Leveraging Auxiliary Information on Marginal Distributions in Nonignorable Models for Item and Unit Nonresponse

Akande, Olanrewaju; Madson, Gabriel; Hillygus, D. Sunshine; Reiter, Jerome P.

doi:10.1111/rssa.12635

Cited by 4 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unit non-response or panel attrition (i.e., principals that participated in wave one but not wave two of our study) between waves in our data was 46.2%; item non-response for our measures during wave one was 0.70% and 3.60% during wave two. To handle unit non-response and cross-sectional missing data (item non-response), we followed Akande et al ( 2021 ), Deng et al ( 2013 ), and Hirano et al ( 2001 ) and thus combined refreshment with a multiple imputation approach (i.e., P+R approach, see Deng et al, 2013 ). Consequently, at each stage of analysis we generated a completed data set that included all N = 493 cases from the panel and refreshment sample, imputed the data 100 times, and used these data for estimating our CLPM and all other reported coefficients and statistics (see ‘ Appendix 3 ’ for an exemplary Mplus input).…”

Section: The Present Studymentioning

confidence: 99%

Innovating teaching and instruction in turbulent times: The dynamics of principals’ exploration and exploitation activities

2022

View full text Add to dashboard Cite

In turbulent environments, schools have to adapt to constantly changing conditions. According to ambidexterity theory, whether they are successful in this primarily depends on their leaders and how they manage the tension between the use of current knowledge (exploitation) and the search for new knowledge (exploration). Through unique top-down and bottom-up pathways, they thus influence the innovation outcome of a school. However, it is so far unclear whether these assumptions are correct. Using data from a panel of principals who are representative of Germany and were surveyed before and during the COVID-19 pandemic, we therefore investigate if and how school leaders adapted to the turbulent environment caused by the pandemic and evaluate the extent to which this had an impact on their schools’ innovations in teaching and instruction. The results demonstrate that principals’ exploration activities increased markedly during the pandemic, while their exploitation activities decreased noticeably. Further, a focus on the use and refinement of existing knowledge in comparatively predictable (pre-COVID-19) environments harmed principals’ readiness to explore new knowledge in increasingly uncertain environments. Nevertheless, exploitation had positive consequences for the innovativeness of schools, and exploration goes along with more radical innovations in teaching and instruction. Our research suggests that schools that innovatively addressed the COVID-19 pandemic had school leaders who were able to quickly shift between the two modes of exploitation and exploration. A capacity to transition seamlessly between these modes of thinking and working thus appears to be vital for the longevity of schools.

show abstract

Section: The Present Studymentioning

confidence: 99%

Innovating teaching and instruction in turbulent times: The dynamics of principals’ exploration and exploitation activities

2022

View full text Add to dashboard Cite

show abstract

A multiple imputation method using population information

Fushiki

2024

Communications in Statistics - Theory and Methods

View full text Add to dashboard Cite

Using Auxiliary Marginal Distributions in Imputations for Nonresponse while Accounting for Survey Weights, with Application to Estimating Voter Turnout

Tang,

Hillygus,

Reiter

2023

Journal of Survey Statistics and Methodology

View full text Add to dashboard Cite

In many survey settings, population counts or percentages are available for some of the variables in the survey, for example, from censuses, administrative databases, or other high-quality surveys. We present a model-based approach to utilize such auxiliary marginal distributions in multiple imputation for unit and item nonresponse in complex surveys. In doing so, we ensure that the imputations produce design-based estimates that are plausible given the known margins. We introduce and utilize a hybrid missingness model comprising a pattern mixture model for unit nonresponse and selection models for item nonresponse. We also develop a computational strategy for estimating the parameters of and generating imputations with hybrid missingness models. We apply a hybrid missingness model to examine voter turnout by subgroups using the 2018 Current Population Survey for North Carolina. The hybrid missingness model also facilitates modeling measurement errors simultaneously with handling missing values. We illustrate this feature with the voter turnout application by examining how results change when we allow for overreporting, that is, individuals self-reporting that they voted when in fact they did not.

show abstract

Leveraging Auxiliary Information on Marginal Distributions in Nonignorable Models for Item and Unit Nonresponse

Cited by 4 publications

References 46 publications

Innovating teaching and instruction in turbulent times: The dynamics of principals’ exploration and exploitation activities

Innovating teaching and instruction in turbulent times: The dynamics of principals’ exploration and exploitation activities

A multiple imputation method using population information

Using Auxiliary Marginal Distributions in Imputations for Nonresponse while Accounting for Survey Weights, with Application to Estimating Voter Turnout

Contact Info

Product

Resources

About