Search Results

You are looking at 11 - 20 of 90 items for :

  • "imputation" x
Clear All
Restricted access

Frank E. DiLiberto, Deborah A. Nawoczenski and Jeff Houck

maintain the statistical power and a sample size of 12 participants, missing data for the 2 cases pertaining to the high-step activity were addressed via a mean imputation method with random variability that was based on the present distribution. 31 , 32 Mean imputation with random variability reduces

Restricted access

Kent A. Lorenz, Hans van der Mars, Pamela Hodges Kulinna, Barbara E. Ainsworth and Melbourne F. Hovell

imputation procedure in SAS 9.3, with 20 imputation cycles performed for each area. The imputed estimates were averaged to produce plausible replacement values that were merged with the observed data. This allowed us to analyze a complete dataset with a combination of observed data and plausible imputation

Restricted access

Anass Arrogi, Astrid Schotte, An Bogaerts, Filip Boen and Jan Seghers

analyses. Missing data exceeded the level at which results can be biased (>5% missing). 27 Therefore, imputations were performed to minimize bias and preserve power. 28 Multiple imputation by chained equations was used to replace missing data ( m  = 20 imputations). The procedure of chained equations is

Restricted access

Koren L. Fisher, Elizabeth L. Harrison, Brenda G. Bruner, Joshua A. Lawson, Bruce A. Reeder, Nigel L. Ashworth, M. Suzanne Sheppard and Karen E. Chad

participants, resulting in a mean of four participants per neighborhood cluster. Finally, a sensitivity analysis was conducted to determine whether imputation for participants with differing amounts of missing data would have an effect on the results. The multivariate analysis was repeated using imputed values

Restricted access

Oleg Zaslavsky, Yan Su, Eileen Rillamas-Sun, Inthira Roopsawang and Andrea Z. LaCroix

strength was measured by a handgrip dynamometer and was rounded up to the nearest kilogram (in kg). BMI was calculated by dividing the weight (in kilograms) by the square of the height (in meters). Missing Data We conducted multiple imputations based on maximizing expectation method to account for the

Restricted access

Sharon Hetherington, Paul Swinton, Tim Henwood, Justin Keogh, Paul Gardiner, Anthony Tuckett, Kevin Rouse and Tracy Comans

, whereas intention-to-treat analyses incorporated multiple imputation ( m  = 10) using the “mice” package ( Buuren & Groothuis-Oudshoorn, 2011 ) in the R programming language to replace missing data. Imputation models included age, sex, health care resource utilization, Geriatric Anxiety Index ( Pachana et

Restricted access

Tiago V. Barreira, Stephanie T. Broyles, Catrine Tudor-Locke, Jean-Philippe Chaput, Mikael Fogelholm, Gang Hu, Rebecca Kuriyan, Estelle V. Lambert, Carol A. Maher, José A. Maia, Timothy Olds, Vincent Onywera, Olga L. Sarmiento, Martyn Standage, Mark S. Tremblay, Peter T. Katzmarzyk and for the ISCOLE Research Group

chance of bias due to exclusion of these cases. Missing values were multiply imputed (5 imputations) using fully conditional specification methods, under missing at random assumptions 24 and using SAS software (version 9.4; PROC MI, SAS Institute Inc., Cary, NC). Country-specific models were used to

Restricted access

Aubrey Newland, Rich Gitelson and W. Eric Legg

indicated that data were missing completely at random, χ 2  = 359.151, df  = 321, p  = .07, and <5% of the data were missing. Thus, hot-deck imputation ( Myers, 2011 ) was used to create the final data set. Hot-deck imputation is a method of replacing missing values of the nonrespondent with data from a

Restricted access

Shijun Zhu, Eun-Shim Nahm, Barbara Resnick, Erika Friedmann, Clayton Brown, Jumin Park, Jooyoung Cheon and DoHwan Park

). Participants who dropped out had frailer health (i.e., more arthritis, depression) than those who stayed in the study and were more likely to be hospitalized during the past 3 months prior to the baseline survey. We chose FIML instead of multiple imputation as FIML showed more efficiency in estimation than

Restricted access

Jeffrey Martin, Mario Vassallo, Jacklyn Carrico and Ellen Armstrong

imputation for five missing data points on the judge’s ratings of emotion was used. With this very low percentage of missing data, this approach is acceptable over more contemporary approaches such as multiple imputation ( Schafer, 1999 ; Schlomer, Bauman, & Card, 2010 ). We also calculated interrater