Using adaptive tests for the analysis of repeated measurements.

Several methods have been proposed for the analysis of data obtained from experimental units that are observed at multiple time points. In this paper we evaluate the performance of an adaptive test for the interaction of group and time, and an adaptive test for the group effect with data sets having measurements at common time points on two groups of experimental units. The results from extensive simulation studies show that the adaptive tests maintain their level of significance and are often more powerful than the corresponding likelihood ratio and mixed model tests when the error distributions and the random effect distributions are nonnormal. When the distributions are normal, the adaptive tests are nearly as powerful as the other tests.

Alcoholism and antisocial personality. Interrelationships, genetic and environmental factors.

In a sample of 127 male and 87 female adult adoptees, antisocial personality and alcohol abuse were related to biologic backgrounds and to environmental factors. In the men, alcohol abuse was increased by a background of problem drinking in first-degree biologic relatives and by drinking problems in the adoptive home. Antisocial personality occurred more frequently in men whose first-degree biologic relatives had antisocial behavior problems. In the women, alcohol abuse was increased in adoptees whose first-degree relatives had problem drinking. Increased alcohol abuse in men and women was not predicted by biologic first-degree relatives with antisocial problems, nor did increased frequency of antisocial personality occur in adoptees with biologic relatives with problem drinking. The results suggest specificity of inheritance of antisocial and alcoholic conditions and the importance of environmental factors.

An adoption study of genetic and environmental factors in drug abuse.

In a sample of 242 male and 201 female adoptees who had been separated at birth from biologic parents, adult adoptee diagnoses of alcohol abuse, drug abuse and antisocial personality were correlated with biologic and environmental factors. Three etiologic relationships with drug abuse were found: drug abuse was highly correlated with antisocial personality, which in turn was predicted from antisocial biologic background; a biologic background of alcohol problems predicted increased drug abuse in adoptees who did not have antisocial personalities; and environmental factors of divorce and psychiatric disturbance in the adoptive family were associated with increased drug abuse.

The effect of state anxiety on personality measurement.

The authors examined the effect of state anxiety on the personality test scores of 56 patients receiving treatment for panic disorder and agoraphobia. The tests were administered before treatment and again 6 weeks later. For the 40 patients who improved by 5 or more points on the Hamilton Anxiety Rating Scale, significant changes in personality measures were observed at week 6, including increased emotional strength and extraversion and decreased interpersonal dependency. The authors conclude that state anxiety, like depression, is a possible confounding factor in personality measurement, and adjustment for it should be made in future studies.

Statistical analysis of K 2 x 2 tables: a comparative study of estimators/test statistics for association and homogeneity.

In order to control for confounding variables, epidemiologists often obtain data in the form of a 2 x 2 table. One variable is usually the disease status, while the other variable represents a dichotomous exposure variable that is suspected of being a risk factor. If a confounding variable is present, the data are often stratified into several 2 x 2 tables. The objectives of the analysis are to test for the association between the suspected risk factor and the disease and to estimate the strength of this relationship. Before estimating a common odds ratio, it is important to check whether the odds ratios are homogeneous. This paper presents the results of a Monte Carlo study that was performed to determine the size and power of a number of tests of association and homogeneity when the data are sparse. We also evaluated the performance of three estimators of the common odds ratio. For the Monte Carlo studies, equal numbers of cases and controls were used in a wide variety of sparse data situations. On the basis of these studies, we recommend the Breslow-Day test for nonsparse data, and the T4 and T5 statistics for sparse data to test for homogeneity. The Mantel-Haenszel test of association is recommended for sparse and nonsparse data sets. With sparse data, none of the odds ratio estimators are entirely satisfactory.

Second nonocular tumors in survivors of heritable retinoblastoma.

We reviewed the records of 50 patients with heritable retinoblastoma to study the cause of death, if deceased, or the incidence of second nonocular malignant neoplasms. The incidence of second tumors in these patients was 6% at ten years, 14% at 20 years, and 14% at 30 years. These findings are lower than previously reported results. Pinealoma was the probable cause of death in three of the five patients who died of second nonocular tumors.

The incidence and significance of hemostatic abnormalities in patients with head injuries.

Abnormal coagulation and fibrinolysis is a frequent complication in patients with head injury. This complication can be severe enough to lead to hemorrhage or thrombosis. A study was undertaken to determine if the hemostatic abnormalities are reliable indicators of outcome. Hemostasis in 269 patients with head injuries alone was screened using platelet count (PC), prothrombin time (PT), activated partial thromboplastin time (APTT), thrombin clotting time (TCT), fibrinogen assay (FIB), level of fibrin-fibrinogen degradation products (FDP), and disseminated intravascular coagulation (DIC) score in the first 24 hours after injury. Test results were compared with the outcome (discharged or dead) in the entire group and in subgroups divided on the basis of the severity of injury as determined by the Glasgow coma score (GCS). Increased consumptive coagulopathy at admission, as reflected in the DIC score, predicts the outcome of head-injured patients with a high degree of accuracy. The degree of increase of the initial FDP level and prolongation of TCT also correlated positively with the outcome. Prolongation of the APTT correlated strongly with unfavorable outcome in a large group of patients, and in a small group, markedly accelerated APTT also predicted death. Stepwise logistic regression analysis demonstrated that GCS, FDP level, and DIC score predicted outcome. Other tests did not provide additional predictive value. Abnormal hemostasis frequently complicates the course of patients with head injuries. This study demonstrates that hemostasis tests are predictors of outcome in these patients.

Genetic and environmental factors in major depression.

A study of 48 individuals with major depression in a sample of 443 adoptees has shown that depression is positively but not significantly correlated with a biologic background of affective disorder. Both primary and secondary depression was positively and significantly correlated with several environmental factors. In males, an adoptive home where another individual had an alcohol problem increased depression; in females, death of an adoptive parent prior to adoptee age 19 and an adoptive family where another individual had a behavior disturbance increased depression. Results suggest that the environmental factors occurring prior to adoptees age 18 predisposed to depression.

Genetic and environmental factors in alcohol abuse and antisocial personality.

Previous analyses of adoptees from Lutheran Social Services of Iowa developed a multifactorial model of adoptee alcohol abuse that related abuse to three factors: biologic background of alcohol-related problems, biologic background of antisocial problems and exposure to an adoptive family where family members had alcohol-related problems. The present study examines an independently collected sample of adoptees from a different agency--the Iowa Children's and Family Services, and confirms the multifactorial model previously found in the Lutheran Social Service data. The model shows a specificity of type of inheritance and type of environmental influence: biologic family alcohol-related problems predict increased alcohol abuse in adoptee, biologic family antisocial behaviors predict increased antisocial personality diagnoses in adoptee, and environmental factors of alcohol-related problems in the adoptive family predict increased adoptee alcohol abuse.

Prediction of the widths of unerupted canines and premolars.

The purpose of this study was to develop, with simple linear regression analysis, equations that could accurately predict the mesiodistal widths of unerupted canines and premolars in both arches of the mixed dentition patient. Clinically useful prediction equations were developed and tested on a sample of orthodontic patients. Performance of the equations in patients was satisfactory. Charts and suggestions for completing a tooth size-arch length analysis in the patient with a mixed dentition were discussed.

Using sign score regression models to select variables in case-control studies.

This paper evaluates the performance of four variable selection methods suitable for case-control studies. Two of the methods are logistic regression and the rank transformed version of it which uses the ranks of the explanatory variables in place of the original observations. The third method is based on Kendall's tau b correlations. I propose a fourth method, a sign score regression model to select variables. To evaluate these four methods, I generate many data sets for a case group and a control group with the use of several different distributions and covariance matrices. I evaluate the methods on their ability to select correctly the variables related to case-control status while not selecting the unrelated variables. Using this criterion, the sign score regression method and the tau b method are more effective than the other two methods with uncorrelated or weakly correlated variables. The sign score regression method is more effective than the tau b method for all simulations that use normal variables and for some that use log-normal variables. Overall, the sign score regression method is the most effective variable selection method for data sets that have low or moderate correlations between variables.

A comparison of several tests for censored paired data.

This paper reviews several tests for censored paired data and uses Monte Carlo methods to evaluate their sizes and powers. Each of the tests maintains its size. The Akritas test and the paired Prentice-Wilcoxon test are somewhat more powerful than the Gehan statistic or the generalized signed rank test for most of the distributions studied. If the survival times follow an exponential distribution, then the Gehan and the generalized signed rank tests are more powerful against a location shift alternative.

On the efficacy of the rank transformation in stepwise logistic and discriminant analysis.

We have evaluated the performance of four stepwise variable selection procedures commonly used in medical and epidemiologic research. The four procedures are discriminant and logistic regression and their rank transformed versions, where the independent variables are replaced by their ranks. We generated, by computer, data for two groups from several distributions with a variety of sample sizes and covariance matrices. The two ranking procedures each increased the chance of correctly selecting those variables related to group membership for data generated from log-normal or contaminated distributions. For normally distributed data the ranking procedure had little effect on variable selection. Rank transformed discriminant analysis and rank transformed logistic regression were equally effective in selecting variables when sample sizes exceeded 100. Rank transformed discriminant analysis was superior for smaller data sets. We discuss the implications of the results of this study for clinical and epidemiologic research.

Using Kendall's tau b correlations to improve variable selection methods in case-control studies.

In this manuscript we evaluate the performance of a variable selection procedure that could be used in case-control studies. This method is based on selection statistics computed from a matrix of Kendall tau b correlation coefficients. A simulation study was performed to compare the performance of this method to logistic regression, discriminant analysis, and the rank-transformed versions of these methods. For most of the situations studied the method based on Kendall tau b correlation coefficients correctly selected the variables that were related to case-control status more often than any of the other methods. We discuss the implications of the results of this study for epidemiologic research.

Total hip acetabular component position affects component loosening rates.

Loosening is the most common long-term problem following total hip arthroplasty. Many factors, including patient selection, cement technique, femoral component placement, and prosthesis design reportedly affect the incidence of loosening. Theoretically, the location of the hip center of rotation substantially affects the load on the hip, and superior and lateral hip center location will result in higher loads than medial and inferior placement. Long-term follow-up studies (average, 9.1 years after surgery) using logistical regression analysis demonstrate significantly higher rates of femoral loosening with acetabular components placed in a superior and lateral (i.e., nonanatomic) position, compared with acetabular components placed in a nearly anatomic position.

A comparison of two methods of estimating a common risk difference in a stratified analysis of a multicenter clinical trial.

In this paper, we compare two methods of estimating the difference between the proportion of adverse events in a test treatment group and the proportion of adverse events in a control treatment group in a multicenter clinical trial. We used simulated data to compare the bias and mean squared error of the weighted least squares estimator to the bias and mean squared error of the Cochran-Mantel-Haenszel estimator. We also computed the coverage probabilities for confidence intervals derived from these estimators. We found that the weighted least squares method was often seriously biased. The coverage probabilities for the Cochran-Mantel-Haenszel estimators were often closer to their nominal values than were the coverage probabilities for the weighted least squares estimators. It also was found that these methods require a larger sample size to maintain coverage probabilities near their nominal values when unequal numbers of persons are assigned to the test and control treatments.

A Monte Carlo investigation of homogeneity tests of the odds ratio under various sample size configurations.

Epidemiologic data for case-control studies are often summarized into K 2 x 2 tables. Given a fixed number of cases and controls, the degree of sparseness in the data depends on the number of strata, K. The effect of increasing stratification on size and power of seven tests of homogeneity of the odds ratio is studied using Monte Carlo methods. In all the designs considered here, the numbers of cases and controls per stratum are the same. Considering both size and power in non-sparse-data settings, we recommend the Breslow-Day statistic (1980, Statistical Methods in Cancer Research, 1. The Analysis of Case-Control Studies, p. 142; Lyon: International Agency for Research on Cancer) for general use. In sparse-data settings the T4 statistic of Liang and Self (1985, Biometrika 72, 353-358) performs the best when all tables, regardless of sample size, have odds ratios generated from the same distribution. In sparse-data settings characterized by a large table with an odds ratio of 1 and many small tables with odds ratios greater than 1, the T5 statistic of Liang and Self (1985) performs the best. One of the most important results of this study is the generally low power for all homogeneity tests especially when the data are sparse.

Reduction in hypochondriasis with treatment of panic disorder.

Hypochondriasis was assessed in 60 patients with panic disorder and agoraphobia using the Illness Behavior Questionnaire. Before treatment, IBQ hypochondriasis scores were similar to those of a group of hypochondriacal psychiatric patients. In patients who improved with treatment, significant reductions in somatic preoccupation, disease phobia, and disease conviction occurred. Hypochondriasis appears to be a prominent feature of panic disorder and agoraphobia, and responds to treatment of the primary conditions. Our findings underscore the importance of providing adequate treatment and thereby avoiding wasteful use of medical resources and alienation of patients from doctors.

Relative afferent pupillary defect in eyes with retinal detachment.

Relative afferent pupillary defects were measured before and after surgery in 38 patients with unilateral rhegmatogenous retinal detachment. All 38 patients were measured preoperatively and the mean (+/- SD) pupillary defect was 1.4 +/- 0.7 log units. The afferent pupillary defect decreased in 36 of the 38 patients after successful scleral buckling operations (postoperative mean = 0.4 +/- 0.3 log units). Twenty patients had defects postoperatively of 0.3 log units or less, and seven of these had no measurable defects at all. A prediction model, using the variables of total number of peripheral quadrants detached and whether the macula was detached, yielded the following prediction equation: Relative afferent pupillary defect (log units) = 0.35 X (total quadrants) + 0.68 X macula detachment. This means that the detachment of each peripheral quadrant of retina caused about 0.35 log units of defect, whereas detachment of the macula caused 0.68 log units. The standard error of this estimate was rather large (+/- .65 log units); therefore, the size of the afferent pupillary defect can only roughly predict the extent of the retinal detachment and vice versa.