Michael Parzen
Emory University
44 Papers
437 Citations
Michael Parzen is an academic researcher from Emory University. The author has contributed to research in topics: Missing data & Covariate. The author has an hindex of 20, co-authored 44 publications. Previous affiliations of Michael Parzen include Harvard University & University of Illinois at Chicago.
Chat about Author
Papers
Striving toward the future: Aspiration-performance discrepancies and planned organizational change
TL;DR: In this article, it is argued that organizations form their social aspirations based on two types of interorganizational comparisons: competitive and striving, and that organizations that are performing well relative to competitors do not necessarily become inertial, as theory suggests.
106
Use of the Probability Integral Transformation to Fit Nonlinear Mixed-Effects Models With Nonnormal Random Effects
Kerrie P. Nelson,Stuart R. Lipsitz,Garrett M. Fitzmaurice,Joseph G. Ibrahim,Michael Parzen,Robert L. Strawderman +5 more
TL;DR: In this article, the maximum likelihood estimates of nonlinear mixed-effect models are obtained by using the probability integral transform (PIT) to transform a normal random effect to a nonnormal random effect.
85
•Posted Content
A Meta-Analysis of the Determinants of Organic Sales Growth
TL;DR: In this paper, the authors present the results of a meta-analysis on drivers of organic sales growth, conducted using a Hierarchical Bayes estimation technique, based on a comprehensive review of a diverse set of literatures.
77
An Estimate of the Odds Ratio That Always Exists
TL;DR: In this article, an estimate of the odds ratio in a (2 × 2) table obtained from studies in which the row totals are fixed by design, such as a phase II clinical trial, is presented.
57
A jackknife estimator of variance for Cox regression for correlated survival data.
Stuart R. Lipsitz,Michael Parzen +1 more
TL;DR: It is shown that a "one-step" jackknife estimator of variance is asymptotically equivalent to their variance estimator, and may be preferred because an investigator needs only to write a simple loop in a computer package instead of a more involved program to compute Wei et al. (1989) and Lee et al.'s (1992) estimator.
45