Exact Binomial Confidence Intervals Research Articles

Phase II Study of Weekly Docetaxel Alone or in Combination with Trastuzumab in Patients with Metastatic Breast Cancer

This study was designed to determine the efficacy and toxicity of weekly docetaxel in metastatic breast cancer when given alone (for HER2/ neu—negative disease) or with trastuzumab (for HER2/ neu—overexpressing disease). Patients with metastatic breast carcinoma received docetaxel given on 2 different schedules (group 1A, 33 mg/m 2 weekly [n = 21]; group 1B, 40 mg/m 2 weekly for 3 weeks with 1 week off [n = 14]). Patients with HER2/ neu—overexpressing disease also received trastuzumab 4 mg/kg on day 1, then 2 mg/kg on days 8 and 15 of each 28-day cycle (group 2). Fifty-two patients were treated with docetaxel alone (group 1A/B, n = 35) or in combination with trastuzumab (group 2, n = 17). Prior taxane therapy given every 3 weeks had been used for metastatic disease in 19 of 35 patients (54%) in group 1A/B and in 2 of 17 patients (12%) in group 2. The mean delivered dose intensity of docetaxel was 29 mg/m 2 per week. Partial response occurred in 7 of 35 patients (21%; 95% exact binomial confidence interval [CI], 9%-38%) treated with docetaxel alone, including 3 of 19 taxane-pretreated patients (16%) and 4 of 16 taxane-naive patients (25%). Partial response occurred in 10 of 17 patients (59%; 95% CI, 34%-82%) treated with docetaxel/trastuzumab. The most common grade 3/4 toxicities, occurring in = 10% of patients, included neutropenia (21%), pulmonary toxicity (12%), and hyperglycemia (10%). The median times to disease progression were 4.5 months (95% CI, 2.5- 6.5 months) in the docetaxel group and 8.5 months (95% CI, 4.5-12.5 months) in the docetaxel/trastuzumab group. Weekly docetaxel/trastuzumab is an effective regimen for patients with HER2/ neu—overexpressing metastatic breast cancer. Weekly docetaxel may be effective in as many as 20% of patients who had progressive disease after treatment with taxanes given every 3 weeks.

Sex ratio in relation to fathers' occupations.

OBJECTIVE: To investigate whether the sex ratio of children varies between fathers of different occupations. METHODS: The sex ratio (the ratio of the number of boys to the number of...

Accurate confidence intervals for measures of test performance

The use of confidence intervals to estimate population parameters is briefly reviewed. Exact binomial confidence intervals can be calculated through the use of tables or statistical software packages. As an alternative, a microcomputer program to calculate sensitivity and specificity, point estimates and binomial confidence intervals for false-negative and -positive rate, positive and negative predictive power, prevalence of cases and non-cases, correct classification rate, and misclassification rate has also been developed. Characteristics of the computer program, ‘AccuCon’, which is available from the authors, are described.

Postoperative management of cesarean patients: The effect of immediate feeding on the incidence of ileus

To evaluate the effect of immediate feeding on gastrointestinal function in patients undergoing cesarean delivery. A prospective study was conducted in which patients were randomized to one of two groups, either early feeding or delayed feeding, ie, feeding according to the institution's current protocol. Questionnaires were filled out by the subjects on the day of discharge. Fisher exact test was used to compare the two groups with respect to the type of anesthetic used and to compare the incidence of gastrointestinal symptoms. A one-sided exact binomial confidence interval was used to determine the upper bound of the likelihood of paralytic ileus. Logistic regression analysis was used to evaluate the presence of ileus symptoms when controlling for the type of anesthetic used. There were no significant differences between the control and study groups. There was no significant difference in the number of gastrointestinal symptoms between the two groups. The incidence of postoperative paralytic ileus was zero in both the study and control groups. Routine early feeding of subjects undergoing cesarean delivery can be implemented without an increase in gastrointestinal symptoms or paralytic ileus.

Exact power calculations when the dependent variable is a single proportion and the number of events is small

This paper presents methods for calculating the exact power to reject the null hypothesis that an observed event rate is significantly lower than a clinically relevant alternative event rate or that the confidence interval is less than a specified range when the hypothesis will be tested using exact binomial confidence intervals. SAS programs that perform the calculations are presented and the results are compared with power calculations using the normal approximation. The method can be extended to studies involving paired comparisons but, in that case, it does not appear to provide a significant advantage over normal approximation methods.

Confidence intervals for the triangle test can give reassurance that products are similar

One of the major advantages of the triangle test to set against its low statistical power is its potential for revealing discriminable sensory differences when the nature of the difference is unknown. That makes it an attractive tool for seeking assurance that there is no sensory difference between samples (after a process change, for instance). Mere absence of significant difference is completely inadequate to give that reassurance and power analysis is much better. However, power analysis requires three somewhat arbitrary parameter values to be selected in advance. An alternative approach based on exact binomial confidence intervals is described which needs only a single parameter, comparable to the alpha level in a test of significance, to be specified. It is shown that the amount of data usually envisaged for seeking reassurance about lack of difference is much too small to do the task adequately.

Continuity and Change Within an HIV Epidemic

To examine trends in acquired immunodeficiency syndrome (AIDS) risk behavior and human immunodeficiency virus (HIV) seroprevalence among injecting drug users (IDUs) in New York City from 1984 through 1992. Comparisons were made between two surveys of IDUs at the same hospital-based New York City drug abuse detoxification program: 141 IDUs in 1984 and 974 IDUs in 1990 through 1992. National Death Registry, New York City Health Department, and drug treatment program records were also used. Persons attending detoxification program randomly selected for participation. Eligibility was based on injection within previous 2 months; 99% acceptance rates were obtained. Participants in the 1984 and 1990 through 1992 surveys were 66% and 79% men, 21% and 19% white, 33% and 34% African American, and 45% and 46% Latin American, respectively. Community-based AIDS prevention programs, including underground syringe exchanges. Acquired immunodeficiency syndrome risk behaviors; HIV serostatus; CD4+ cell counts; death rates among 1984 subjects; and injection and intranasal routes of drug administration. The HIV seroprevalence remained stable at slightly more than 50%. Mean CD4+ cell counts declined from 0.716 x 10(9)/L (716/microL) to 0.575 x 10(9)/L (P < .009). Annual death rate among 1984 subjects was 3%, with a significantly higher rate among HIV-seropositive subjects (relative risk, 2.57; 95% exact binomial confidence interval, 1.12 to 6.61). Large-scale declines were observed in AIDS risk behaviors, eg, use of potentially contaminated syringes declined from 51% to 7% of injections (P < .001). Recent additional risk reduction was associated with use of the underground syringe exchanges. Intranasal heroin use was the primary route of drug administration for 46% of heroin admissions to New York City drug treatment programs. The HIV seroprevalence has remained stable among this population of New York City IDUs for almost a decade. Continuation of current trends should lead to further reduction in HIV transmission, although reversal of the trend to intranasal use could lead to substantially increased transmission.

Prevalence of drug use among pregnant women in a rural area.

To determine the prevalence of alcohol and illegal drug use among pregnant women in a rural midwestern area. Descriptive, prospective study. Private tertiary medical center in a rural midwestern area. A nonprobability convenience sample of 202 women enrolling for prenatal care. Hypothesized that the prevalence of alcohol and illegal drug use by pregnant women in a rural midwestern area may be similar to the prevalence in urban areas. The prevalence for perinatal drug use among the sample was 3.9%, with a 95% exact binomial confidence interval of 1.7% to 7.7%. The 3.9% prevalence level is significantly lower than the 11% prevalence levels projected by urban studies (p = .0006). Additional studies need to be conducted on rural populations, however, with periodic testing performed throughout pregnancy. Further studies should examine, through self-reporting, prevalence rates of tobacco and alcohol use during pregnancy.

A Rapidly Converging Algorithm for Exact Binomial Confidence Intervals About the Relative Risk in Follow-up Studies with Stratified Incidence-Density Data

A rapidly converging algorithm is given to calculate exact confidence intervals about the adjusted relative risk in follow-up studies with stratified incidence-density data. The network approach that Mehta developed for tables with person-count numerators and denominators is adapted to tables with person-count numerators and person-time denominators. This algorithm updates an earlier program by Guess et al, yielding the same quantities but with running times that are between ten and a hundred times faster. Applications to Poisson regression are discussed.

Epidemiologic programs for computers and calculators. Exact binomial confidence intervals for the relative risk in follow-up studies with sparsely stratified incidence density data.

The authors present a computer program for hypothesis testing and calculation of exact binomial confidence intervals for the adjusted relative risk in follow-up studies involving multiple strata with incidence density (person-time) denominators and small or zero person-count numerators. The program is an extension to multiple tables of a single-table method by Rothman and Boice (NIH publication no. 79-1649, Washington, DC: US GPO, 1979) and represents a counterpart for person-time denominators to the program of Thomas (Comput Biomed Res 1975;8:423-46) for exact analysis of multiple tables with person-count denominators. Comparisons with asymptotic analyses of real and simulated data are given. Copies of the program are available from the authors on request.