Assessment of the effect on statistical power of regression model misspecification by using techniques of mathematical statistics and simulation study

Objectives. This paper seeks to assess the effect on statistical power of regression model misspecification in a variety of situations. ^ Methods and results. The effect of misspecification in regression can be approximated by evaluating the correlation between the correct specification and the misspecification of the outcome variable (Harris 2010).In this paper, three misspecified models (linear, categorical and fractional polynomial) were considered. In the first section, the mathematical method of calculating the correlation between correct and misspecified models with simple mathematical forms was derived and demonstrated. In the second section, data from the National Health and Nutrition Examination Survey (NHANES 2007-2008) were used to examine such correlations. Our study shows that comparing to linear or categorical models, the fractional polynomial models, with the higher correlations, provided a better approximation of the true relationship, which was illustrated by LOESS regression. In the third section, we present the results of simulation studies that demonstrate overall misspecification in regression can produce marked decreases in power with small sample sizes. However, the categorical model had greatest power, ranging from 0.877 to 0.936 depending on sample size and outcome variable used. The power of fractional polynomial model was close to that of linear model, which ranged from 0.69 to 0.83, and appeared to be affected by the increased degrees of freedom of this model.^ Conclusion. Correlations between alternative model specifications can be used to provide a good approximation of the effect on statistical power of misspecification when the sample size is large. When model specifications have known simple mathematical forms, such correlations can be calculated mathematically. Actual public health data from NHANES 2007-2008 were used as examples to demonstrate the situations with unknown or complex correct model specification. Simulation of power for misspecified models confirmed the results based on correlation methods but also illustrated the effect of model degrees of freedom on power.^

Understanding treatment-related symptoms, symptom management techniques, and symptom management self-efficacy in a sample of non-muscle invasive bladder cancer patients

The current literature available on bladder cancer symptom management from the perspective of the patients themselves is limited. There is also limited psychosocial research specific to bladder cancer patients and no previous studies have developed and validated measures for bladder cancer patients’ symptom management self-efficacy. The purpose of this study was to investigate non-muscle invasive bladder cancer patients’ health related quality of life through two main study objectives: (1) to describe the treatment related symptoms, reported effectiveness of symptom-management techniques, and the advice a sample of non-muscle invasive bladder cancer patients would convey to physicians and future patients; and (2) to evaluate Lepore’s symptom management self-efficacy measure on a sample of non-muscle invasive bladder cancer patients. Methods. A total of twelve (n=12) non-muscle invasive bladder cancer patients participated in an in-depth interview and a sample of 46 (n=4) non-muscle invasive bladder cancer patients participated in the symptom-management self-efficacy survey. Results. A total of five symptom categories emerged for the participants’ 59 reported symptoms. Four symptom management categories emerged out of the 71 reported techniques. A total of 62% of the participants’ treatment related symptom-management techniques were reported as effective in managing their treatment-related symptoms. Five advice categories emerged out of the in-depth interviews: service delivery; medical advice; physician-patient communication; encouragement; and no advice. An exploratory factor analysis indicated a single-factor structure for the total population and a multiple factor structure for three subgroups: all males, married males, and all married participants. Conclusion. These findings can inform physicians and patients of effective symptom-management techniques thus improving patients’ health-related quality of life. The advice these patients’ impart can improve service-delivery and patient education.^

Public service use by residents of Jackson Hinds Gardens before and after enrollment

Homelessness is associated with high use of public services such as health care and criminal justice services. Intervention designs to reverse homelessness have broadly fallen into two categories: either standard care which employs requisitely addressing the causes of homelessness, or housing first, which emphasizes provision of permanent housing without requisitely addressing the causes of homelessness. Multiple cities have recently commenced housing first interventions. Locally, Houston’s first housing first development is the Jackson Hinds Gardens project. The purpose of this study is to analyze the public service use of residents of housing first in Houston. Residents of Jackson Hinds Gardens who have been enrolled for at least 6 months were evaluated for public service use for an equal amount of time preceding and during their residence at Jackson Hinds. Resident interactions with county health services and criminal justice entities were determined by electronic database searches; these data were supplemented by life experience interview data. Service usage values pre- and post-enrollment at Jackson Hinds Gardens were compared by paired t-test analyses. We found that ER and inpatient usage decreased following enrollment in Jackson Hinds, although these reductions were not significant. In contrast, outpatient care and number of medications significantly increased following enrollment. These analyses inform on the effects of housing first in another major city, as well as informing the ethical considerations regarding housing first versus standard care. ^

Physical activity among breast and prostate cancer survivors: Barriers, facilitators and maintenance following the FRESH START trial

Research provides evidence of the positive health effects associated with regular physical activity participation in all populations. Activity may prove to be especially beneficial in those with chronic conditions such as cancer. However, the majority of cancer patients and survivors do not participate in the recommended amount of physical activity. The purpose of this dissertation was to identify factors associated with physical activity participation, describe how these factors change as result of a diet and exercise intervention, and to evaluate correlates of long term physical activity maintenance. ^ For this dissertation, I analyzed data from the FRESH START trial, a randomized, single-blind, phase II clinical trial focused on improving diet and physical activity among recently diagnosed breast and prostate cancer survivors. Analyses included both parametric and non-parametric statistical tests. Three separate studies were conducted, with sample sizes ranging from 400 to 486. ^ Common barriers to exercise, such as “no willpower,” “too busy,” and “I have pain,” were reported among breast and prostate cancer survivors; however, these barriers were not significantly associated with minutes of physical activity. Breast cancer survivors reported a greater number of total barriers to exercise as well as higher proportions reporting individual barriers, compared to prostate cancer survivors. Just less than half of participants reduced their total number of barriers to exercise from baseline to 1-year follow-up, and those who did reduce barriers reported greater increases in minutes of physical activity compared to those who reported no change in barriers to exercise. Participants in both the tailored and standardized intervention groups reported greater minutes of physical activity at 2-year follow-up compared to baseline. Overall, twelve percent of participants reached recommended levels of physical activity at both 1- and 2-year follow-up. Self-efficacy was positively associated with physical activity maintenance, and the number of total barriers to exercise was inversely associated with physical activity maintenance. ^ Results from this dissertation are novel and informative, and will help to guide future physical activity interventions among cancer survivors. Thoughtfully designed interventions may encourage greater participation in physical activity and ultimately improve overall quality of life in this population. ^

Campaign contributions to congressional candidates by the healthcare sector from 1990 to 2008

Stakeholder groups with special interests as donors to finance congressional campaigns have been a controversial issue in the United Sates. While previous studies concentrated on whether a connection existed between the campaign contributions provided by stakeholder groups and the voting behavior of congressional members, there is little evidence to show the trend of allocation of their campaign contributions to their favorite candidates during the elections. This issue has become increasingly important in the health sector since the health care reform bill was passed in early 2010.^ This study examined the long-term trend of campaign contributions offered by various top healthcare stakeholder groups to particular political parties (i.e. Democrat and Republican). The main focus of this paper was to observe and describe the financial donations provided by these healthcare stakeholder groups in the congressional election cycles from 1990 to 2008 in order to obtain an overview of their patterns of campaign contributions. Their contributing behaviors were characterized based on the campaign finance data collected by the Center for Responsive Politics (CRP). Specifically, I answered the questions: (1) to which political party did specific healthcare stakeholder groups give money and (2) what was the pattern of their campaign contributions from 1990 to 2008?^ The findings of my study revealed that the healthcare stakeholder groups had different political party preferences and partisanship orientations regarding the Democratic or Republican Party. These differences were obvious throughout the election cycles from 1990 to 2008 and their distinct patterns of financial contribution were evident across industries in the health sector as well. Among all the healthcare stakeholder groups in this study, physicians were the top contributors in the congressional election. The pharmaceutical industry was the only group where the majority of contribution funds were allocated to Republicans in every election period studied. This study found that no interest group has succeeded in electing the preferred congressional candidate by giving the majority of its financial support to the winning party in every election. Chiropractors, hospitals/nursing homes, and health services/HMOs performed better than other healthcare stakeholder groups by supporting the electoral winner 8 out of 9 election cycles.^

African American and Hispanic adolescent STI and pregnancy prevention: Whose responsibility is it, anyway?

This dissertation utilized quantitative and qualitative methods to examine the role of responsibility in the prevention of sexually transmitted infections (STIs) and pregnancy through condom use and other sexual behaviors among young adolescents. Data were analyzed across race and gender and three papers were developed. The quantitative portion used logistic regression to assess associations between personal responsibility, as well as other know correlates, and reported condom use and condom use intentions as a means of STI and pregnancy prevention among 445 inner-city, high school adolescents. Responsibility to prevent pregnancy by providing the condom was associated with condom use at last sex and consistent condom use. Responsibility to prevent acquiring a STI by using a condom was significantly associated with consistent condom use. No significant associations were found between responsibility and condom use intentions. ^ The qualitative section of the dissertation project involved conducting 28 in-depth interviews among 9th and 10th grade, African American and Hispanic students who attended a large urban school district in South Central Texas. Perceptions of responsibility for preventing STIs and unintended pregnancy, as well as for condom use, were explored. Male and female adolescents expressed joint responsibility to prevent a STI or pregnancy. Perceptions of responsibility for providing and using the condoms were mixed. Despite the indication of both partners, mostly all participants implied that females, more so than the males, had the final responsibility to prevent contracting a STI, a pregnancy, to provide a condom, and to make sure a condom was used. Participants expressed the role of parents' involvement for preventing these outcomes as well as the need for more sexual health education and access to preventative methods. ^ The last section of this dissertation involved qualitative inquiry to ascertain perceptions of reasons why adolescents engage in anal and oral (non-coital) sex. Pleasure-seeking and giving as well social influence and pressure were described as the main reasons why teenagers have non-coital sex. Other reasons included conveniences of participating in these behaviors such as ease of performing oral sex and anal sex as a convenient alternative to vaginal sex. Sexual inexperience was an indicator for why anal sex occurs. Many of the reasons involved misperceptions and adolescents who practice these sexual behaviors place themselves at-risk for contracting a STI. ^ This dissertation increased the current knowledge base about adolescent sexual responsibility and non-coital behaviors. Future studies should explore perceptions of responsibility and actual sexual activity practices among adolescents to reduce the burden of STIs and pregnancy as well as help public health professionals develop programs for adolescent populations, schools, and communities where these issues persist.^

Targeted immunization to protect infants against pertussis in the United States

Pertussis is an infectious disease caused by the bacteria Bordetella pertussis, and is associated with a serious respiratory infection, a prolonged cough, and can require hospitalization. A vaccine for adolescents and adults has been available since 2005. This paper examines one recommended immunization strategy to prevent pertussis among infants, called “cocooning.” The strategy focuses on creating immunity among adult caregivers so they serve as a protective cocoon to the newborns, who are too young to be vaccinated. This paper looks at relevant studies summarizing implementation of cocooning strategies and addresses the question – Does the research literature support the view of using cocooning as an effective strategy to prevent pertussis in infants? After exclusions, 8 studies remained for synthesis. The evidence shows that cocooning is complex strategy and the evidence is mixed when it comes to ensuring an increase in immunization of caregivers. ^

Ascertainment, meta-analysis and reporting of adverse reactions in clinical trials of antibiotics

The ascertainment and analysis of adverse reactions to investigational agents presents a significant challenge because of the infrequency of these events, their subjective nature and the low priority of safety evaluations in many clinical trials. A one year review of antibiotic trials published in medical journals demonstrates the lack of standards in identifying and reporting these potentially fatal conditions. This review also illustrates the low probability of observing and detecting rare events in typical clinical trials which include fewer than 300 subjects. Uniform standards for ascertainment and reporting are suggested which include operational definitions of study subjects. Meta-analysis of selected antibiotic trials using multivariate regression analysis indicates that meaningful conclusions may be drawn from data from multiple studies which are pooled in a scientifically rigorous manner. ^

Community diagnosis: A working tool for developing culturally appropriate diarrhea intervention programs

Most studies related to diarrhea have been focused narrowly on the etiological and pathophysiological factors involved in inducing the disease. Such studies have often failed to consider other facets contributing to and possibly prolonging the problem, namely: socio-economic conditions, educational opportunities and attainments, cultural characteristics and beliefs, and the political administration and its commitment towards fulfilling its moral and ethical obligations in responding to and fostering human development.^ This study utilized the diagnostic approach of the PRECEDE model. The acronym stands for the predisposing reinforcing, and enabling constructs in educational diagnosis and evaluation. The constituents of this model were identified by utilizing participant observation field methods, traditionally applied by ethnographers to collect data describing the multiple facets of a culture, and linguistic anthropology used to capture and define characteristic semantics and viewpoints. The household study sample was randomly selected from a defined list of households known to have at least one child less than five years of age. An open-ended questionnaire format was used to interview the 115 mothers in the selected households sample.^ Kalama, the study community, is characteristically an agricultural village, situated in the Governorate of Kaliobia and located approximately 25 Km (about 15.5 miles) from the capital, Cairo, Egypt. The 1986 census indicates a population size of 13,328 people in 4,818 households. There were 65 deaths occurring among children less than five years in 1986. The causes of death were primarily related to diarrhea, followed by upper respiratory infections, congenital anomalies and birth injuries.^ This study outlines (a) practices related to the management of diarrhea, including the administration of foods and drinks during such episodes; (b) influences of governmental policies; and (c) recommended strategies for overcoming barriers and promoting effective diarrhea intervention programs. ^

Comparison of alternative methods of contact tracing in a syphilis control program

The purpose of this study was to compare the relative effectiveness of alternative methods of tracing named contacts of syphilis patients. A total of 236 contacts, identified by patients in two City of Houston Department of Health and Human Services clinics during the period April 1 through July 31, 1987, were studied. After contacts were grouped by sex and age, the proportion brought to examination by each of three methods, and by a combination of methods, was determined for each subgroup.^ The study found that 78.4% of all the 236 named sex contacts reported were located and brought to examination by the various methods of contact tracing and that 21.6% were missed. Of the 185 contacts examined, a combination of methods identified 47.7% of the cases, telephone contact, 28.6%, field contact, 16.9%, and patient referral, 11.8%.^ Of the 236 contacts reported, males made up 56.8% and females 43.2%. Contact tracing was more successful among females, with 81.4% of the 102 named female contacts, as compared to 76.1% of the 134 named male contacts being brought to examination. It is not known whether equal efforts were exerted in the follow-up of both male and female contacts. In both female and male subgroups, a combination of methods brought over 40% of sex contacts to examination. Telephone contact among females yielded 27.7% of the cases and field contact 18.1%, whereas in males, telephone contact identified 29.4% of the cases and field contact 15.7%. Patient referral was the least productive method in both sex groups, locating 12.8% in males as compared to 10.8% in females.^ On an age specific basis, a combination of methods was the most effective method in the 15-39 age group, whereas telephone contact was most effective in the 40-44 age group, and field contact in the 50-54 age group. Of all the methods of contact tracing, patient referral was the least productive in most age groups.^ Future studies of contact tracing should incorporate several important variables which were not examined in this study. ^

Assessment of cancer incidence in Titus County, Texas, 1977--1984

The purpose of this study was to determine the incidence of cancer in Titus County, Texas, through the identification of all cases of cancer that occurred in residents of the county during the period from 1977 to 1984. Data gathered from Texas Cancer Registry, hospital records, and death certificates were analyzed with regard to anatomic site, race, sex, age, city of residence, and place of birth. Adjustment of incidence rates by sex and race allowed comparisons with U.S. rates provided by the Surveillance, Epidemiology, and End Results Program (SEER).^ Seven hundred sixty-six (766) cancer cases were identified for the eight year period during 171,536 person-years of observation. In whites, statistically significant standardized incidence ratios (SIR) were found for leukemia (males SIR = 2.70 and females SIR = 2.26), melanoma (males SIR = 1.90 and females SIR = 2.25), lung (males SIR = 1.45) and for multiple myeloma (both sexes combined SIR = 1.86). In blacks, significant excess numbers of cases were found for Hodgkin's disease (males SIR = 8.33 and females SIR = 13.3) and for esophagus and bone considering both sexes together (SIR = 2.68 and 12.54, respectively). Rates for blacks were based on a small population and therefore unstable. A statistically significant excess number of cases for all sites combined was found in Mount Pleasant residents (age-adjusted incidence rate = 563.6 per 100,000 per year).^ A review of possible environmental risk factors in the area: hazardous waste disposal site, lignite deposits, and petrochemical and poultry industries are presented. A need for further epidemiological and environmental studies to identify etiological factors that could be responsible for the excess number of leukemia cases are recommended. For melanoma, a public health educational program to teach the population methods of protection from sun exposure is also suggested. ^

Epidemiologic and methodological issues in serial measurements of blood pressure: The blood pressure study in Mexican children

The Blood Pressure Study in Mexican Children (BPSMC) is a short term longitudinal study of serial blood pressure collected in three observation periods by standardized examinations of 233 female children, 10 to 12 years of age, enrolled in public and private primary schools in Tlalpan, Mexico. Study objectives were: (1) to describe from baseline information the distribution and relationship of blood pressure to age and selected anthropometric factors, as well as to compare the BPSMC results with other blood pressure studies, (2) to examine the sources and amount of variation present in serial blood pressure of 123 children, and (3) to evaluate observer performance by means of intra- and inter-observer variability.^ Stepwise regression results from baseline revealed that of all anthropometric factors and age, weight was the best predictor for blood pressure.^ The results of serial blood pressure measurements show that, besides the known sources of blood pressure variability (subject, day, reading), the physiologic event of menarche has an important bearing upon the variability and characterization of blood pressure in young girls. The assessment of the effects of blood pressure variability and reliability upon the design and analysis of epidemiologic studies, became apparent among post-menarcheal girls; where blood pressure measurements taken from them have low reliability. Research is needed to propose alternatives for assessing blood pressure during puberty.^ Finally, observer performance of blood pressure and anthropometry were evaluated. Anthropometric measurements had reliabilities in excess of R = 0.96. Acceptable reliabilities (R = 0.88 to 0.95) were obtained for systolic and diastolic (phase 4 and 5) blood pressures. The BPSMC showed a 50 percent decrease in measurement error from the first to the third observation periods. ^

The association of previous induced abortion with the subsequent pregnancy complication of placenta previa

Placenta previa is alleged to be more common among women with a history of prior induced abortion. To investigate further whether there is a relationship between previous induced abortion and subsequent pregnancy complication of placenta previa, a matched case-comparison study was conducted comparing the reproductive histories of 256 women with placenta previa matched on age, date of delivery, and hospital with those of 256 women having normal deliveries and cesarean section deliveries without placental complications.^ Women with placenta previa had a twofold increase in the odds of having had one previous induced abortion (odds ratio 2.25) over women with no placental complications. Women with placenta previa and two or more previous induced abortions had a sevenfold increase in odds.^ The significant association of placenta previa and previous induced abortion remained after including gravida status, previous dilatation and curettage (D&C) status, previous spontaneous abortion, and race in a conditional logistic regression model. There is interaction between high gravidity and previous spontaneous abortion. Dilatation and curettage is associated with placenta previa primarily because women with abortion histories have also had a dilatation and curettage.^ Women who are seeking abortion and wish to have children later should be informed that there may be a longterm effect of developing placental complications in subsequent pregnancies. Women who have had at least one induced abortion or any dilatation and curettage procedure should be monitored carefully during any subsequent pregnancy for the risk of the complication of placenta previa. This knowledge should alert the physician or nurse-midwife to treat those women with a history of previous induced abortions as potential high risk pregnancies and could perhaps reduce maternal and fetal morbidity rates. ^

A descriptive study of comprehensive and categorical services for pregnant and parenting adolescents in West Dallas

This study evaluates the effectiveness of the Children and Youth Projects' Adolescent Family Life Program, a comprehensive program serving pregnant and parenting adolescents in the economically disadvantaged area of West Dallas. The underlying question asked is what are the relative contributions of the comprehensive, school-linked Adolescent Family Life (AFL) Program compared with the Maternal Health and Family Planning Program (MHFPP), a categorical provider of family planning and reproductive services, towards meeting the immediate and intermediate term needs of adolescent mothers. Also addressed are the protective effects of participation in the Dallas Independent School District Health Special Program, a segregated school for pregnant adolescents.^ A cohort of 339 West Dallas adolescent mothers who delivered babies during a two-year period, 1986 through 1987, are monitored by linking records from Parkland Hospital, the primary provider to hospital services to indigent women in Dallas, the Dallas Independent School District, and the prenatal care providers, the AFL and MHFP Programs. Information is collected on each teen describing her demographic, fertility, service utilization and educational characteristics.^ The study tests the hypothesis that adolescents receiving services from the comprehensive AFL program will be less likely to have a repeat birth and to discontinue school during the 24 month study period, compared with categorical provider clients. Although the study finds that there are no statistically significant differences in repeat deliveries, using survival analysis, or in school continuation between programs, important findings are revealed about the ethnic differences. Black and Hispanic fertility and educational behaviors are compared, and their implications for program design and evaluation discussed. ^

Patterns of homicide Houston: Texas, 1987

The situational and interpersonal characteristics of homicides occurring in Houston, Texas, during 1987 were investigated. A total of 328 cases were ascertained from the linking of police computer data, medical examiner's records, and death certificate information. The medical examiner's records contained all of the ascertained cases. The comparability ratio between the medical examiner's records and police and vital statistic data was 1.03 and 0.966, respectively. Data inconsistencies were found between the three information sources on Spanish surname, age, race/ethnicity, external cause of death coding, alcohol and drug involvement, weapon/method used, and Hispanic immigration status. Recommendations for improving the quality of homicide information gathered and for linking homicide surveillance systems were made.^ Males constituted 82% of all victims. The age-adjusted homicide rate for Blacks was 31.1 per 100,000 population, for Hispanics 19.2, and for Anglos 5.4. Among males, Blacks had an age-adjusted rate of 54.5, Hispanics, 31.0, and Anglos 7.5. Among females, Blacks had an age-adjusted rate of 9.3, Hispanics 6.1, and Anglos 3.1. Black males, ages 25-34, had the highest homicide rate, at 96.5.^ Half of all homicides occurred in a residence. Among Hispanic males, homicides occurred most often in the street. Firearms were used to commit 64% of the homicides. Arguments preceded 58% of all cases. Nearly two-thirds of the victims knew their assailant. Only 15% of males compared to 62% of females were killed by a spouse, an intimate acquaintance, or a family member. Blacks (93%) and Hispanics (88%) were more likely than Anglos (70%) to have been killed by persons of the same race/ethnicity. Nearly three-fourths of all Houston Hispanic homicide victims were foreign born.^ Alcohol was detected in 47% of the victims tested. Nearly one-third of those tested had blood alcohol concentrations (BACs) greater than 100 mg%. Males (53%) were more likely than females (20%) to have positive BACs. Hispanic males (64%) were more likely to have detectable BACs than either Black (51%) or Anglo (44%) males.^ Illegal drugs were detected in 20% of the victims tested. One-fourth of the victims who tested positive for drugs had more than one drug in their system at death. The stimulant cocaine was the most commonly detected drug, comprising 53% of all illegal drugs identified.^ Recommendations for the primary, secondary, and tertiary prevention of homicide and for future homicide research are made. ^