Epidemiology and biostatistics

Based on the our October paper "A Generalized Viral Infection Mathematical Model Derived from Covid-19 Simulation", at a conceptual level higher than the classic SIR/SEIR model, we have established the 6 laws of infection regarding the final infection ratio within any given population without any artificial intervention and have shown the final infection ratio in a natural, non-interfered pandemic must fall within a specified lower and upper bound as 1 − 1 R 2 0 ≤ F R ≤ 2 (1 − 1 R 0). Whereas R 0 is the intrinsic R 0 value of the disease. In this paper, we show how human intervention strategies alter the previous assumptions based on 2 factors. First, artificial intervention with cycles of restricting measures and relaxations. Based on our May paper "The Predictions on Worldwide Covid-19 Pandemic Cases Based on Historical Data", we have already demonstrated the dynamic falling R 0 (t) curve during lock down measures. With more historical data and observation, we now expand the scope to include a dynamic rising R 0 (t) curve following the relaxation of measures, completing the cycle of restriction and relaxation. Second, the introduction of vaccination at a steady rate introduced a new variable into the existing infection model, we denote it as function V (t). We demonstrate the optimal strategies of vaccination interpreted within our existing established framework.

Aims: To discuss different LMM-based approaches applied in GWAS and software packages implementation and Classify different computational tools that applies LMM approaches according to their applicability and performance. To identify possible SNPs associated to a particular disease using different computational tools based on LMM approaches. To estimate genetic and residual variance parameters that account phenotypic variation of the disease. Study Design: Case control study Place and Duration of Study: The research was carried out in Tanzania at African Institute of Mathematical Science for six months. Methodology: Linear Mixed Models (LMMs) are widely applied in genomic wide associations studies (GWAS) owing to their effectiveness of correcting hidden relationship, population structure and family structure. This essay is aimed at exploring different mathematical approaches of LMMs in GWAS. These approaches are linear mixed model with inclusion of all markers (LMMi) and linear mixed model with Original Research Article Wanyonyi et al.; AJPAS, 1(4): xxx-xxx, 2018; Article no.AJPAS.44107 2 exclusion of all markers (LMMe) when calculating genetic relationship matrix. LMMi is more efficient as compared to LMMe when applied in studies of randomly ascertained quantitative traits. The LMM approaches are classified based on their applicability and performance. Two computational GWAS tools namely, PLINK and EMMAX were used which were based on LMM approaches to analyze unpublished real data from West Africa (Gambia and Ghana). Genetic and residual variance parameters were estimated that accounted for the phenotypic variation of the disease to be 0.0594 and 0.0723. A total of 338408 variants and 959 people (484 males, 405 females and 70 missing phenotypes) pass filters and quality control using PLINK was used in the study. Among the remaining phenotypes, 864 are cases and 95 are controls. The performance of different mathematical approaches of LMMs and their software implementation, including EMMAX and Plink via the application to a GWAS of tuberculosis (TB) in 959 individuals in West Africa (Ghana and Gambia) was compared. Of these 864 cases of TB and 95 healthy individuals retained after quality control (QC) using Plink, and 329601 autosome single nucleotide polymorphisms (from chromosome 1 to chromosome 22) included in the analysis after 288 duplicands ID individuals removed after QC. The LMM approaches are classified based on their applicability and performance. Two computational GWAS tools, namely Plink and EMMAX were used in the analysis of data. Genetic and residual variance parameters were estimated that accounted for the phenotypic variation of the disease to be 0.0594 and 0.0723. Results: Result showed that SNPs associated with tuberculosis were 7225581 on chromosome 17 and SNP 491412 on chromosome 13 with both having 0.69% false discovery rate with step up significance value. Plink failed to correct hidden relatedness. Although EMMAX reduced the false positive rate, it still exhibited very low presence of stratification. Conclusion: This study aimed at understanding and exploring different approaches of mixed models as applied in genetic studies. Overview of genetic variation, advantages, successes and application of mixed models and current challenges of mixed models in GWAS were discussed. Moreover, the study showed that SNPs was associated with a particular disease using computational tools that applies LMM approaches. The summary statistics from PLINK and EMMAX found two causal SNPs associated with the TB. These SNPs were rs7225581 on chromosome 17 and SNP rs4941412 on chromosome 13 with both having 0.69% FDR H. However, PLINK failed to correct hidden relatedness. This phenotypic variation showed that all common single nucleotide polymorphisms (SNPs) expressed approximately 18.52% of phenotypic variation of the disease. Keywords: Genomic wide association studies (GWAS); mixed linear models approaches; single nucleotide polymorphism (SNP).

Background: Iodine deficiency disorder is common public health problem in developed and developing countries. In Worldwide, nearly 70% of the households only using adequate iodized salt in their regular food. To estimate the household salt utilization, prevalence of goiter, status of iodine deficiency disorder, and to find the iodine level at household level in the study areas. Materials and Methods: We have done a community-based observational study on IDD in the coastal areas of Villupuram District, Tamil Nadu with examined households salt in 1233 households in selected eight villages. All data were analyzed using Chi-Square test. p–value<0.05 was considered as statistically significant. Results: Totally 1233 households were recruited and incorporated in this study. Among 1233 households, male 385 (31.2%) and female 848 (68.8%). The male and female age-group was showed statistically highly significant association with p<0.01. Out of 1233 individuals, 141 (11.4%) were found a...

This text book is a comprehensive user friendly and easy to read introduction to biostatistics and research methodology meant for undergraduate and postgraduate medical students and allied biomedical sciences (Dental, Nursing, Psychology, Nutrition, MSc and PhD students).

Succinct yet thorough, it serves as an outstanding resource for students and health researchers for writing protocol for research projects as well as allows readers to acquire ability to apply appropriate statistical methods to summarize, analyze, and draw conclusions from biological research including data presentation methods.

Unique features of the book (2nd Edition):

 Emphasis on key concepts of data presentation, scales of measurement, measures of central tendency and dispersion, normal distribution, sample size calculation and sampling techniques, probability, sampling variability, null hypothesis, and details on tests of significance, written in lucid language.
 Numerous examples illustrate the application of each statistical method and further exemplified with tables and diagrams where necessary.
 Complicated statistical issues such as correlation and regression with their interpretations are dealt with in simplified manner.
 Theory questions from different university examinations across India at the end of each chapter.
 Collection of Multiple Choice Questions from different post graduate entrance examinations at the end of each chapter with explanation of the answers.
 Basic information about writing a research protocol.
 Useful tool to write the thesis of postgraduate students, project of undergraduate students and other research reports.
 Some useful tips on publication of research work in journals.

Практическо учебно ръководство за студенти по медицина и медицински специалисти, разработено специално за курса по биостатистика на студенти по медицина и други медицински специалности. Може да бъде използвано като подходяща добавка и в по-високи нива на обучение. Издание на Академично издателство на Тракийски университет, Стара Загора.

Caesarian Section (CS) rates have been known to have geographical varaitions. The purpose of this paper was to determine Ghana's situation (regional trend) and also to provide a two-year forcast estimates for the ten (10) regions of Ghana. The data was longitudinal and comprised monthly CS records of women from 2008 to 2017. The dataset was divided into training and testing dataset. A total of eighty four (84) months were used as the training dataset and the remaining thirty six (36) months were used as testing dataset. The ARIMA methodology was applied in the analysis. Augmented Dicker-Fuller (ADF), KPSS and the Philips-Perron (PP) unit root tests were employed to test for stationarity of the series plot. KPSS (which is known to give more robust results) and PP test consistently showed that the series was stationary (p ＜ 0.05) for all ten (10) regions, although there were some conflicting results with the ADF test for some regions. Tentative models were formulated for each regi...

Prevalence of Breast Cancer in Delta State, Nigeria was discussed in this paper. Secondary data sourced from the records units of five hospitals in delta state was used. Cross tabulation, Chi-square test for independence, Regression Analysis, Correlation Analysis and Odds Ratio were applied on the three year study, from which it was found that breast cancer cases are independent on environmental factor and dependent on educational factor. A strong linear relationship exists between Breast Cancer and death from such disease, implying that increase in the number of breast cancer cases has very high positive effect on the occurrence of death  (r = 0.968), 93.7% of the variation in death occurrence is explained  by breast cancer. The probability of dying from breast cancer is higher in women 50 years and above than in younger women (age < 50 yrs).

Statistical Theory and Analysis in Bioassay is a seven-chapter monograph tailored essentially to meet the needs of graduate students, practitioners, and researchers in the fields of medicine, pharmacology, biosciences/life sciences, and related fields that employs the tools of biostatistics in bioassays and analysis. In this wise, we have taken time to discuss in detail relevant topics; principles, methods, and applications. Practice exercises are also included where necessary. The earlier chapters gave background information, definition of terms, purpose, types, structure, and relative potency in bioassay. An important theorem, Fieller’s theorem is proved in detail with illustrative examples. The last two chapters are on dose-response relationship, fitting in parallel-line assays and estimation. We are convinced that this monograph will meet the expectations of the readers while constructive criticisms that will improve another edition will be appreciated.

This report is a compilation of findings from the first Jamaican Healthy Lifestyle Survey (JHLS I)  which sought to determine health status, nutritional habits, lifestyle and behaviour in a nationally representative sample of 15-74-year-old Jamaican adults and  to assess the association of  these chracteristics - health status, nutritional habits, lifestyle and behaviour - to relevant demographic and socio-economic variables.

La administración de los recursos renovables ha estado fundamentada en el concepto de
máximo rendimiento sustentable, según el cual el inventario de los recursos biológicos no
puede sobreexplotarse sin una pérdida final de productividad. Este concepto se basa en
esquemas de crecimiento biológico. El objeto de este trabajo es presentar algunos modelos
de crecimiento bajo el enfoque de dinámica de sistemas, lo cual permite estudiarlos
mediante simulación y análisis de sensibilidad. Se presentan los principios del modelaje de
ecosistemas, los modelos clásicos de crecimiento (exponencial y logístico) y en anexo, los
fundamentos de la dinámica de sistemas.

Food safety has been a major health challenge in both developed and developing countries. Ensuring food safety is key to preventing food borne illnesses which are contracted through consumption of unsafe foods. The aim of this study was to identify the food safety practices of residents of a rural community in Southwest, Nigeria. The study design was cross-sectional. Five clusters were selected by simple random sampling from the sampling frame. All households in the clusters were sampled to achieve a sample size of 216 households. Data were collected using a semi-structured questionnaire. The results show that majority of the respondents were female (62.2%), Christians (78.1%), married (53.1%), and belong to the Yoruba ethnic group (88.3%). Residents of the community showed good food safety practices with 80.6% reported to always washing their hands before cooking, 90.3% always clean their cooking utensils before and after use, 83.7% always clean their cooking environment, and nearly all (96.9%) reported washing their hands after using the toilet. A statistical association was found between educational level and washing of hands after the use of toilet (p = 0.037). Though the results show a satisfactory level of food safety practice, however, more improvements can still be made. The method of waste disposal and source of drinking water pose a future threat to the health of the community residents. Hence, a call for government's intervention in providing potable water and modernised waste disposal facilities.

Foodborne diseases can be defined as those conditions that are commonly transmitted through ingested food. The two most common types of food borne diseases are intoxication and infection. Intoxication occurs when toxin produced by the pathogens cause food poisoning, while infection is caused by the ingestion of food containing pathogens. Some microorganisms can use our food as a source of nutrients for their growth. By growing on the food, metabolizing them and producing byproducts, they not only render the food inedible but also pose health problems upon consumption. Clostridia produce the highest number of toxins of any type of bacteria. Among Clostridium species, clostridium perfringens is the largest toxin producer and also the most widespread, being found as part of the microbiota of animals and humans and in the soil. In most cases, clostridium perfringens food poisoning results by eating improperly cooked and stored foods. Clostridium perfringens food poisoning is quite commo...

A Estatística é uma ferramenta imprescindível a qualquer pesquisador ou pessoa que necessite tomar decisões. O seu estudo não representa uma tarefa muito fácil, principalmente no início, quando são apresentados muitos conceitos novos que exigem um tipo especial de raciocínio.

Introduction: Mastectomy is the common surgical procedure for breast cancer. Following mastectomy potential complications are likely to occur and lymphedema is one of the dreadful complications. Post mastectomy exercises play an important role in prevention of complications by releasing muscular tension, preventing contractures and restoring strength. Studies have reported that pre and post operative education is the best method to reduce complications. Realizing the importance to create awareness on management of Lymphedema, a study was undertaken with an aim to determine the effectiveness of video assisted teaching on knowledge regarding post mastectomy exercises among breast cancer patients. Materials and Methods: A quasi experimental study, with pre and post test research design without control group approach was undertaken among breast cancer patients who undergo mastectomy at Kidwai Memorial Institute of Oncology, Bangalore (Karnataka). A total of 50 pre operative breast cancer patients were selected using convenient sampling method. Pre test was conducted for those patients using structured interview schedule, the same day video assisted teaching was given for duration of 20min and on the 7 th day post test was given. Results were compared between pre test and post test knowledge scores and association was studied between various demographic variables. Results: In pre test, the overall knowledge score was (16.42±3.0) which is 36.48% whereas after implementation of video assisted teaching programme, the post test knowledge score had improved (34.92±3.80) which is 77.6% and the gain in knowledge was statistically significant. It was noted that knowledge on post mastectomy exercises had significant association with demographic variables like type of family and family history of cancer at p<0.05 level. Conclusion: The study concluded that video assisted teaching is an effective instructional method & educational tool in imparting knowledge on post mastectomy exercises among breast cancer patients who undergo mastectomy.

Adolescents are generally thought to be healthier than other age groups having survived many of the diseases of early childhood and being decades away from the diseases associated with aging (WHO, 1998). However, some adolescents are affected by diseases while others die prematurely. A major threat to the health of the adolescents stems primarily from their sexual behavior which is partly influenced by lack of knowledge of reproductive health issues. The main objective of this study was to assess reproductive health knowledge and attitude among secondary school students in Nandi Hills Constituency. This was a cross-sectional study design of male and female secondary school students in Nandi Hills Constituency. Four classes of secondary level were involved in this study. The study assessed knowledge and attitudes of these students towards reproductive health. Data was collected from secondary school forms 1 to 4 students who were selected from 5 of the 10 co-educational secondary schools in Nandi Hills Constituency using a purposive sampling technique. 40 students were sampled from 5 schools using a 10% quota. This made the sample size of this study to be 200 respondents. The study found that majority (71.4%) of the female secondary students interviewed from the different schools had not learnt about puberty and maturation of girls. According to the study findings, majority of the female students believed that one can get pregnant half way between the end of one period and beginning of the next (48.0%). Other 26.5% and 10.3% of the female students interviewed in this study believed that they could get pregnant immediately before and after periods respectively. This study concludes that there are low knowledge levels on reproductive health among secondary school adolescents in Nandi Hills Constituency. It recommends a multi-sectoral approach to addressing of the adolescents reproductive health needs. Such approach should involve parents, peers, teachers and health departments.

Background and Aims
Childhood eating habits become behaviors lasting until adulthood and most of the research has also shown that children in Denmark are not eating recommended daily intake (RDI) of fruits and vegetables (FV). The study aims to identify the determinants promoting or preventing consumption of FV among 5-12 year-old multi-national students in an after school program (ASP) at Østerport International School, Copenhagen, Denmark.
Methods
Using a pre-test/post-test experimental study design, 53 children of ages 5 to 7 and 8 to 10 years old from 18 different countries were randomly selected for study. The food frequency questionnaires (FFQ) were administered before and after two-weeks nutrition education intervention. Children lunches were observed and recorded for one week before and after the nutrition education intervention. Some pre-test questions were repeated during the post-test, while others were not repeated in the post-test due to a lack of resources and time on the part of the researchers.
Results
The FFQ showed that 47% children consumed FV due to family influence and knowledge, 49% due to taste preferences (likes/dislikes), 34% due to school environment and 28% due to peer group, . Among all the determinants, availability and attitude were shown to have less influence on the consumption of FV (11%). There was no evidence that repeated taste-testing of new FV resulted in children consuming more FV.
Conclusions
Nutrition education intervention can be important tool to promote FV consumption in school and to address the several factors preventing them to eat more FV in their daily life

The novel Coronavirus disease (COVID-19) is a severe respiratory infection that officially occurred in Wuhan, China, in December 2019. In late February, the disease began to spread quickly across the world, causing serious health, social, and economic emergencies. This paper aims to forecast the incidence of the COVID-19 epidemic through the medium of an autoregressive integrated moving average (ARIMA) model, applied to Italy, Russia, and the USA, in three different time windows. The forecasts show that: i) the Arima models are reliable enough when new daily cases begin to stabilize; and ii) Russia and the USA will require more time than Italy to drop COVID-19 cases near zero. This may suggest the importance of the application of lockdown measures, which have been relatively stricter in Italy. Therefore, even if the results should be interpreted with caution, ARIMA models seem to be a good tool that can help the health authorities to monitor the diffusion of the outbreak.

Kebiasaan makan adalah ekspresi setiap individu dalam memilih makanan yang akan membentuk pola perilaku makan. Oleh karena itu, ekspresi setiap individu dalam memilih makanan akan berbeda satu dengan yang lain. Menurut Hadi (2003) ketidakseimbangan asupan energy (energy intake) yang melebihi energi yang digunakan (energy expenditure) dapat menyebabkan obesitas. Perubahan pola makan ini dipercepat oleh kemajuan teknologi informasi dan globalisasi ekonomi. Perbaikan tingkat

Objective 　To evaluate the effect of training to HIV/AIDS knowledge, attitude and practice of elementary health care workers. Methods  57 elementary health care workers were trained and accepted pre and post test and answered a questionnaire named “How do you feel about HIV/AIDS?”  Results  After training, the average score of test increased 21.93, which is 47.6% higher than pre test. Item of HIV occupational post exposure prophylaxis had the largest increasing extent of 172%. Correct rate of “How do you feel about HIV/AIDS? ” also increased after training.  Conclusion  It is necessary to strengthen knowledge on HIV occupational and build a correct  HIV/AIDS prevention & treatment viewpoint. Design trainings with suitable content and multiple training methods will not only increase the knowledge and contribute to formation of reasonable attitude and behavior.

Anthropometric and body frame size parameters (ABFSP) are used to interpret body mass and to evaluate nutritional status. Objective of the present study was to investigate the interrelationships between ABFSP, percentage body fat (BF%) and body mass index (BMI). The study was carried out in a sample of 141 adult Bengalee healthy male brick-kiln workers (age range 18–59 years) from Murshidabad district in West Bengal, India. Body weight was recorded; anthropo-metric measurements included height, breadth (elbow, wrist, hand, foot, ankle, knee), circumferences (mid-upper arm, chest, waist, hip, thigh, medial calf) and skinfolds (biceps, triceps, subscapular, suprailiac). Derived ABFSP included sum of breadth and circumferences, frame index, BMI, BF%, sum of skinfolds, ratio of central and peripheral skinfolds, arm muscle area, arm muscle circumference, arm fat area and brachial adipo-muscular ratio. Correlations (age-controlled) between ABFSP, BMI and BF% were highly significant (p < 0.001). The ABFSP and BF% varied significantly (p < 0.0001) in relation to BMI-based nutritional status (BNS). Multinomial logistic regression analysis (age-adjusted) showed ABFSP had statistically significant (p < 0.01) relationships with BNS. There were strong interrelationships between ABFSP, BMI and BF% independent of age. The ABFSP in individuals with normal BMI, suffering from undernutrition (low BMI) or overweight are different.

Medical students’ assessment about the performed education in Biostatistics was presented through analysis of results of students’ feedback. Computer programmes and examples used during the practical education were assessed highly by the most students. The common assessment especially for the practical education was high. Students assessed especially high the stimulation of their own activity during biostatistics’ education. They considered as necessity the further undergraduate and postgraduate education in Biostatistics. Authors considered the results as satisfying for them. Recognition of benefit of practical skills in the field of Biostatistics for the future professional work and the stimulation of the interest especially in the area of analytic statistics were pointed out.

Anthropology's response to the West African Ebola epidemic was one of the most rapid and expansive anthropological interventions to a global health emergency in the discipline's history. This article sets forth the size and scale of the anthropological response and describes the protagonists, interventions , and priorities for anthropological engagement. It takes an inclusive approach to anthropological praxis by engaging with the work of nonanthro-pologist " allies, " including qualitative researchers, social workers, and allied experts. The article narrates how the concept of " anthropology " came to serve as a semantic marker of solidarity with local populations, respect for customary practices and local sociopolitical realities, and an avowed belief in the capacities of local populations to lead localized epidemic prevention and response efforts. Of particular consideration is the range of complementary and conflicting epistemological, professional, and critical engagements held by anthropologists. The article also discusses how to assess anthropological " impact " in epidemics. 421

Background: Neonatal sepsis is a common condition among neonates particularly in developing countries. Treatment of neonatal sepsis is with antibiotics, which have huge benefits when indications are clear. However, widespread utilisation of antibiotics over the years has been reported to favour the emergence of antibiotic resistance. In this study, we aimed at assessing antibiotic resistance and associated factors for neonatal sepsis at a selected children’s hospital in Zambia. Method: We conducted a retrospective cross-sectional study from January, 2018 to December, 2019. Data was collected from files of all admitted neonates and the microbiology blood culture register. Analysis of factors associated with antibiotic resistance was done by logistic regression using STATA software, version 14 and statistical tests were done using 5% significance level and 95% confidence intervals. Results: Out of the 172 blood cultures analysed, 61.0% (105/172) were male admitted with suspected neona...

Austin Bradford Hill's  famous paper, "The Environment and Disease," and his nine factors indicating that a statistical correlation might be causal, have been widely cited, but often misunderstood---especially in the US legal system, where these factors are often described as "criteria." Haack explores the arguments of Hill's paper in detail; traces the history of their use (and misuse) in legal contexts, and finally argues that what hill offered was a useful but incomplete sketch-map of the much epistemological territory: the weight of combined evidence.

If this paper interests you, you might want also to look at "Risky Business: Statistical Proof of Specific Causation" (2014), "Proving Causation: The Holism of Warrant and the Atomism of Daubert (2008), and  and "An Epistemologist  among the Epidemiologists" (2004)

POWERPOINTS TO ACCOMPANY THIS PAPER ARE AVAILABLE IN THE SECTION LABELED “SELECTED PRESENTATIONS” BELOW (UNDER “MORE”).

If the probability of success parameter, p, of a binomial distribution has a beta-distribution with shape parameters α >0 and β > 0, the resulting distribution is known as a beta-binomial distribution. For a binomial distribution, p, is assumed to be fixed for successive trials and there are exactly two mutually exclusive outcomes of a trial. For the beta-binomial distribution, the value of p changes for each trial. The occurrence of over-dispersion, meaning that the variability in the data is not adequately described by the models is dealt with through a beta-binomial model, the beta-binomial distribution is one of the distributions that allows for over-dispersion, and under dispersion relative to the binomial distribution. William’s procedure, Scaling, Generalized Estimating Equation and the Beta-binomial are used to correct over-dispersion using standard software R. By using applications to real life data, it is shown that the Beta-binomial distribution, William’s procedure, Scaling and GEE outperforms the standard binomial distribution.

Keywords: binomial distribution; beta-binomial distribution; GEE; goodness-of-fit-tests; over-dispersion; scaling

Background: Majority of the women with cervical cancer delay to seek health care and the determinants are not well not.
Objective: This study sought to investigate potential determinants of patient delay among Ugandan women with cervical cancer.
Methods: A cross-sectional study was conducted from March 2017 to May 2017 at the Mulago National Referral Hospital in the capital city of Uganda. The data was collected using questionnaire among patients with cervical cancer (stages I–IV).
An interval longer than 90 days between self-discovery of a potential symptoms and presentation to a qualified health worker was defined as a patient delay.
Results: One hundred and thirty-six patients with cervical cancer enrolled in this study and 36.8% had patient delay. The median and mode age group was 35-46 years, 76.5% had not exceeded secondary level of education. The findings showed that 71.4% were diagnosed with stages II-IV and among them 32.7% were found having patient delay. The regression analysis showed that women over 55 years (p=0.041), fear of being diagnosed with cancer (p=0.039), borrowing money to pay medical bills (p=0.02), long distance (p=0.046), and poor quality of health service (p = 0.001) were significantly associated with patient delay.
Conclusion: The study shows that source of funds to pay medical bills is the only socio-economic factor  associated with patient delay while the fear of being diagnosed with cervical cancer is the only individual factor associated with patient delay. The distance to the first choice of provider and quality of health services are the health system factors associated with delay in seeking health care among women with cervical cancer in Uganda.

Imagine that a thousand people—randomly selected from the U.S. population—had unprotected sex yesterday. How many of them will eventually die from contracting HIV from that single sexual encounter? Now, imagine a different thousand people. These people will drive from Detroit to Chicago tomorrow—about 300 miles. How many will die on the trip as a result of a car crash? Which of those two numbers is bigger? If you’re anything like the participants in a new study led by Terri D. Conley of the University of Michigan, the HIV estimate should be bigger—a lot bigger. In fact, the average guess for the HIV case was a little over 71 people per thousand, while the average guess for the car-crash scenario was about 4 people per thousand. In other words, participants thought that you are roughly 17 times more likely to die from HIV contracted from a single unprotected sexual encounter than you are to die from a car crash on a 300-mile trip. But here’s the deal: Those estimates aren’t just wrong, they’re completely backward.