Daniel Mihalko

On Similarity Indices and Correction for Chance Agreement

Similarity indices can be used to compare partitions (clusterings) of a data set. Many such indices were introduced in the literature over the years. We are showing that out of 28 indices we were able to track, there are 22 different ones. Even though their values differ for the same clusterings compared, after correcting for agreement attributed to chance only, their values become similar and some of them even become equivalent. Consequently, the problem of choice of the index to be used for comparing different clusterings becomes less important.

Gene expression changes in postmortem tissue from the rostral pons of multiple system atrophy patients

Multiple system atrophy (MSA) is a neurodegenerative disease characterized by various degrees of Parkinsonism, cerebellar ataxia, and autonomic dysfunction. In this report, Affymetrix DNA microarrays were used to measure changes in gene expression in the rostral pons, an area that undergoes extensive damage in MSA, but not other synucleinopathies. Significant changes in expression of 254 genes (180 downregulated and 74 upregulated) occurred in pons tissue from MSA patients when compared with control patients. The downregulated genes were primarily associated with biological functions known to be impaired in Parkinsons disease (PD) and other neurological diseases; for example, downregulation occurred in genes associated with mitochondrial function, ubiquitin‐proteasome function, protein modification, glycolysis/metabolism, and ion transport. On the other hand, upregulated genes were associated with transcription/RNA modification, inflammation, immune system function, and oligodendrocyte maintenance and function. Immunocytochemistry, in conjunction with quantitative image analysis, was carried out to characterize α‐synuclein protein expression as glial cytoplasmic inclusions in the pontocerebellar tract in rostral pons tissue and to determine the relationship between the amount of aggregated α‐synuclein protein and changes in specific gene expression. Of the regulated genes, 86 were associated with the amount of observed aggregated α‐synuclein protein in the rostral pons tissue. These data indicate that cells in the pons of MSA patients show changes in gene expression previously associated with the substantia nigra of PD patients and/or other neurological diseases, with additional changes, for example related to oligodendrocyte function unique to MSA.

Predictors of response to alprazolam and placebo in patients with panic disorder

Date from a panic disorder treatment study with 506 patients, comparing alprazolam and placebo in a double-blind manner for 8 weeks, were analyzed to identify demographic and clinical characteristics of the patients that might predict response to treatment. The strongest predictors of response to alprazolam were age over 40, and lower baseline levels of anxiety and phobic symptoms. Predictors of response to placebo were weaker and, in addition to lower levels anxiety and panic attacks, included a lack of previous psychiatric treatment.

Score computation for linear rank procedures

Efficient scores for linear rank two sample procedures on censored data take the form of multiple integrals which often cannot be expressed in closed algebraic form. In this paper we show that efficient scores for censored data can be written as a linear combination of the efficient scores for uncensored data. A recursive scheme for computing the coefficients in these linear combinations is given. The usefulness of the procedure is demonstrated by its application to censored lognormal data. The accuracy and applicability of the algorithm is discussed.

Repeated significance testing in survival analysis using a litter-matched design

This paper shows that, asymptotically, a general class of linear rank procedures in a litter-matched design form a Gauss-Markov process over time. This result is used to develop a procedure for repeated significance testing for time-to-response differences in litter-matched studies. In addition, an important class of two-sample linear rank procedures is shown to have uncorrelated increments over time. An example is given using a litter-matched cancer study. Empirical indications of the accuracy of a method for approximating multivariate normal critical values are also given.

A Monte Carlo Power Study of Logrank, Wilcoxon and Normal Scores Procedures on Matched and Censored Data

The powers of several nonparametric tests for determining a treatment effect using matched censored data are compared by simulation. The tests include adaptations of two sample Prentice efficient score extensions of the Exponential Scores, Wilooxon and Normal Scores tests with three different variance estimators. The tests are compared on simulated exponential, loglogistic and lognormal matched censored data. No test performed uniformly better than the others. However the Exponential Scores, or Logrank, test using the permutation or hypergeometric variance seemed to be more powerful in quite a few situations as well as having other advantages.

A sequential regression method in monte carlo studies

In this paper we consider a sequential version of the regression method in Monte Carlo studies under the framework of sequential estimation theory. The proposed procedure is easy to adopt on the computer, and its asymptotically optimal properties are carefully justified. Empirical results are also given.