be delineated in terms of statistical matching goals (D'Orazio, Di Zio & Scanu, 2006). In the macro approach the source files are used in order to have a direct estimation of certain characteristics of the specific variables, such as joint distributions, marginal distributions or correlation matrices.…”

Section: Observationsmentioning

confidence: 99%

Statistical matching in practice – An application to the evaluation of the education system from PISA and TALIS

Iztueta¹,

Navarro²,

Murgiondo

2017

rie

View full text Add to dashboard Cite

show abstract

Section: Observationsmentioning

confidence: 99%

Statistical matching in practice – An application to the evaluation of the education system from PISA and TALIS

Iztueta¹,

Navarro²,

Murgiondo

2017

rie

View full text Add to dashboard Cite

show abstract

“…These procedures and tools can be seen as extensions of the hot deck approach. See D'Orazio et al for a detailed treatment of the subject (19).…”

Section: Statistical Matchingmentioning

confidence: 99%

“…(The effect of ignoring this is analyzed in the subsection on population mismatch of the section on stochastic results.) D'Orazio et al recommend using the larger data set as donor and the smaller data set as recipient (19). Violating this recommendation obviously leads to donor records used more than once and, therefore, to a modification of the variability of the imputed variables (in this case, extended sociodemographics and activity schedules).…”

Section: Statistical Matchingmentioning

confidence: 99%

Using Survey Calibration and Statistical Matching to Reweight and Distribute Activity Schedules

Müller

Axhausen

2014

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

The processes used to generate a 106-member agent population for a longrange study of 2030 travel in Switzerland are presented in this paper. This study was part of an effort to assess the effects of electric vehicles on the energy production and stability of the electric supply network. The process used well-established statistical methods—survey calibration and statistical matching. Both methods are described, and consistency with known approaches in transportation planning is shown. The paper introduces a new approach that allows exogenous specification of shares of activity types while maintaining the representativeness of the population: survey calibration is applied to satisfy these constraints, and statistical matching allows the joining of data sets with common variables. The discussion of the results for Switzerland focuses on the quality metrics available and highlights the links between the activity schedules and total shares of the activity types. Furthermore, the error introduced by the calibration and matching stages was analyzed and quantified, with special emphasis placed on uncontrolled sociodemographic and travel variables. The specified activity shares could be replicated almost perfectly; the resultant mean error in the uncontrolled variables was within the range of a few percentage points. Therefore, this approach is a viable alternative to a complicated estimation of an activity schedule model that would be necessary otherwise. Finally, two practical issues—data sets describing different populations and biased surveys—and their effect on the outcome were tested by suitably adjusting the input data.

show abstract

“…This is typically done to avoid predicting something nonsensical like percentage of pregnant males. Overviews of the data fusion literature have been provided, among others, by Radner et al , 6 van Pelt, 9 Raessler 10 and D ' Orazio et al 11 This allows inference of most likely market research segments or lifestyle clusters. Now you can infer ' soft characteristics ' with some statistical likelihood, even though these customers have not been involved in the market research.…”

Section: Fusing Market Research With Proprietary Databasesmentioning

confidence: 99%

Data analysis across various media: Data fusion, direct marketing, clickstream data and social media

Breur¹

2011

J Direct Data Digit Mark Pract

View full text Add to dashboard Cite

As the volume and diversity of digitally stored data keeps growing, the importance for the business to create a holisti c picture of the customer conti nues to grow. In this paper, we discuss the possibiliti es available to researchers with four diff erent streams of data. First, we discuss data fusion, merging of proprietary databases with market research data, which enables appending atti tudinal data to customer behaviour. Secondly, best practi ces in direct marketi ng leverage analysis of customer response patt erns to provide the right off er to the right customer at the right moment. Thirdly, analysing internet usage data allows many opportuniti es for small-scale, agile marketi ng pilots. And fi nally, social media are discussed, one of the newer opportuniti es to collect data about customer senti ments that relies heavily on text mining analyti cs.

show abstract

Statistical Matching

Cited by 209 publications

References 0 publications

Statistical matching in practice – An application to the evaluation of the education system from PISA and TALIS

Statistical matching in practice – An application to the evaluation of the education system from PISA and TALIS

Using Survey Calibration and Statistical Matching to Reweight and Distribute Activity Schedules

Data analysis across various media: Data fusion, direct marketing, clickstream data and social media

Contact Info

Product

Resources

About