Search

Multimode data collection has emerged as a common approach for conducting household surveys in the United States. A number of different data collection schemes have been investigated, with an emphasis on collecting as many respondents by the Web prior to going to paper data collection to reduce costs. Despite this, little research has been conducted on the approaches to weighting data from multimode surveys. The typical approach assumes that all respondents should be treated the same regardless of mode even though it is well known that the response patterns by mode vary substantially. We examine an adaptive mode adjustment to address these differences and propose an imbalance measure to help determine the adjustment factor using ideas from responsive design. We then compare the effects of the alternative weighting method in two recent sequential mixed-mode surveys and show it appears to reduce bias while only slightly increasing variances of the estimates. [ABSTRACT FROM AUTHOR]

We discuss a model for long memory and persistence in time series that amounts to harmonically weighting short memory processes, ∑jxt−j/(j+1). A non‐standard rate of convergence is required to establish a Gaussian functional central limit theorem. Theoretically, the harmonically weighted (HW) process displays less persistence and weaker memory than the classical competitor, fractional integration (FI) of order d. Still, we establish that a test rejects the null hypothesis of d = 0 if the process is HW. Similarly, a bias approximation shows that estimators of d will fail to distinguish between HW and FI given realistic sample sizes. The difficulties to disentangle HW and FI are illustrated experimentally and with USA inflation data. [ABSTRACT FROM AUTHOR]

Dual-frame telephone surveys that sample from both landline and cell-phone frames have become common because the US population is increasingly abandoning landline phones. Designing a dual-frame telephone survey requires a decision on the sample allocation, and ultimately the allocation of respondents, from each of the two frames. The allocation of the sample to the two frames influences the unequal weighting effect (UWE), and consequently, the precision of estimates calculated from the survey data. The sample allocation also influences cost, since obtaining cell-phone respondents is often more expensive than obtaining landline respondents. In this paper, we present results that designers of dual-frame studies can use to determine an allocation of responders that optimizes the precision of the survey estimates for a given cost. [ABSTRACT FROM AUTHOR]

Given the theoretical promise of these auxiliary data for overcoming the challenge of nonresponse, survey researchers have shown an increased interest in collecting paradata, data from screening interviews, and other contextual information. However, very few studies have systematically assessed the use of these data for post-survey nonresponse adjustments. Those studies that do exist generally do not identify auxiliary variables that correlate with response propensity and key survey variables, a necessary condition for auxiliary data to be effective tools for reducing nonresponse bias. Using the National Survey of Family Growth (NSFG), this paper leverages a large set of auxiliary variables available for the full NSFG sample to assess their potential as independent tools for post-survey nonresponse adjustments. We begin by using this auxiliary information to predict response propensity (RP) for each person in the full sample. We then display descriptive estimates for a variety of attitudes and behaviors measured in the NSFG, using post-stratification weighting adjustments as well as RP adjustments followed by post-stratification. The results show that accounting for RP in the weighting adjustment often produces noteworthy differences in the estimates, thus supporting the collection of these types of auxiliary variables in practice. These results also suggest that standard post-stratification adjustments may not be entirely effective at removing nonresponse bias from all survey estimates, and that some subgroup analyses may be especially subject to bias when adjusting survey estimates using post-stratification alone. [ABSTRACT FROM AUTHOR]