The interpretation of scholars' interpretations of confidence intervals: criticism, replication, and extension of Hoekstra et al. (2014)

Hoekstra et al. (Psychonomic Bulletin & Review, 2014, 21:1157–1164) surveyed the interpretation of confidence intervals (CIs) by first-year students, master students, and researchers with six items expressing misinterpretations of CIs. They asked respondents to answer all items, computed the number of items endorsed, and concluded that misinterpretation of CIs is robust across groups. Their design may have produced this outcome artifactually for reasons that we describe. This paper discusses first the two interpretations of CIs and, hence, why misinterpretation cannot be inferred from endorsement of some of the items. Next, a re-analysis of Hoekstra et al.’s data reveals some puzzling differences between first-year and master students that demand further investigation. For that purpose, we designed a replication study with an extended questionnaire including two additional items that express correct interpretations of CIs (to compare endorsement of correct vs. nominally incorrect interpretations) and we asked master students to indicate which items they would have omitted had they had the option (to distinguish deliberate from uninformed endorsement caused by the forced-response format). Results showed that incognizant first-year students endorsed correct and nominally incorrect items identically, revealing that the two item types are not differentially attractive superficially; in contrast, master students were distinctively more prone to endorsing correct items when their uninformed responses were removed, although they admitted to nescience more often that might have been expected. Implications for teaching practices are discussed.

Confidence intervals for large non- centrality parameter

We use asymptotic linearity to derive confidence intervals for large noncentrality parameters. These results enable us to measure relevance of effects and interactions in multifactors models when we get highly statistically significant the values of F tests statistics. We show how to use our approach by considering two sets of data as application examples.

Rock fracture mean trace length estimation and confidence interval calculation using maximum likelihood methods

There has been a resurgence of interest in the mean trace length estimator of Pahl for window sampling of traces. The estimator has been dealt with by Mauldon and Zhang and Einstein in recent publications. The estimator is a very useful one in that it is non-parametric. However, despite some discussion regarding the statistical distribution of the estimator, none of the recent works or the original work by Pahl provide a rigorous basis for the determination a confidence interval for the estimator or a confidence region for the estimator and the corresponding estimator of trace spatial intensity in the sampling window. This paper shows, by consideration of a simplified version of the problem but without loss of generality, that the estimator is in fact the maximum likelihood estimator (MLE) and that it can be considered essentially unbiased. As the MLE, it possesses the least variance of all estimators and confidence intervals or regions should therefore be available through application of classical ML theory. It is shown that valid confidence intervals can in fact be determined. The results of the work and the calculations of the confidence intervals are illustrated by example. (C) 2003 Elsevier Science Ltd. All rights reserved.

Intervals between response choices on a single-item measure of quality of life.

BACKGROUND: A single overall rating of quality of life (QoL) is a sensitive method that is often used in population surveys. However, the exact meaning of response choices is unclear. In particular, uneven spacing may affect the way QoL ratings should be analyzed and interpreted. This study aimed to determine the intervals between response choices to a single-item QoL assessment. METHODS: A secondary analysis was conducted on data from the Lc65+ cohort study and two additional, population-based, stratified random samples of older people (N = 5,300). Overall QoL was rated as excellent, very good, good, fair or poor. A QoL score (range 0-100) was derived from participants' answers to a 28-item QoL assessment tool. A transformed QoL score ranging from 1 (poor) to 5 (excellent) was calculated. The same procedure was repeated to compute seven domain-specific QoL subscores (Feeling of safety; Health and mobility; Autonomy; Close entourage; Material resources; Esteem and recognition; Social and cultural life). RESULTS: Mean (95 % confidence intervals) QoL scores were 96.23 (95.81-96.65) for excellent, 93.09 (92.74-93.45) for very good, 81.45 (80.63-82.27) for good, 65.44 (62.67-68.20) for fair and 54.52 (45.31-63.73) for poor overall QoL, corresponding to transformed QoL scores of respectively 5.00, 4.70, 3.58, 2.05, and 1.00. Ordinality of the categories excellent to poor was preserved in all seven QoL subscores. CONCLUSIONS: The excellent-to-poor rating scale provides an ordinal measure of overall QoL. The intervals between response choices are unequal, but an interval scale can be obtained after adequate recoding of excellent, very good, good, fair and poor.

Point estimates and confidence regions for sequential trials involving selection

A number of authors have proposed clinical trial designs involving the comparison of several experimental treatments with a control treatment in two or more stages. At the end of the first stage, the most promising experimental treatment is selected, and all other experimental treatments are dropped from the trial. Provided it is good enough, the selected experimental treatment is then compared with the control treatment in one or more subsequent stages. The analysis of data from such a trial is problematic because of the treatment selection and the possibility of stopping at interim analyses. These aspects lead to bias in the maximum-likelihood estimate of the advantage of the selected experimental treatment over the control and to inaccurate coverage for the associated confidence interval. In this paper, we evaluate the bias of the maximum-likelihood estimate and propose a bias-adjusted estimate. We also propose an approach to the construction of a confidence region for the vector of advantages of the experimental treatments over the control based on an ordering of the sample space. These regions are shown to have accurate coverage, although they are also shown to be necessarily unbounded. Confidence intervals for the advantage of the selected treatment are obtained from the confidence regions and are shown to have more accurate coverage than the standard confidence interval based upon the maximum-likelihood estimate and its asymptotic standard error.

Statistical evaluation of time-dependent metabolite concentrations: estimation of post-mortem intervals based on in situ 1H-MRS of the brain

Knowledge of the time interval from death (post-mortem interval, PMI) has an enormous legal, criminological and psychological impact. Aiming to find an objective method for the determination of PMIs in forensic medicine, 1H-MR spectroscopy (1H-MRS) was used in a sheep head model to follow changes in brain metabolite concentrations after death. Following the characterization of newly observed metabolites (Ith et al., Magn. Reson. Med. 2002; 5: 915-920), the full set of acquired spectra was analyzed statistically to provide a quantitative estimation of PMIs with their respective confidence limits. In a first step, analytical mathematical functions are proposed to describe the time courses of 10 metabolites in the decomposing brain up to 3 weeks post-mortem. Subsequently, the inverted functions are used to predict PMIs based on the measured metabolite concentrations. Individual PMIs calculated from five different metabolites are then pooled, being weighted by their inverse variances. The predicted PMIs from all individual examinations in the sheep model are compared with known true times. In addition, four human cases with forensically estimated PMIs are compared with predictions based on single in situ MRS measurements. Interpretation of the individual sheep examinations gave a good correlation up to 250 h post-mortem, demonstrating that the predicted PMIs are consistent with the data used to generate the model. Comparison of the estimated PMIs with the forensically determined PMIs in the four human cases shows an adequate correlation. Current PMI estimations based on forensic methods typically suffer from uncertainties in the order of days to weeks without mathematically defined confidence information. In turn, a single 1H-MRS measurement of brain tissue in situ results in PMIs with defined and favorable confidence intervals in the range of hours, thus offering a quantitative and objective method for the determination of PMIs.

DISTRIBUTION FUNCTIONS, MEAN SQUARED ERRORS, AND CONFIDENCE LIMITS FOR RIDGE REGRESSION ESTIMATORS

A large number of ridge regression estimators have been proposed and used with little knowledge of their true distributions. Because of this lack of knowledge, these estimators cannot be used to test hypotheses or to form confidence intervals.^ This paper presents a basic technique for deriving the exact distribution functions for a class of generalized ridge estimators. The technique is applied to five prominent generalized ridge estimators. Graphs of the resulting distribution functions are presented. The actual behavior of these estimators is found to be considerably different than the behavior which is generally assumed for ridge estimators.^ This paper also uses the derived distributions to examine the mean squared error properties of the estimators. A technique for developing confidence intervals based on the generalized ridge estimators is also presented. ^

Birth-to-pregnancy intervals and adverse perinatal outcomes among African-born black women in Washington State.

Thesis (Master's)--University of Washington, 2016-06

Point-wise confidence interval estimation by neural networks: A comparative study based on automotive engine calibration.

In developing neural network techniques for real world applications it is still very rare to see estimates of confidence placed on the neural network predictions. This is a major deficiency, especially in safety-critical systems. In this paper we explore three distinct methods of producing point-wise confidence intervals using neural networks. We compare and contrast Bayesian, Gaussian Process and Predictive error bars evaluated on real data. The problem domain is concerned with the calibration of a real automotive engine management system for both air-fuel ratio determination and on-line ignition timing. This problem requires real-time control and is a good candidate for exploring the use of confidence predictions due to its safety-critical nature.

[food Insecurity In Brazilian Families With Children Under Five Years Of Age].

This article analyzes food insecurity and hunger in Brazilian families with children under five years of age. This was a nationally representative cross-sectional study using data from the National Demographic and Health Survey on Women and Children (PNDS-2006), in which the outcome variable was moderate to severe food insecurity, measured by the Brazilian Food Insecurity Scale (EBIA). Prevalence estimates and prevalence ratios were generated with 95% confidence intervals. The results showed a high prevalence of moderate to severe food insecurity, concentrated in the North and Northeast regions (30.7%), in economic classes D and E (34%), and in beneficiaries of conditional cash transfer programs (36.5%). Multivariate analysis showed that the socioeconomic relative risks (beneficiaries of conditional cash transfers), regional relative risks (North and Northeast regions), and economic relative risks (classes D and E) were 1.8, 2.0 and 2.4, respectively. Aggregation of the three risks showed 48% of families with moderate to severe food insecurity, meaning that adults and children were going hungry during the three months preceding the survey.

Self-reported Diabetes In Older People: Comparison Of Prevalences And Control Measures.

The objective of this study was to analyze the prevalence of diabetes in older people and the adopted control measures. Data regarding older diabetic individuals who participated in the Health Surveys conducted in the Municipality of Sao Paulo, SP, ISA-Capital, in 2003 and 2008, which were cross-sectional studies, were analyzed. Prevalences and confidence intervals were compared between 2003 and 2008, according to sociodemographic variables. The combination of the databases was performed when the confidence intervals overlapped. The Chi-square (level of significance of 5%) and the Pearson's Chi-square (Rao-Scott) tests were performed. The variables without overlap between the confidence intervals were not tested. The age of the older adults was 60-69 years. The majority were women, Caucasian, with an income of between > 0.5 and 2.5 times the minimum salary and low levels of schooling. The prevalence of diabetes was 17.6% (95%CI 14.9;20.6) in 2003 and 20.1% (95%CI 17.3;23.1) in 2008, which indicates a growth over this period (p at the limit of significance). The most prevalent measure adopted by the older adults to control diabetes was hypoglycemic agents, followed by diet. Physical activity was not frequent, despite the significant differences observed between 2003 and 2008 results. The use of public health services to control diabetes was significantly higher in older individuals with lower income and lower levels of education. Diabetes is a complex and challenging disease for patients and the health systems. Measures that encourage health promotion practices are necessary because they presented a smaller proportion than the use of hypoglycemic agents. Public health policies should be implemented, and aimed mainly at older individuals with low income and schooling levels. These changes are essential to improve the health condition of older diabetic patients.

Usefulness Of Vaginal Cytology Tests In Women With Previous Hysterectomy For Benign Diseases: Assessment Of 53,891 Tests.

To assess the value of vaginal screening cytology after hysterectomy for benign disease. This cross-sectional study used cytology audit data from 2,512,039 screening tests in the metropolitan region of Campinas from 2000 to 2012; the object was to compare the prevalence of abnormal tests in women who had undergone a hysterectomy for benign diseases (n=53,891) to that of women who had had no hysterectomy. Prevalence ratios (95% confidence intervals, 95% CI) were determined, and chi-square analysis, modified by the Cochrane-Armitage test for trend, was used to investigate the effects of age. The prevalence of atypical squamous cells (ASC), low-grade squamous intraepithelial lesion (LSIL), and high-grade squamous intraepithelial lesion or squamous-cell carcinoma (HSIL/SCC) was 0.13%, 0.04% and 0.03%, respectively, in women who had undergone hysterectomy, and 0.93%, 0.51% and 0.26% in women who had not undergone hysterectomy. The prevalence ratios for ASC, LSIL and HSIL/SCC were 0.14 (0.11-0.17), 0.08 (0.06-0.13) and 0.13 (0.08-0.20), respectively, in women with a hysterectomy versus those without. For HSIL/SCC, the prevalence ratios were 0.09 and 0.29, respectively, for women <50 or ≥50years. The prevalence rates in women with a previous hysterectomy showed no significant variation with age. The prevalence rates of ASC, LSIL and HSIL/SCC were significantly lower in women with a previous hysterectomy for benign disease compared with those observed in women with an intact uterine cervix. This study reinforces the view that there is no evidence that cytological screening is beneficial for women who have had a hysterectomy for benign disease.

Contribution Of Antepartum And Intrapartum Hemorrhage To The Burden Of Maternal Near Miss And Death In A National Surveillance Study.

To evaluate the occurrence of severe obstetric complications associated with antepartum and intrapartum hemorrhage among women from the Brazilian Network for Surveillance of Severe Maternal Morbidity. Multicenter cross-sectional study. Twenty-seven obstetric referral units in Brazil between July 2009 and June 2010. A total of 9555 women categorized as having obstetric complications. The occurrence of potentially life-threatening conditions, maternal near miss and maternal deaths associated with antepartum and intrapartum hemorrhage was evaluated. Sociodemographic and obstetric characteristics and the use of criteria for management of severe bleeding were also assessed in these women. The prevalence ratios with their respective 95% confidence intervals adjusted for the cluster effect of the design, and multiple logistic regression analysis were performed to identify factors independently associated with the occurrence of severe maternal outcome. Antepartum and intrapartum hemorrhage occurred in only 8% (767) of women experiencing any type of obstetric complication. However, it was responsible for 18.2% (140) of maternal near miss and 10% (14) of maternal death cases. On multivariate analysis, maternal age and previous cesarean section were shown to be independently associated with an increased risk of severe maternal outcome (near miss or death). Severe maternal outcome due to antepartum and intrapartum hemorrhage was highly prevalent among Brazilian women. Certain risk factors, maternal age and previous cesarean delivery in particular, were associated with the occurrence of bleeding.