Repeated measures with zeros

Berk, KN; Lachenbruch, PA; Berk, K N; Lachenbruch, P A
August 2002
Statistical Methods in Medical Research;Aug2002, Vol. 11 Issue 4, p303
Academic Journal
journal article
Consider repeated measures data with many zeros. For the case with one grouping factor and one repeated measure, we examine several models, assuming that the nonzero data are roughly lognormal. One of the simplest approaches is to model the zeros as left-censored observations from the lognormal distribution. A random effect is assumed for subjects. The censored model makes a strong assumption about the relationship between the zeros and the nonzero values. To check on this, you can instead assume that some of the zeros are 'true' zeros and model them as Bernoulli. Then the other values are modeled with a censored lognormal. A logistic model is used for the Bernoulli p, the probability of a true nonzero. The fit of the pure left-censored lognormal can be assessed by testing the hypothesis that p is 1, as described by Moulton and Halsey. The model can also be simplified by omitting the censoring, leaving a logistic model for the zeros and a lognormal model for the nonzero values. This is approximately equivalent to modeling the zero and nonzero values separately, a two-part model. In contrast to the censored model, this model assumes only a slight relationship (a covariance component) between the occurrence of zeros and the size of the nonzero values. The models are compared in terms of an example with data from children's private speech.


Related Articles

  • Meta Analysis of Advanced Cancer Survival Data Using Lognormal Parametric Fitting: A Statistical Method to Identify Effective Treatment Protocols. Qazi, S.; DuMez, D.; Uckun, F. M. // Current Pharmaceutical Design;May2007, Vol. 13 Issue 15, p1533 

    We describe the use of a parametric lognormal model to calculate and compare survival statistics in the clinical treatment of advanced/metastatic pancreatic, breast and colon cancers. The fit using the lognormal model explained greater than 90% (R2 ranged from 0.917 to 0.998 for a total of the...

  • On Earthquake Predictability Measurement: Information Score and Error Diagram. Kagan, Yan Y. // Pure & Applied Geophysics;Oct2007, Vol. 164 Issue 10, p1947 

    We discuss two methods for measuring the effectiveness of earthquake prediction algorithms: The information score based on the likelihood ratio and error diagrams. For both of these methods, closed form expressions are obtained for the renewal process based on the gamma and lognormal...

  • An annual wet sulfate deposition index. Mohapl, J. // Stochastic Environmental Research & Risk Assessment;May2003, Vol. 17 Issue 1/2, p76 

    Averages of annual wet deposition data are often used as an indicator of acid amounts in the atmosphere. From the view point of statistics, the average is a meaningful estimator only for identically distributed data with specific types of probability distribution. Wet deposition data usually...

  • On the Generalized Lognormal Distribution. Toulias, Thomas L.; Kitsos, Christos P. // Journal of Probability & Statistics;2013, p1 

    This paper introduces, investigates, and discusses the γ-order generalized lognormal distribution (γ-GLD). Under certain values of the extra shape parameter γ, the usual lognormal, log-Laplace, and log-uniform distribution, are obtained, as well as the degenerate Dirac distribution. The...

  • Editorial. Eryilmaz, S.; Koutras, Markos // Methodology & Computing in Applied Probability;Dec2016, Vol. 18 Issue 4, p935 

    No abstract available.

  • Wind Energy Validation Using Available Wind Potential. Hapse, Manik M.; Thosar, A. G.; Shinde, Sanjay M.; Markad, Satish A. // International Journal on Communication;Mar2011, Vol. 2 Issue 1, p33 

    This paper analyzes the probability distribution of wind speed data recorded by Maharashtra Energy Development Agency (MEDA) wind farm at Ahmednagar (India). The main objective is to validate the wind energy probability by using probability distribution function (PDF) of available wind...

  • Tests of Long Memory: A Bootstrap Approach. Grau-Carles, Pilar // Computational Economics;Feb2005, Vol. 25 Issue 1/2, p103 

    Many time series in diverse fields have been found to exhibit long memory. This paper analyzes the behaviour of some of the most used tests of long memory: the R/ S analysis, the modified R/ S, the Geweke and Porter-Hudak (GPH) test and the detrended fluctuation analysis (DFA). Some of these...

  • Author's response. Lindquist, Russell // Quality Progress;Mar2013, Vol. 46 Issue 3, p6 

    The author responds to a letter concerning his article "In the Crosshairs," from the January 2013 issue, focusing on lognormal distributions and data analysis in time-based characterization calculations.

  • The variable for the generalized confidence interval for the lognormal mean. Maiklad, Thongkam // Songklanakarin Journal of Science & Technology;2008, Vol. 30 Issue 4, p547 

    The purpose of this paper is to propose a new variable for the generalized confidence interval method to estimate the Confidence interval of the lognormal mean. In order to evaluate the efficiency of this new method, here called t-generalized method, a simulation study was conducted to examine...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics