Search PubMed⌕ Search

Biomedical subjects

A A Afifi

Publications and source records attributed to A A Afifi.

At least 19 recordsLinked to original sources
PubMed1999

Exact and asymptotic tests for homogeneity in several 2 x 2 tables.

This paper presents the results of a Monte Carlo study comparing the performance, in terms of size and power, of six exact and six asymptotic tests for the homogeneity of odds ratios in several 2 x 2 contingency tables. With a small sample size or sparse data structure, the exact tests performed better than the asymptotic tests because they maintained the nominal size and, in some situations, had slightly higher power. Among the exact tests, we recommend the Zelen, Pearson chi-square and scores tests. Among the asymptotic tests, the Breslow-Day and Pearson chi-square tests were slightly better in some situations than the unconditional and conditional score tests. However, both exact and asymptotic tests had low power for small strata sizes, even with moderate to large heterogeneity of odds ratios. Corroborating previous findings, the asymptotic unconditional likelihood ratio test was too liberal in terms of size.

Chi-Square Distribution↗
PubMed1997

Ozone-induced DNA strand breaks In guinea pig tracheobronchial epithelial cells.

Ozone (O3), the major oxidant of photochemical smog, is thought to be genotoxic and a potential respiratory carcinogen or promoter of carcinogenic processes. Because of oxidative reactions with the mucus in the upper airway, O3 reaction products are able to penetrate into the tracheobronchial epithelial (TE) cells. The carcinogenic effects of O3 on the TE cells are especially of interest since most previous studies have focused on the morphology or permeability changes of tracheas only. Therefore, the objective of this study was to examine the potential O3 genotoxicity in TE cells after an in vivo exposure, using DNA strand breaks as an index. Two-month-old male Dunkin-Hartley guinea pigs, specific pathogen free, 4 in each group, were exposed to 1.0 ppm O3 for 0, 12, 24, 48, 72, or 96 h. Animals exposed to filtered air without O3 exposure were used as controls. After O3 exposure, the trachea with two main bronchi was removed from each animal, and TE cells were isolated and employed for determination of DNA strand breaks by fluorometric analysis of DNA unwinding (FADU). The statistical significance level was set at alpha = .05. Compared with controls, ozone exposure did not alter the TE cell yield or viability, but caused an increase in protein content in tracheal lavage and an increase in DNA strand breaks. The amount of DNA left in the alkali lysate of TE cells found at 72 h exposure was significantly decreased from controls for 3 different alkali incubation times. An increase of the double-stranded DNA left in the alkali lysate of TE cells was observed at 96 h of exposure and approached the value of 24 h of exposure. The same pattern was seen with all 3 different alkali incubation times at 15 degrees C. One Qd unit was estimated to correspond to 100 strand breaks per cell. The Qd was also used as an indicator for O3 damage. Compared to controls, the Qd increases significantly after 1 ppm O3 exposure for 72 h, regardless of the alkali incubation time at 15 degrees C.

Animals↗
PubMed1997

Occupational electric and magnetic field exposure and leukemia. A meta-analysis.

We conducted a meta-analysis to acquire an understanding of the association between leukemia and occupational exposure to electric and magnetic fields. To explore sources of heterogeneity, study characteristics were scored and examined using regression analysis. While most studies present a small elevation in risk, the apparent lack of a clear pattern of exposure to EMF and risk of leukemia substantially detracts from the hypothesis that measured magnetic fields in the work environment are responsible for the observed excess risk of leukemia. Findings were not sensitive to assumptions, influence of individual studies, weighting schemes, and modeling. Some evidence of publication bias is noted.

Bias↗
PubMed1997

Censoring issues in survival analysis.

A key characteristic that distinguishes survival analysis from other areas in statistics is that survival data are usually censored. Censoring occurs when incomplete information is available about the survival time of some individuals. We define censoring through some practical examples extracted from the literature in various fields of public health. With few exceptions, the censoring mechanisms in most observational studies are unknown and hence it is necessary to make assumptions about censoring when the common statistical methods are used to analyze censored data. In addition, we present situations in which censoring mechanisms can be ignored. The effects of the censoring assumptions are demonstrated through actual studies.

Bias↗
PubMed1995

Occupational electric and magnetic field exposure and brain cancer: a meta-analysis.

We conducted a meta-analysis to acquire an understanding of the association between central nervous system cancer and occupational exposure to electric and magnetic fields. To explore sources of heterogeneity, study characteristics were scored and examined using regression analysis. An inverse-variance weighted pooling leads to a small overall increase in relative risk (10 to 20%) for the broad group of electrical occupations. One of the largest differences was lower relative risk for Scandinavian studies. Lower relative risks were also reported in cohort- and incidence-based studies. Findings were not sensitive to assumptions, including unpublished data, influence of individual studies, weighting schemes, and modeling. Whereas most studies present a small elevation in risk, there is considerable heterogeneity among the results.

Brain Neoplasms↗
PubMed1991

Evaluation of exact and asymptotic interval estimators in logistic analysis of matched case-control studies.

We compare six methods for constructing confidence intervals for a single parameter in stratified logistic regression. Three of these are based on inversion of standard asymptotic tests--namely, the Wald, the score, and the likelihood ratio tests. The other three are based on the exact distribution of the sufficient statistic for the parameter of interest. These include the traditional exact method of constructing confidence intervals, and two others, the mid-P and mean-P methods, which are modifications of this procedure that aim at reducing the conservative bias of the exact method. Using efficient algorithms, the six methods are compared by determination of their exact coverage levels in a series of conditional sample spaces. An incident case-control study of lung cancer in women is used to further illustrate the differences among the various methods. Computation of coverage functions is seen as a useful graphical diagnostic tool for assessing the appropriateness of different methods. The mid-P and the score methods are seen to have better coverage properties than the other four.

Biometry↗
PubMed1990

Effects of short-term, single and combined exposure to low-level NO2 and O3 on lung tissue enzyme activities in rats.

To examine the pulmonary effects of relatively low levels of NO2 and O3, and test for any possible interaction in their effects, we exposed 3-mo-old male Sprague-Dawley rats, free of specific pathogens, to either filtered room air (control) or 1.20 ppm (2256 micrograms/m3) NO2, 0.30 ppm (588 micrograms/m3) O3, or a combination of the two oxidants continuously for 3 d. We studied a series of parameters in the lung, including lung weight, and enzyme activities related to NADPH generation, sulfhydryl metabolism, and cellular detoxification. The results showed that relative to control, exposure to NO2 caused small but nonsignificant changes in all the parameters; O3 caused significant increases in all the parameters except for superoxide dismutase; and a combination of NO2 and O3 caused increases in all the parameters, and the increases were greater than those caused by NO2 or O3 alone. Statistical analysis of the data showed that the effects of combined exposure were synergistic for 6-phosphogluconate dehydrogenase, isocitrate dehydrogenase, glutathione reductase, and superoxide dismutase activities, and additive for glutathione peroxidase and disulfide reductase activities, but indifferent from those of O3 exposure for other enzyme activities.

Animals↗
PubMed1989

A note on confidence limits for quartiles with right censored data.

Two new methods are proposed for constructing the confidence limits for quartiles. The small sample behaviour of these two methods is compared with the Jennison and Turnbull modified Brookmeyer-Crowley method at three quartiles. The simulation study indicates that one of the new methods, the smoothed modified reflected method, is preferred over the other methods when the censoring rate is less than 40 per cent while the Jennison and Turnbull method is preferred for higher censoring. The results for the upper quartile are similar to the median. For the lower quartile with small sample and high censoring, semi-infinite intervals may often occur. The correct practice is to permit the semi-infinite intervals without modifying them since it is more informative and gives closer to nominal level coverage.

Computer Simulation↗
PubMed1988

Estimation of probabilities using the logistic model in retrospective studies.

Methods for estimating the parameters of the logistic regression model when the data are collected using a case-control (retrospective) scheme are compared. The regression coefficients are estimated by maximum likelihood methodology. This leaves the constant term parameter to be estimated. Four methods for estimating this parameter are proposed. The comparison of the four estimators is in two parts. First, they are compared for large samples. This is accomplished via the asymptotic distribution of the estimators. Second, the estimators are compared for small samples. This is conducted via stimulation using 11 logistic models. The estimation of the posterior probability of the response variable being a success (Px), as given by the logistic regression model, when the constant parameter is estimated by each of the four proposed methods is the main focus of this paper. A third concern is the comparison of the logistic discriminant procedures when each of the four methods of estimating the constant parameters is used. In addition, the linear discriminant function procedure is included. This comparison is executed only for small samples via simulation. It was found that when estimating Px, method 1 (which is essentially the MLE) minimizes the expected mean square error. The results were not as clear when the parameter of interest was the constant term itself. The results from the classification comparisons implied that when the logistic model contains mostly (or all) binary regression variables the logistic discriminant procedure using method 1 to estimate the constant term gives minimum expected error rate; otherwise the linear discriminant function gives minimum expected error rate. In the latter case the logistic discriminant procedure (method 1 estimator of the constant term) is approximately as good.

Computer Simulation↗
PubMed1987

Prevalence of Alzheimer's disease in a retirement community.

In a white, predominantly middle class southern California retirement community, 817 adults aged 65-99 years were evaluated in 1980-1982 in a study designed to assess prevalence of early Alzheimer-type senile dementia. Based on 162 neurologically diagnosed cases, the age- and sex-adjusted prevalence of Alzheimer's disease in the target population was 15.3% (95% confidence interval = 13.0-17.5) among persons aged 65+ years and 35.8% among persons aged 80+ years. Age-adjusted correction for false negatives not detected by a screening procedure yields an estimated prevalence of 16.4% in persons aged 65+ years. Validity of the diagnostic approach was confirmed by a follow-up study. These rates far exceed past prevalence estimates for this disease. Since prevalence of mid- or later stages of Alzheimer's disease may have been underestimated, the high rates in this study may reflect a considerable community burden of early disease. Observed prevalence of Alzheimer-type senile dementia was higher among men than women after adjustment for age, 19.1% and 13.1%, respectively. The female predominance reported in many past clinical surveys may be peculiar to late disease and reflect care-seeking and care-utilization behaviors, rather than differences in incidence.

Aged↗
PubMed1984

Respiratory impairment in coke oven workers: relationship to work exposure and bronchial inflammation detected by sputum cytology.

Coke oven workers are at excess risk of developing lung cancer and may be at risk for chronic obstructive lung disease (COLD). We have studied 3799 male workers to assess the relationship between the two diseases. Repeated lung function and sputum cytology tests were obtained over a 3-year period. Sputum samples were assessed using standardized methods; in addition to metaplastic and neoplastic changes, we reproducibly assessed the presence and extent of acute and chronic inflammatory changes. Spirometric flow rates (FEV1) were significantly reduced in workers most exposed to coke oven emissions, particularly in those with excessive inflammatory cells and regular metaplasia in sputum. The presence of reactive bronchial epithelial cells and metaplasia were potent predictors of an abnormal FEV1/FVC. Studies like these may offer a means to investigate the relationship between COLD and lung cancer. Such changes in sputum may identify individuals at risk of developing both diseases.

Bronchi↗
PubMed1982

Definition and comparability of nosocomial infection rates.

Nosocomial infection rates are frequently calculated by dividing the number of infections acquired during a month by the number of patients discharged during that month. This method does not allow for prediction of future events or comparability between locations for statistical analysis. A more appropriate rate is the number of infections divided by patient-days spent in the hospital. This rate avoids the problems associated with the commonly used method. On the basis of the rate of infections per patient-day, it is possible to test for interhospital and intrahospital differences as well as for differences over time.

California↗
PubMed1981

Fitting a linear relationship with confidence intervals by correlation.

The study of the empirical linear relationship between two measured variables should use correlation analysis which treats the variables symmetrically, rather than linear regression which inappropriately assumes a dependent and an independent variable. An APL computer program calculates the best fitting bivariate Gaussian distribution and plots the data with the superimposed straight line relationship and the confidence interval.

Body Constitution↗
PubMed1981

Risk factors for obstructive lung disease.

To assess the role of various risk factors in the pathogenesis of chronic obstructive lung disease (COLD), 163 men and women were followed for approximately 6 yr. Subjects were either community volunteers or relatives of patients with antitrypsin deficiency (PiZ or MZ phenotype). At the onset of the study no subject was receiving medical care for COLD. Covariance analysis revealed that expiratory airflow rates declined excessively in male subjects who had the PiMZ phenotype and reported a family history of lung disease. In subjects with the combination of characteristics, loss of lung function approximated that reported in subjects who have established COLD. In several such subjects, abnormalities have progressed so that they now require treatment. Changes in lung function were less striking in the presence of only 1 or 2 of the 3 risk factors studied. These findings demonstrated that the characteristics of the population being studied can influence the outcome of an investigation. This effect may help account fo the conflicting results of previous investigations designed to assess the role of the PiMZ phenotype in the pathogenesis of COLD.

Adult↗
PubMed1977

Parent Attitude Research Instrument (PARI): clinical vs. statistical inferences in understanding abusive mothers.

Attitudes toward child rearing and early experiences in childhood traditionally have been regarded as psychodynamic factors that influence adult behavior. The present study assessed the capacity of the Parent Attitude Research Instrument (PARI) to differentiate between court-identified abusive mothers and a control sample of nonabusive, well-baby clinic mothers of comparable socioeconomic status. While univariate t-tests showed statistical significance for 3 of the 23 PARI scales, more sophisticated and appropriate multivariate tests (Discriminant Function Analysis) demonstrated that the PARI correctly classified the experimental and control Ss only 65% of the time. It appears that the PARI alone should not be used to identify potentially abusive mothers. Even more important, the results caution and alert non-statistically informed clinicians and researchers to the pitfall of over-interpreting clinical data that are based on the more simple univariate tests of statistical significance.

Attitude↗
PubMed1975

A discriminant function procedure for identifying abusing parents.

From 60 abusive parents was selected a sample of 15 males and 18 females, each identified as the primary abusive parent in the home. The Minnesota Multiphasic Personality Inventory of each was subjected to a series of discriminant function analyses. Recognizing that sex is an important determinant in understanding and predicting child abuse, separate scales were derived for males, females, and sexes combined. A graph is included that allows for estimating the probability of an individual's being an abusive parent. Using these scales in conjunction with clinical interviews and medical history, there is thus an increased probability of identifying parents "at risk." Content analyses of the scale items reflect specific conflict areas for males and females that make for increased understanding of the psychology of child abuse.

Child Abuse↗