A method for calculating age-weighted death proportions for comparison purposes.
OBJECTIVE: To introduce a method for calculating age-weighted death proportions (wDP) for comparison purposes. MATERIALS AND METHODS: A methodological study using secondary data from the municipality of Sao Paulo, Brazil (1980-1994) was carried out. First, deaths are weighted in terms of years of potential life lost before the age of 100 years. Then, in order to eliminate distortion of comparisons among proportions of years of potential life lost before the age of 100 years (pYPLL-100), the denominator is set to that of a standard age distribution of deaths for all causes. Conventional death proportions (DP), pYPLL-100, and wDP were calculated. RESULTS: Populations in which deaths from a particular cause occur at older ages exhibit lower wDP than those in which deaths occur at younger ages. The sum of all cause-specific wDP equals one only when the test population has exactly the same age distribution of deaths for all causes as that of the standard population. CONCLUSION: Age-weighted death proportions improve the information given by conventional DP, and are strongly recommended for comparison purposes. (+info)
A review of statistical methods for estimating the risk of vertical human immunodeficiency virus transmission.
BACKGROUND: Estimation of the risk of vertical transmission of human immunodeficiency virus (HIV) has been complicated by the lack of a reliable diagnostic test for paediatric HIV infection. METHODS: A literature search was conducted to identify all statistical methods that have been used to estimate HIV vertical transmission risk. Although the focus of this article is the analysis of birth cohort studies, ad hoc studies are also reviewed. CONCLUSIONS: The standard method for estimating HIV vertical transmission risk is biased and inefficient. Various alternative analytical approaches have been proposed but all involve simplifying assumptions and some are difficult to implement. However, early diagnosis/exclusion of infection is now possible because of improvements in polymerase chain reaction technology and complex estimation methods should no longer be required. The best way to analyse studies conducted in breastfeeding populations is still unclear and deserves attention in view of the many intervention studies being planned or conducted in developing countries. (+info)
Statistical inference by confidence intervals: issues of interpretation and utilization.
This article examines the role of the confidence interval (CI) in statistical inference and its advantages over conventional hypothesis testing, particularly when data are applied in the context of clinical practice. A CI provides a range of population values with which a sample statistic is consistent at a given level of confidence (usually 95%). Conventional hypothesis testing serves to either reject or retain a null hypothesis. A CI, while also functioning as a hypothesis test, provides additional information on the variability of an observed sample statistic (ie, its precision) and on its probable relationship to the value of this statistic in the population from which the sample was drawn (ie, its accuracy). Thus, the CI focuses attention on the magnitude and the probability of a treatment or other effect. It thereby assists in determining the clinical usefulness and importance of, as well as the statistical significance of, findings. The CI is appropriate for both parametric and nonparametric analyses and for both individual studies and aggregated data in meta-analyses. It is recommended that, when inferential statistical analysis is performed, CIs should accompany point estimates and conventional hypothesis tests wherever possible. (+info)
Incidence and duration of hospitalizations among persons with AIDS: an event history approach.
OBJECTIVE: To analyze hospitalization patterns of persons with AIDS (PWAs) in a multi-state/multi-episode continuous time duration framework. DATA SOURCES: PWAs on Medicaid identified through a match between the state's AIDS Registry and Medicaid eligibility files; hospital admission and discharge dates identified through Medicaid claims. STUDY DESIGN: Using a Weibull event history framework, we model the hazard of transition between hospitalized and community spells, incorporating the competing risk of death in each of these states. Simulations are used to translate these parameters into readily interpretable estimates of length of stay, the probability that a hospitalization will end in death, and the probability that a nonhospitalized person will be hospitalized within 90 days. PRINCIPAL FINDINGS: In multivariate analyses, participation in a Medicaid waiver program offering case management and home care was associated with hospital stays 1.3 days shorter than for nonparticipants. African American race and Hispanic ethnicity were associated with hospital stays 1.2 days and 1.0 day longer than for non-Hispanic whites; African Americans also experienced more frequent hospital admissions. Residents of the high-HIV-prevalence area of the state had more frequent admissions and stays two days longer than those residing elsewhere in the state. Older PWAs experienced less frequent hospital admissions but longer stays, with hospitalizations of 55-year-olds lasting 8.25 days longer than those of 25-year-olds. CONCLUSIONS: Much socioeconomic and geographic variability exists both in the incidence and in the duration of hospitalization among persons with AIDS in New Jersey. Event history analysis provides a useful statistical framework for analysis of these variations, deals appropriately with data in which duration of observation varies from individual to individual, and permits the competing risk of death to be incorporated into the model. Transition models of this type have broad applicability in modeling the risk and duration of hospitalization in chronic illnesses. (+info)
Quantitative study of the variability of hepatic iron concentrations.
BACKGROUND: The hepatic iron concentration (HIC) is widely used in clinical practice and in research; however, data on the variability of HIC among biopsy sites are limited. One aim of the present study was to determine the variability of HIC within both healthy and cirrhotic livers. METHODS: Using colorimetric methods, we determined HIC in multiple large (microtome) and small (biopsy-sized) paraffin-embedded samples in 11 resected livers with end-stage cirrhosis. HIC was also measured in multiple fresh samples taken within 5 mm of each other ("local" samples) and taken at sites 3-5 cm apart ("remote" samples) from six livers with end-stage cirrhosis and two healthy autopsy livers. RESULTS: The within-organ SD of HIC was 13-1553 microg/g (CV, 3.6-55%) for microtome samples and 60-2851 microg/g (CV, 15-73%) for biopsy-sized samples. High variability of HIC was associated with mild to moderate iron overload, because the HIC SD increased with increasing mean HIC (P <0.002). Livers with mean HIC >1000 microg/g exhibited significant biological variability in HIC between sites separated by 3-5 cm (remote sites; P <0.05). The SD was larger for biopsy-sized samples than for microtome samples (P = 0.02). CONCLUSION: Ideally, multiple hepatic sites would be sampled to obtain a representative mean HIC. (+info)
A simulation study of confounding in generalized linear models for air pollution epidemiology.
Confounding between the model covariates and causal variables (which may or may not be included as model covariates) is a well-known problem in regression models used in air pollution epidemiology. This problem is usually acknowledged but hardly ever investigated, especially in the context of generalized linear models. Using synthetic data sets, the present study shows how model overfit, underfit, and misfit in the presence of correlated causal variables in a Poisson regression model affect the estimated coefficients of the covariates and their confidence levels. The study also shows how this effect changes with the ranges of the covariates and the sample size. There is qualitative agreement between these study results and the corresponding expressions in the large-sample limit for the ordinary linear models. Confounding of covariates in an overfitted model (with covariates encompassing more than just the causal variables) does not bias the estimated coefficients but reduces their significance. The effect of model underfit (with some causal variables excluded as covariates) or misfit (with covariates encompassing only noncausal variables), on the other hand, leads to not only erroneous estimated coefficients, but a misguided confidence, represented by large t-values, that the estimated coefficients are significant. The results of this study indicate that models which use only one or two air quality variables, such as particulate matter [less than and equal to] 10 microm and sulfur dioxide, are probably unreliable, and that models containing several correlated and toxic or potentially toxic air quality variables should also be investigated in order to minimize the situation of model underfit or misfit. (+info)
Wavelet transform to quantify heart rate variability and to assess its instantaneous changes.
Heart rate variability is a recognized parameter for assessing autonomous nervous system activity. Fourier transform, the most commonly used method to analyze variability, does not offer an easy assessment of its dynamics because of limitations inherent in its stationary hypothesis. Conversely, wavelet transform allows analysis of nonstationary signals. We compared the respective yields of Fourier and wavelet transforms in analyzing heart rate variability during dynamic changes in autonomous nervous system balance induced by atropine and propranolol. Fourier and wavelet transforms were applied to sequences of heart rate intervals in six subjects receiving increasing doses of atropine and propranolol. At the lowest doses of atropine administered, heart rate variability increased, followed by a progressive decrease with higher doses. With the first dose of propranolol, there was a significant increase in heart rate variability, which progressively disappeared after the last dose. Wavelet transform gave significantly better quantitative analysis of heart rate variability than did Fourier transform during autonomous nervous system adaptations induced by both agents and provided novel temporally localized information. (+info)
Excess of high activity monoamine oxidase A gene promoter alleles in female patients with panic disorder.
A genetic contribution to the pathogenesis of panic disorder has been demonstrated by clinical genetic studies. Molecular genetic studies have focused on candidate genes suggested by the molecular mechanisms implied in the action of drugs utilized for therapy or in challenge tests. One class of drugs effective in the treatment of panic disorder is represented by monoamine oxidase A inhibitors. Therefore, the monoamine oxidase A gene on chromosome X is a prime candidate gene. In the present study we investigated a novel repeat polymorphism in the promoter of the monoamine oxidase A gene for association with panic disorder in two independent samples (German sample, n = 80; Italian sample, n = 129). Two alleles (3 and 4 repeats) were most common and constituted >97% of the observed alleles. Functional characterization in a luciferase assay demonstrated that the longer alleles (3a, 4 and 5) were more active than allele 3. Among females of both the German and the Italian samples of panic disorder patients (combined, n = 209) the longer alleles (3a, 4 and 5) were significantly more frequent than among females of the corresponding control samples (combined, n = 190, chi2 = 10.27, df = 1, P = 0.001). Together with the observation that inhibition of monoamine oxidase A is clinically effective in the treatment of panic disorder these findings suggest that increased monoamine oxidase A activity is a risk factor for panic disorder in female patients. (+info)