Selection bias and the cross-validation of regression models for prediction

Strategies are compared for the development of a linear regression model with stochastic (multivariate normal) regressor variables and the subsequent assessment of its predictive ability. Bias and mean squared error of four estimators of predictive performance are evaluated in simulated samples of 32 population correlation matrices. Models including all of the available predictors are compared with those obtained using selected subsets. The subset selection procedures investigated include two stopping rules, C$\sb{\rm p}$ and S$\sb{\rm p}$, each combined with an 'all possible subsets' or 'forward selection' of variables. The estimators of performance utilized include parametric (MSEP$\sb{\rm m}$) and non-parametric (PRESS) assessments in the entire sample, and two data splitting estimates restricted to a random or balanced (Snee's DUPLEX) 'validation' half sample. The simulations were performed as a designed experiment, with population correlation matrices representing a broad range of data structures.^ The techniques examined for subset selection do not generally result in improved predictions relative to the full model. Approaches using 'forward selection' result in slightly smaller prediction errors and less biased estimators of predictive accuracy than 'all possible subsets' approaches but no differences are detected between the performances of C$\sb{\rm p}$ and S$\sb{\rm p}$. In every case, prediction errors of models obtained by subset selection in either of the half splits exceed those obtained using all predictors and the entire sample.^ Only the random split estimator is conditionally (on $\\beta$) unbiased, however MSEP$\sb{\rm m}$ is unbiased on average and PRESS is nearly so in unselected (fixed form) models. When subset selection techniques are used, MSEP$\sb{\rm m}$ and PRESS always underestimate prediction errors, by as much as 27 percent (on average) in small samples. Despite their bias, the mean squared errors (MSE) of these estimators are at least 30 percent less than that of the unbiased random split estimator. The DUPLEX split estimator suffers from large MSE as well as bias, and seems of little value within the context of stochastic regressor variables.^ To maximize predictive accuracy while retaining a reliable estimate of that accuracy, it is recommended that the entire sample be used for model development, and a leave-one-out statistic (e.g. PRESS) be used for assessment. ^

Information bias and lifetime mortality risks of radiation-induced cancer

Additive and multiplicative models of relative risk were used to measure the effect of cancer misclassification and DS86 random errors on lifetime risk projections in the Life Span Study (LSS) of Hiroshima and Nagasaki atomic bomb survivors. The true number of cancer deaths in each stratum of the cancer mortality cross-classification was estimated using sufficient statistics from the EM algorithm. Average survivor doses in the strata were corrected for DS86 random error ($\sigma$ = 0.45) by use of reduction factors. Poisson regression was used to model the corrected and uncorrected mortality rates with covariates for age at-time-of-bombing, age at-time-of-death and gender. Excess risks were in good agreement with risks in RERF Report 11 (Part 2) and the BEIR-V report. Bias due to DS86 random error typically ranged from $-$15% to $-$30% for both sexes, and all sites and models. The total bias, including diagnostic misclassification, of excess risk of nonleukemia for exposure to 1 Sv from age 18 to 65 under the non-constant relative projection model was $-$37.1% for males and $-$23.3% for females. Total excess risks of leukemia under the relative projection model were biased $-$27.1% for males and $-$43.4% for females. Thus, nonleukemia risks for 1 Sv from ages 18 to 85 (DRREF = 2) increased from 1.91%/Sv to 2.68%/Sv among males and from 3.23%/Sv to 4.02%/Sv among females. Leukemia excess risks increased from 0.87%/Sv to 1.10%/Sv among males and from 0.73%/Sv to 1.04%/Sv among females. Bias was dependent on the gender, site, correction method, exposure profile and projection model considered. Future studies that use LSS data for U.S. nuclear workers may be downwardly biased if lifetime risk projections are not adjusted for random and systematic errors. (Supported by U.S. NRC Grant NRC-04-091-02.) ^

POPULATION ASSESSMENTS OF INFECTION WITH SCHISTOSOMA MANSONI: EFFECTS OF BIAS CAUSED BY THE RELATIVE SENSITIVITY OF DIAGNOSTIC TECHNIQUES (PUERTO RICO)

This study establishes the extent and relevance of bias of population estimates of prevalence, incidence, and intensity of infection with Schistosoma mansoni caused by the relative sensitivity of stool examination techniques. The population studied was Parcelas de Boqueron in Las Piedras, Puerto Rico, where the Centers for Disease Control, had undertaken a prospective community-based study of infection with S. mansoni in 1972. During each January of the succeeding years stool specimens from this population were processed according to the modified Ritchie concentration (MRC) technique. During January 1979 additional stool specimens were collected from 30 individuals selected on the basis of their mean S. mansoni egg output during previous years. Each specimen was divided into ten 1-gm aliquots and three 42-mg aliquots. The relationship of egg counts obtained with the Kato-Katz (KK) thick smear technique as a function of the mean of ten counts obtained with the MRC technique was established by means of regression analysis. Additionally, the effect of fecal sample size and egg excretion level on technique sensitivity was evaluated during a blind assessment of single stool specimen samples, using both examination methods, from 125 residents with documented S. mansoni infections. The regression equation was: Ln KK = 2.3324 + 0.6319 Ln MRC, and the coefficient of determination (r('2)) was 0.73. The regression equation was then utilized to correct the term "m" for sample size in the expression P ((GREATERTHEQ) 1 egg) = 1 - e('-ms), which estimates the probability P of finding at least one egg as a function of the mean S. mansoni egg output "m" of the population and the effective stool sample size "s" utilized by the coprological technique. This algorithm closely approximated the observed sensitivity of the KK and MRC tests when these were utilized to blindly screen a population of known parasitologic status for infection with S. mansoni. In addition, the algorithm was utilized to adjust the apparent prevalence of infection for the degree of functional sensitivity exhibited by the diagnostic test. This permitted the estimation of true prevalence of infection and, hence, a means for correcting estimates of incidence of infection. ^

Practice and attitude differences in physician cigarette use: A study of prevalence, physicians' role, and smoking policy awareness in Dubai, UAE

The use of tobacco products ruins the health of millions of people around the world. On average, tobacco users die nearly seven years earlier than non-tobacco users. n1 Cigarette smoking is a particular concern in the developing countries of the Middle East and Gulf Cooperation Council (GCC) region where smoking prevalence is expected to increase. This is due to the tobacco industry's vigorous commercial and marketing activities. n3 Smoking prevalence among physicians is considered to be an effective indicator of a society's readiness to identify the smoking epidemic and its related health diseases. n4 There is a lack of detailed data on the smoking prevalence among healthcare professionals, particularly physicians, in the United Arab Emirates (UAE). This cross sectional study is the first to address smoking practices among physicians working at the Department of Health and Medical Services (DOHMS); in Dubai, UAE. ^ This study describes the cigarette smoking prevalence among DOHMS Physicians, physician attitudes towards tobacco use and tobacco bans; physician attitudes towards smoking cessation techniques (among smokers and non-smokers); and physician awareness of official anti-smoking policies. Data for the study was collected through the use of an adapted WHO standardized questionnaire, the Global Health Professionals Survey. The questionnaire was administered by the researcher to physicians (n=288) at their work place. Date was analyzed using the SPSS analytic software program. ^ Twelve percent of DOHMS physicians smoked cigarettes. Regardless of smoking status, the majority supported a tobacco ban in hospitals and public places, and a ban on tobacco advertising. There is a significant relationship between physician smoking status and discussing risks of tobacco use (p < 0.05). Non-smoking physicians reported spending more time with patients discussing hazards of smoking (p < 0.01). Non-smokers reported providing more counseling than their smoking colleagues. The majority of DOHMS physicians (63%) reported a lack of knowledge about 5As/ 5Rs. The majority of physicians also reported they are aware of hospital smoking policies that restrict smoking. Regardless of physician smoking status, DOHMS physicians are not very actively involved in smoking cessation activities. This cross sectional study is the first to address smoking programs, policies, and practices among physicians in Dubai, UAE. Findings support the need for increased physical smoking cessation training as well as the development of smoking cessation programs for tobacco control, and programs with a focus on physician participation in reducing tobacco and cigarette use among the general population.^

Mexican Americans' awareness, knowledge, and beliefs of hypertension

Cardiovascular disease (CVD) is the number one cause of death for people in Texas as well as Mexico. The progressive morbidity and mortality of CVD can be prevented initially and controlled through regular health screenings or visits to the physician where health markers such as hypertension can be detected and treated. Yet, many people go unaware of existing hypertension not only due to lack of access to health care but to their own personal beliefs, ideas, or perceived barriers that prevent them from seeking preventative health care. ^ The main purpose of this study was to evaluate whether individuals of Mexican origin, who have some form of medical coverage, posses more knowledge, more perceived severity, less perceived barriers, and greater self-efficacy in regards to hypertension than those individuals who have no medical coverage. This was done by addressing the following specific aims: 1.To evaluate the association between individuals who have health care coverage and those who do not have health care coverage in regards to their beliefs of hypertension; 2. To evaluate if there exists a variation among the respondents demographic data and their beliefs of hypertension. ^ The total number of respondents were 150; with 75 being from Cuidad Juarez, and 75 being from El Paso, Texas. The results indicated that the individuals with some form of medical coverage perceived themselves to be more susceptible to suffering a cardiac event or developing heart disease than those who had no form of medical coverage. The individuals with some form of health care coverage also found themselves having less perceived barriers than those who had no health care coverage. The level of education seemed to have some association with individuals perceiving themselves as being susceptible to experiencing a cardiac event if they do not control their hypertension. Regarding self-efficacy, or the self-reported confidence in performing certain behaviors to controlling hypertension, those individuals who perceived themselves as having no self-efficacy had a lower level of education, compared to those who did perceive themselves as possessing self-efficacy. The findings of this study indicate that beliefs regarding hypertension and medical coverage are variables that need to be investigated further for individuals in the El Paso and Cuidad Juarez region. ^

Increasing awareness of colorectal cancer screening through targeted exam room based video messages

Colorectal cancer (CRC) is the third largest cause of cancer death in the United States. While the disease burden is high, there are proven methods to screen for CRC and detect it at a stage that is amenable to cure. Patients with low health literacy have difficulty navigating the health care system and are at increased risk to not receive preventive care services such as colorectal cancer screening (CRCS). To address this need, an exam-room based video was developed to be played for patients in the privacy of the exam room, while they are waiting to be seen by their medical provider. In roughly 2 minutes, the video informs the patient about CRC and CRCS and how they can successfully complete CRCS. One of the key barriers to completing CRCS is the need to increase patients' knowledge and improve attitudes surrounding CRCS. This study examines the impact of the video on patients' knowledge and attitudes about CRC and CRCS in a medically underserved patient population in Houston, Texas. ^ Sixty-one patients presenting for routine medical care were enrolled in the study. Depending on their randomization, the patients either received routine information about CRC and CRCS or they watched the video. We found that the patients who did watch the video did have improvements in their knowledge and improved attitudes about CRC and CRCS. Future studies will be needed to examine whether the video improves the patients' completion of CRCS.^

HPV knowledge, HPV vaccine awareness and initiation among Hispanics: The role of language, information seeking, and information scanning

Background. Among Hispanics, the HPV vaccine has the potential to eliminate disparities in cervical cancer incidence and mortality but only if optimal rates of vaccination are achieved. Media can be an important information source for increasing HPV knowledge and awareness of the vaccine. Very little is known about how media use among Hispanics affects their HPV knowledge and vaccine awareness. Even less is known about what differences exist in media use and information processing among English- and Spanish-speaking Hispanics.^ Aims. Examine the relationships between three health communication variables (media exposure, HPV-specific information scanning and seeking) and three HPV outcomes (knowledge, vaccine awareness and initiation) among English- and Spanish-speaking Hispanics.^ Methods. Cross-sectional data from a survey administered to Hispanic mothers in Dallas, Texas was used for univariate and multivariate logistic regression analyses. Sample used for analysis included 288 mothers of females aged 8-22 recruited from clinics and community events. Dependent variables of interest were HPV knowledge, HPV vaccine awareness and initiation. Independent variables were media exposure, HPV-specific information scanning and seeking. Language was tested as an effect modifier on the relationship between health communication variables and HPV outcomes.^ Results. English-speaking mothers reported more media exposure, HPV-specific information scanning and seeking than Spanish-speakers. Scanning for HPV information was associated with more HPV knowledge (OR = 4.26, 95% CI = 2.41 - 7.51), vaccine awareness (OR = 10.01, 95% CI = 5.43 - 18.47) and vaccine initiation (OR = 2.54, 95% CI = 1.09 - 5.91). Seeking HPV-specific information was associated with more knowledge (OR = 2.27, 95% CI = 1.23 - 4.16), awareness (OR = 6.60, 95% CI = 2.74 - 15.91) and initiation (OR = 4.93, 95% CI = 2.64 - 9.20). Language moderated the effect of information scanning and seeking on vaccine awareness.^ Discussion. Differences in information scanning and seeking behaviors among Hispanic subgroups have the potential to lead to disparities in vaccine awareness.^ Conclusion. Findings from this study underscore health communication differences among Hispanics and emphasize the need to target Spanish language media as well as English language media aimed at Hispanics to improve knowledge and awareness.^

Left, right and interval bivariate censored data: Evaluating screening mammography in the presence of lead -time bias, length bias and over-detection

Of the large clinical trials evaluating screening mammography efficacy, none included women ages 75 and older. Recommendations on an upper age limit at which to discontinue screening are based on indirect evidence and are not consistent. Screening mammography is evaluated using observational data from the SEER-Medicare linked database. Measuring the benefit of screening mammography is difficult due to the impact of lead-time bias, length bias and over-detection. The underlying conceptual model divides the disease into two stages: pre-clinical (T0) and symptomatic (T1) breast cancer. Treating the time in these phases as a pair of dependent bivariate observations, (t0,t1), estimates are derived to describe the distribution of this random vector. To quantify the effect of screening mammography, statistical inference is made about the mammography parameters that correspond to the marginal distribution of the symptomatic phase duration (T1). This shows the hazard ratio of death from breast cancer comparing women with screen-detected tumors to those detected at their symptom onset is 0.36 (0.30, 0.42), indicating a benefit among the screen-detected cases. ^

¿De una pedagogía a una política de la Educación Corporal?

¿Qué es un quiebre epistemológico? ¿Qué implicancias tiene éste en la metodología de la investigación y la Educación Corporal? Pasar de un sesgo "pedagógico y didáctico con que se pensaba a la Educación Física" (Crisorio y otros: proyecto 11/H465) a uno de cohorte político implica interpretar las prácticas corporales por fuera del deber ser. Entonces, ¿cuáles son los sentidos y las lógicas que adquieren? ¿Cómo se entienden las prácticas corporales? ¿Qué pasa con el lugar universal, con la conciencia o el conocimiento, con el hombre? Las ideas de práctica, epistemología y política han permitido cambiar la interpretación según las investigaciones realizadas por el Grupo de Estudios en Educación Corporal. ¿Cómo son entendidas estas ideas por una Educación Corporal que supone un abordaje distinto en el uso del cuerpo? Por último, cabe preguntarse si estas ideas modifican el orden discursivo -en sentido foucaulteano- sobre la voluntad del saber y por consecuencia sobre la perspectiva metodológica

¿De una pedagogía a una política de la Educación Corporal?

¿Qué es un quiebre epistemológico? ¿Qué implicancias tiene éste en la metodología de la investigación y la Educación Corporal? Pasar de un sesgo "pedagógico y didáctico con que se pensaba a la Educación Física" (Crisorio y otros: proyecto 11/H465) a uno de cohorte político implica interpretar las prácticas corporales por fuera del deber ser. Entonces, ¿cuáles son los sentidos y las lógicas que adquieren? ¿Cómo se entienden las prácticas corporales? ¿Qué pasa con el lugar universal, con la conciencia o el conocimiento, con el hombre? Las ideas de práctica, epistemología y política han permitido cambiar la interpretación según las investigaciones realizadas por el Grupo de Estudios en Educación Corporal. ¿Cómo son entendidas estas ideas por una Educación Corporal que supone un abordaje distinto en el uso del cuerpo? Por último, cabe preguntarse si estas ideas modifican el orden discursivo -en sentido foucaulteano- sobre la voluntad del saber y por consecuencia sobre la perspectiva metodológica

¿De una pedagogía a una política de la Educación Corporal?

¿Qué es un quiebre epistemológico? ¿Qué implicancias tiene éste en la metodología de la investigación y la Educación Corporal? Pasar de un sesgo "pedagógico y didáctico con que se pensaba a la Educación Física" (Crisorio y otros: proyecto 11/H465) a uno de cohorte político implica interpretar las prácticas corporales por fuera del deber ser. Entonces, ¿cuáles son los sentidos y las lógicas que adquieren? ¿Cómo se entienden las prácticas corporales? ¿Qué pasa con el lugar universal, con la conciencia o el conocimiento, con el hombre? Las ideas de práctica, epistemología y política han permitido cambiar la interpretación según las investigaciones realizadas por el Grupo de Estudios en Educación Corporal. ¿Cómo son entendidas estas ideas por una Educación Corporal que supone un abordaje distinto en el uso del cuerpo? Por último, cabe preguntarse si estas ideas modifican el orden discursivo -en sentido foucaulteano- sobre la voluntad del saber y por consecuencia sobre la perspectiva metodológica

Operator and replicability bias in comparative taphonomic studies

The operator effect is a well-known methodological bias already quantified in some taphonomic studies. However, the replicability effect, i.e., the use of taphonomic attributes as a replicable scientific method, has not been taken into account to the present. Here, we quantified for the first time this replicability bias using different multivariate statistical techniques, testing if the operator effect is related to the replicability effect. We analyzed the results reported by 15 operators working on the same dataset. Each operator analyzed 30 biological remains (bivalve shells) from five different sites, considering the attributes fragmentation, edge rounding, corrasion, bioerosion and secondary color. The operator effect followed the same pattern reported in previous studies, characterized by a worse correspondence for those attributes having more than two levels of damage categories. However, the effect did not appear to have relation with the replicability effect, because nearly all operators found differences among sites. Despite the binary attribute bioerosion exhibited 83% of correspondence among operators it was the taphonomic attributes that showed the highest dispersion among operators (28%). Therefore, we conclude that binary attributes (despite showing a reduction of the operator effect) diminish replicability, resulting in different interpretations of concordant data. We found that a variance value of nearly 8% among operators, was enough to generate a different taphonomic interpretation, in a Q-mode cluster analysis. The results reported here showed that the statistical method employed influences the level of replicability and comparability of a study and that the availability of results may be a valid alternative to reduce bias.