Special issue: ‘Weighting: Practical Issues and ‘How to’ Approach

Editors: Jean Dumais, Lars Kaczmirek, Stephanie Steinmetz, Caroline Vandenplas


Weights, what should we do with it? Although all survey samplers will agree that the inclusion of weights in any statistical analyses is necessary to avoid biased estimates, the ‘how’ and ‘why’ are less obvious for data users. In many aspects, weights are just a bit of a mystery. With this collection of articles, ‘Survey Methods: Insights from the Field’ hopes to help its reader to gain a better understanding of weights, both on what they are and on the reasons why they should be included in analyses.

The editors warmly thank all the authors who contributed to the thematic collection of article, especially Pierre Lavallée and Jean-François Beaumont who kindly accepted to write an introductory article. We also would like to thank our invited editors Jean Dumais and Stephanie Steinmetz for their enthusiastic involvement in ‘Weighting: Practical issues and ‘How to’ Approach’.

Lars Kaczmirek & Caroline Vandenplas

Simultaneous Raking of Survey Weights at Multiple Levels Special issue

Stanislav Kolenikov, Ph.D., Abt SRBI
Heather Hammer, Ph.D., Abt SRBI


This paper discusses the problem of creating general purpose calibrated survey weights when the control totals data exist at different levels of aggregation, such as households and individuals. We present and compare three different methods. The first does the weighting in two stages, using only the household data, and then only the individual data. The second redefines targets at the individual level, if possible, and uses these targets to calibrate only the individual level weights. The third uses multipliers of household size to produce household level weights that simultaneously calibrate to the individual level totals. We discuss the advantages and …


, , ,

No Comments

How to weight survey data with a dyadic multi-actor design? Special issue

Inge Pasteels, University of Antwerp


This paper deals with adjustment for nonresponse in dyadic multi-actor survey designs. It presents a multi-dimensional approach to weighting that addresses the various analytical units represented in such data, so that sampling design weights are correctly accounted for and so that consistency between weights is achieved. This approach is demonstrated by using the primary respondents in the Divorce in Flanders study, which is a typical example of a dyadic multi-actor design. Five sets of weighting coefficients are made available whereby different subsets of data, according to different analytical units, are selected: the subset of the dyads, the subset of men …


, , , ,

No Comments

The Impact of Typical Survey Weighting Adjustments on the Design Effect: A Case Study Special issue

Golshid Chatrchi, Marie-Claude Duval, François Brisebois, Steven Thomas
Household Survey Methods Division, Statistics Canada


In survey sampling, the final sample weight assigned to each sampled unit reflects different steps of weighting adjustments such as frame integration, nonresponse and calibration. The analysis of the design effects for each of these adjustments casts light on their effects on the precision of survey estimates. In this paper, we limit our scope to the Canadian Community Health Survey (CCHS), briefly describe the weighting process of this survey and examine design effects at different steps of the weighting process to quantify how the overall variability in estimates can be attributed to the complex survey design and to each of …


, , , ,

No Comments

Weighting Procedures for Dual Frame Telephone Surveys: A Case Study in Egypt Special issue

Mahmoud A. Elkasabi, Ph.D., ICF International.


Although it is a quick and non-expensive tool used to collect survey data in Egypt, the landline telephone surveys cannot reach the non-landline households, which makes up 73.4 percent of the households in Egypt according to the 2012/2013 Egypt – Household Income, Expenditure, and Consumption Survey (HIECS). Therefore, among other centers, the Public Opinion Poll Center (POPC) adopted the dual frame telephone surveys as an alternative to the landline telephone surveys, in which the landline sample is supplemented by a Pseudo-Random-Digit-Dial (Pseudo-RDD) sample of cell phones. The cell phone sample can reach the cell-only households (households with no landline but …


, , ,

No Comments

Computing Sampling Weights in Large-Scale Assessments in Education Special issue

Sabine Meinck, IEA Data Processing and Research Center, Hamburg, Germany


Sampling weights are a reflection of sampling design; they allow us to draw valid conclusions about population features from sample data. This paper explains the fundamentals of computing sampling weights for large-scale assessments in educational research. The relationship between the nature of complex samples and best practices in developing a set of weights to enable computation of unbiased population estimates is described. Effects of sampling weights on estimates are shown, as well as potential consequences of not using weights when analysing data from complex samples. Illustrative examples are provided in order to make it easy to understand the rationale behind …


, , ,

No Comments

Finding Respondents in the Forest: A Comparison of Logistic Regression and Random Forest Models for Response Propensity Weighting and Stratification Special issue

Trent D. Buskirk, Ph.D. Marketing Systems Group
Stanislav Kolenikov, Ph.D. Abt SRBI


Survey response rates for modern surveys using many different modes are trending downward leaving the potential for nonresponse biases in estimates derived from using only the respondents. The reasons for nonresponse may be complex functions of known auxiliary variables or unknown latent variables not measured by practitioners. The degree to which the propensity to respond is associated with survey outcomes casts light on the overall potential for nonresponse biases for estimates of means and totals. The most common method for nonresponse adjustments to compensate for the potential bias in estimates has been logistic and probit regression models. However, for more …


, , , , ,

No Comments

Should Recall of Previous Votes Be Used to Adjust Estimates of Voting Intention? Special issue

Claire Durand, Mélanie Deslauriers, Isabelle Valois, Department of sociology, Université de Montréal


Correction of estimates of voting intention using voter recall of previous votes is frequent in electoral polls, particularly in Europe. However, research on the impact of its use is scarce. The results presented in this paper confirm that voting is not a salient, memorable behaviour for all voters. People who always vote the same way and identify with a political party are likely to accurately remember their vote, but in most developed countries, change of allegiance is now common. A substantial portion of the electorate changes its mind between or during campaigns, and switchers seem to have more difficulty remembering …


, , , ,

No Comments

Except where otherwise noted, content on this site is licensed under a Creative Commons Attribution 4.0 International License. Creative Commons License