A Weighting Approach for GEE Analysis with Missing Data

We propose a new weighting (WT) method to handle missing categorical outcomes in longitudinal data analysis using generalized estimating equations (GEE). The proposed WT provides a valid GEE estimator when the data are missing at random (MAR), and has more stable weights and shows advantage in efficiency compared to the inverse probability weighing method in the presence of small observation probabilities. The WT estimator is similar to the stabilized weighting (SWT) estimator under mild conditions, but it is more stable and efficient than SWT when the associations of the outcome with the observation probabilities and the covariate are strong.     

Methods for missing covariates in logistic regression

Various methods have been suggested in the literature to handle a missing covariate in the presence of surrogate covariates. These methods belong to one of two paradigms. In the imputation paradigm, Pepe and Fleming (1991) and Reilly and Pepe (1995) suggested filling in missing covariates using the empirical distribution of the covariate obtained from the observed data. We can proceed one step further by imputing the missing covariate using nonparametric maximum likelihood estimates (NPMLE) of the density of the covariate. Recently Murphy and Van der Vaart (1998a) showed that such an approach yields a consistent, asymptotically normal, and semiparametric efficient estimate for the logistic regression coefficient. In the weighting paradigm, Zhao and Lipsitz (1992) suggested an estimating function using completely observed records after weighting inversely by the probability of observation. An extension of this weighting approach designed to achieve semiparametric efficient bound is considered by Robins, Hsieh and Newey (RHN) (1995). The two ends of each paradigm (NPMLE and RHN) attain the efficiency bound and are asymptotically equivalent. However, both require a substantial amount of computation. A question arises whether and when, in practical situations, this extensive computation is worthwhile. In this paper we investigate the performance of single and multiple imputation estimates, weighting estimates, semiparametric efficient estimates, and two new imputation estimates. Simulation studies suggest that the sample size should be substantially large (e.g. n=2000) for NPMLE and RHN to be more efficient than simpler imputation estimates. When the sample size is moderately large (n≤ 1500), simpler imputation estimates have as small a variance as semiparametric efficient estimates.     

Analytic computation of nonparametric Marsan–Lengliné estimates for Hawkes point processes

In 2008, Marsan and Lengliné presented a nonparametric way to estimate the triggering function of a Hawkes process. Their method requires an iterative and computationally intensive procedure which ultimately produces only approximate maximum likelihood estimates (MLEs) whose asymptotic properties are poorly understood. Here, we note a mathematical curiosity that allows one to compute, directly and extremely rapidly, exact MLEs of the nonparametric triggering function. The method here requires that the number q of intervals on which the nonparametric estimate is sought equals the number n of observed points. The resulting estimates have very high variance but may be smoothed to form more stable estimates. The performance and computational efficiency of the proposed method is verified in two disparate, highly challenging simulation scenarios: first to estimate the triggering functions, with simulation-based 95% confidence bands, for earthquakes and their aftershocks in Loma Prieta, California, and second, to characterise triggering in confirmed cases of plague in the United States over the last century. In both cases, the proposed estimator can be used to describe the rate of contagion of the processes in detail, and the computational efficiency of the estimator facilitates the construction of simulation-based confidence intervals.     

A History of Prejudice: Race,Caste, and Difference in India and the United States

Robert S. Gottfried, Epidemic Disease in Fifteenth‐Century England. The Medical Response and the Demographic Consequences (1978), xiii+262 (Leicester University Press, £10.00).

Phyllis Mack Crew, Calvinist Preaching and Iconoclasm in the Netherlands 1544–1569 (1978), 221 (Cambridge University Press, £9.50).

F. Furet and J. Ozouf, Lire et Ecrire: l'alphabétisation des français de Calvin à Jules Ferry, (1977), 2 vols. 370+379 (Editions de Minuit, Paris, 45 F and 55 F). [Reading and Writing. The development of literacy amongst the French from Calvin to Jules Ferry]

S. Åkerman, H. Chr. Johansen and D. Gaunt (eds) with J. Pedersen (co. ed.), Chance and Change: Social and Economic Studies in Historical Demography in the Baltic Area (1978), 296 (Odense University Press, D.kr. 100.00).

Angus McLaren, Birth Control in Nineteenth‐century England (1978), 263 (Croom Helm, £8.95).

Edward J. Bristow, Vice and Vigilance: Purity Movements in Britain Since 1700 (1977), xii+274 (Gill and Macmillan, Dublin, £12).

Timothy Tackett, Priest and Parish in Eighteenth‐century France: a social and political study of the curés in a diocese of the Dauphine, 1750–1791 (Princeton, 1977). xiii+350 (Princeton University Press, £14.60).

Jerome Blum, The End of the Old Order in Rural Europe (1978), xiii+505 (Princeton University Press, Princeton, £18.40).

David Spring (ed.), European Landed Elites in the Nineteenth Century (1977), vii+147 (The Johns Hopkins University Press, Baltimore, £8.75).

Peter R. Decker, Fortunes and Failures: White‐collar Mobility in Nineteenth‐century San Francisco (1978), xvi+336 (Harvard University Press, £14.00).

Geoffrey Crossick, An Artisan Elite in Victorian Society, Kentish London 1840–1880 (1978), 306 (Croom Helm, £9.95).

John Bodnar, Immigrants and Industrialization: Ethnicity in an American Mill Town, 1870–1940 (1977), xix+213 (University of Pittsburgh Press, $11.95).

John W. Briggs, An Italian Passage: Immigrants to Three American Cities, 1890–1930 (1978), xxii+348 (Yale University Press, New Haven and London, £14.40).

Pat Thane (ed.), The Origins of British Social Policy (1978), 209 (Croom Helm, £7.95).

J. R. Hay, The Development of the British Welfare State 1880–1975 (1978), 116 (Edward Arnold, £7.00, paperback £2.25).     

Are You Truly a Recovering Dope Fiend? Local Interpretive Practices at a Therapeutic Community Drug Treatment Program

Previous qualitative research on treatment programs for drug addiction/alcoholism has primarily focused on those processes whereby participants are expected to construct a new sense of self according to institutional parameters. The present article builds on that research and explores how contemporary programs attempt to resolve the problem that it is almost impossible to tell if someone has engaged in this self‐construction process. Informed by five months of ethnographic fieldwork at an adult residential drug treatment facility, the article asks: under what circumstances do program members call into doubt a client's efforts to create an institutional self, and how do they express this skepticism? The article reveals that staff and clients employ a set of local interpretive practices about community and emotions to assess whether clients are constructing the institutional self of a “recovering dope fiend.” It specifically considers how they interpret a client's emotional displays to represent that client's current self under construction. That is, a client's ability to control anger appropriately or to handle anxiety demonstrates s/he is effectively “doing the program” of self‐construction.     

Adolescent Sexuality and the Risk of Marital Dissolution

This research investigates whether first sexual intercourse during adolescence is associated with increased risk of first marriage dissolution and tests whether the results are consistent with causal or selection explanations. Drawing on a sample of 3,793 ever‐married women from the 2002 National Survey of Family Growth, this study estimated event‐history models of first‐marriage dissolution. Results indicate that wanted sexual debut in later adolescence does not directly increase the risk of marital dissolution but is linked indirectly as a result of subsequent premarital sexual outcomes. Sexual debut that is not completely wanted or that occurs before age 16 is associated with increased risk of marital dissolution. The results suggest that the timing and context of adolescent sexual debut have important implications for marital stability.     

Repeated measurement analysis for nonnormal data in small samples

The small sample performance of Zeger and Liang's extended generalized linear models for the analysis of longitudinal data (Biometrics, 42,121-130,1986) is investigated for correlated gamma data. Results show that the confidence intervals do not provide desirable coverage of the true parameter due to considerably biased point estimates. Improved estimates are proposed using the jackknife procedure. Simulations performed to evaluate the proposed estimates indicate superior properties to the previous estimates.