scholarly journals Reflections on modern methods: Statistics education beyond ‘significance’: novel plain English interpretations to deepen understanding of statistics and to steer away from misinterpretations

Author(s):  
Hilary C Watt

Abstract Concerns have been expressed over standards of statistical interpretation. Results with P <0.05 are often referred to as ‘significant’ which, in plain English, implies important. This leads some people directly into the misconception that this provides proof that associations are clinically relevant. There are calls for statistics educators to respond to these concerns. This article provides novel plain English interpretations that are designed to deepen understanding. Experience teaching postgraduates at Imperial College is discussed. A key issue with focusing on ‘significance’ is the common inappropriate practice of implying no association exists, simply because P >0.05. Referring to strengths of association in ‘study participants’ gives them gravitas, which may help to avoid this. This contrasts with the common practice of focusing on imprecision, by referring to the ‘sample’ and to ‘point estimates’. Unlike formal statistical definitions, interpretations developed and presented here are rooted in the application of statistics. They are based on one set of study participants (not many random samples). Precision of strengths of association are based on using strengths in study participants to estimate strengths of association in the population (from which participants were selected by probability random sampling). Reference to ‘compatibility with study data, dependent on statistical modelling assumptions’ reminds us of the importance of data quality and modelling assumptions. A straightforward graph shows the relationship between P-values and test statistics. This figure and associated interpretations were developed to illuminate the continuous nature of P-values. This is designed to discourage focus on whether P <0.05, and encourage interpretation of exact P-values.

2017 ◽  
Vol 16 (2) ◽  
pp. 38-63
Author(s):  
KEREN ARIDOR ◽  
DANI BEN-ZVI

This article examines how two processes – reasoning with statistical modelling of a real phenomenon and aggregate reasoning – can co-emerge. We focus in this case study on the emergent reasoning of two fifth graders (aged 10) involved in statistical data analysis, informal inference, and modelling activities using TinkerPlotsTM. We describe nine phases of the students’ articulations of aggregate and modelling reasoning as they explored a small sample, constructed a model and generated random samples from this model to examine its validity. These phases are distinguished by the students’ views toward data, variability, and models. We discuss implications and limitations of the results. Despite the idiosyncrasy of the case, the lessons are important because they open a new direction for research about reasoning with data and models. First published November 2017 at Statistics Education Research Journal Archives


Author(s):  
Göran Friman

Objective: To describe the distribution of risk, diagnosis and pharmacological treatments for diabetes and hypertension after seven years among patients provided with opportunistic medical screening in a dental setting. Material and Methods: The initial screening’s 170 participants were asked to take part in a seven-year follow-up study. Data were collected through self-reported information in a written health declaration. Outcome measures: • Number of study participants who had passed away • Prescription of antidiabetics or antihypertensives • Changes in weight and height to calculate body mass index (BMI) Results: The follow-up study consisted of 151 participants. Twenty had passed away. The risk needs for medicating with antihypertensive drugs after seven years for those not receiving pharmacological treatment at the initial screening was 3.7 times greater (p=0.025 CI 1.2-11.3) for participants with a diastolic blood pressure (BP) ≥ 90 mm Hg (85 for diabetics) than for the others. The risk was 3.9 times greater (p=0.020 CI 1.2-12.6) for those with a systolic BP of 140-159 mm Hg and 54.2 times greater (p<0.0001 CI 9.8-300.3) for those with a systolic BP ≥ 160 mm Hg than for those with a systolic BP 140 mm Hg. There were no changes in BMI. Conclusion: At least one in ten cases of incorrect medication or undiagnosed hypertension may be identifiable through opportunistic medical screening


2021 ◽  
pp. 026858092199852
Author(s):  
Aneta Piekut ◽  
Gill Valentine

In this article, the authors move away from approaching generations as static categories and explore how ordinary people, as opposed to scholars, distinguish generations and justify their different responses to cultural diversity in terms of ethnicity, race and religion/belief. The analysis draws on 90 in-depth interviews with 30 residents in the Polish capital, Warsaw (2012–2013). Through approaching generation as an analytical category, the authors identify various differentiating narratives which the study participants employed to draw boundaries between generations, reinforcing the common belief that the youngest Poles are most accepting of diversity. Although generations are seen as the axis of difference, conditioning generation-specific responses to diversity, the accounts emerging from the interviews reveal their relational nature, as well as similarities and points of connection between their experiences.


2019 ◽  
Vol 18 (1) ◽  
pp. 46-62
Author(s):  
NOELLE M. CROOKS ◽  
ANNA N. BARTEL ◽  
MARTHA W. ALIBALI

In recent years, there have been calls for researchers to report and interpret confidence intervals (CIs) rather than relying solely on p-values. Such reforms, however, may be hindered by a general lack of understanding of CIs and how to interpret them. In this study, we assessed conceptual knowledge of CIs in undergraduate and graduate psychology students. CIs were difficult and prone to misconceptions for both groups. Connecting CIs to estimation and sample mean concepts was associated with greater conceptual knowledge of CIs. Connecting CIs to null hypothesis  significance testing, however, was not associated with conceptual knowledge of CIs. It may therefore be beneficial to focus on estimation and sample mean concepts in instruction about CIs. First published May 2019 at Statistics Education Research Journal Archives


2014 ◽  
Vol 13 (1) ◽  
pp. 53-65 ◽  
Author(s):  
ROBYN REABURN

This study aimed to gain knowledge of students’ beliefs and difficulties in understanding p-values, and to use this knowledge to develop improved teaching programs. This study took place over four consecutive teaching semesters of a one-semester tertiary statistics unit. The study was cyclical, in that the results of each semester were used to inform the instructional design for the following semester. Over the semesters, the following instructional techniques were introduced: computer simulation, the introduction of hypothetical probabilistic reasoning using a familiar context, and the use of alternative representations. The students were also encouraged to write about their work. As the interventions progressed, a higher proportion of students successfully defined and used p-values in Null Hypothesis Testing procedures. First published May 2014 at Statistics Education Research Journal Archives


2018 ◽  
Vol 5 (2) ◽  
pp. 72-89
Author(s):  
Martine Jayne Barons ◽  
Rachel L Wilkerson

Causal questions drive scientific enquiry. From Hume to Granger, and Rubin to Pearl the history of science is full of examples of scientists testing new theories in an effort to uncover causal mechanisms. The difficulty of drawing causal conclusions from observational data has prompted developments in new methodologies, most notably in the area of graphical models. We explore the relationship between existing theories about causal mechanisms in a social science domain, new mathematical and statistical modelling methods, the role of mathematical proof and the importance of accounting for uncertainty. We show that, while the mathematical sciences rely on their modelling assumptions, dialogue with the social sciences calls for continual extension of these models. We show how changing model assumptions lead to innovative causal structures and more nuanced casual explanations. We review differing techniques for determining cause in different disciplines using causal theories from psychology, medicine, and economics.


2021 ◽  
Author(s):  
Andrew W Bergen ◽  
Carolyn M Ervin ◽  
Christopher S McMahan ◽  
James W Baurley ◽  
Harold S Javitz ◽  
...  

Background: Factors influencing cessation include biopsychosocial characteristics, treatments and responses to treatment. The first cessation trial designed to assess cessation disparities between African American and White cigarette smokers demonstrated that socioeconomic, treatment, psychosocial and smoking characteristics explained cessation disparities. Ongoing translational efforts in precision cessation treatment grounded in genetically informed biomarkers have identified cessation differences by genotype, metabolism, ancestry and treatment. Methods: In planned analyses, we evaluated six smoking-related measures, demographic and socioeconomic covariates, and prospective abstinence (7-day point prevalence at 12 weeks with bupropion, nicotine replacement and counseling treatments). We assessed concurrent and predictive validity in two covariate models differing by inclusion of Office of Management and Budget (OMB) race/ethnicity or genomic ancestry. Results: We studied Pharmacogenetic Study participants (N=456, mean age 49.5 years, 41.5% female, 7.4% African American, 9.4% Multiracial, 6.5% Other, and 6.7% Hispanic). Cigarettes per day (OR=0.95, P<.001), Fagerström score (OR=0.89, P≤.014), Time-To-First-Cigarette (OR=0.75, P≤.005) and predicted urinary nicotine metabolite ratio (OR=0.57, P≤.039) were associated with abstinence. OMB African American race (ORs from 0.31 and 0.35, p-values≤.007) and African genomic ancestry (ORs from 0.21 and 0.26, p-values≤.004) were associated in all abstinence models. Conclusions: Four smoking-related measures exhibited association with abstinence, including predicted nicotine metabolism based on a novel genomic model. African genomic ancestry was independently associated with reduced abstinence. Treatment research that includes social, psychological, treatment and biological factors is needed to reduce cessation disparities.


2017 ◽  
Vol 15 (1) ◽  
pp. 20-22
Author(s):  
Roma KM ◽  
Manita Pyakurel ◽  
Veena Gupta ◽  
Piush Kanodia

Background: Neonatal period is a period from birth to under 28 days of life. The common causes of mortality and morbidity in our region are preventable, among which neonatal sepsis is the commonest one. Most of the deaths occur within 7 days of life. Objectives: To study the clinical profile, pattern of diseases, causes of morbidity and mortality amongst newborns. Materials and methods: A hospital based descriptive study was done among total 967 newborns including both inborn and out born admitted in NICU, NGMC from January 2016 to December 2016. Age, sex, gestational age, diagnosis at admission, outcome of admitted th newborns were the main variables under study. Data was entered in Excel and analyzed using SPSS 20th version. Data were presented through pie, bar graph and table with frequency and percentage. Results: Male were predominant in the study (65%). One third of the admitted newborns were preterms. Half of the admitted newborns were admitted on their first day of life. Neonatal sepsis was the most common cause of admission. Deaths occured in 7.4%of total babies. Seventy-six percent got improved after treatment. Only 2.8% were referred to higher center. Conclusions: Most of the neonates got admitted in first day of life with commonest cause being neonatal sepsis. Recovery rate was satisfactory. To reduce the mortality and morbidity of neonates, we need to increase awareness level in general population and proper aseptic practices in medical practitioners.


2019 ◽  
Vol 47 (2) ◽  
pp. 194-202 ◽  
Author(s):  
Rebecca Dresser

The revised Common Rule adopts the reasonable person standard to guide research disclosure. Some members of the research community contend that the standard is confusing and ill-suited to the research oversight system. Yet the revised rule is not as radical as it might seem. During the 1970s, judges started using the standard to evaluate negligence claims brought by injured patients who said doctors had failed to obtain informed consent to the harmful procedures. In its influential Belmont Report, the National Commission recommended application of a “reasonable volunteer standard” to guide IRBs evaluating research disclosures. Evidence also suggests that IRBs often invoke the reasonable person standard in deliberations about consent forms. But past application of the standard has been informal and uneven. Robust application of the reasonable person standard will require researchers and IRBs to learn more about what ordinary people want and need to know about the studies they are invited to join. Input from people with personal experience as study participants could be particularly useful to this effort.


2007 ◽  
Vol 2 (4) ◽  
pp. 80 ◽  
Author(s):  
Shelagh K. Genuis

A review of: Kuhlthau, Carol C. “Inside the Search Process: Information Seeking from the User's Perspective.” Journal of the American Society for Information Science 42.5 (1991): 361-71. Objective – To extend understanding of purposeful information seeking and to present a model of the information search process (ISP) from the perspective of the user. Design – Review of theoretical foundation, summing up of qualitative and quantitative data from a series of five foundational studies, and presentation of ISP model. Setting – Summarised research was conducted primarily in high school and college environments where subjects were investigating an assigned topic. A small proportion of public libraries were used in the fifth study within the reviewed series. Subjects – The ISP model as presented in this ‘classic’ article is based on studies involving a total of 558 participants. The first study involved 26 academically advanced high school seniors, and the 2 subsequent studies involved respectively 20 and 4 of the original participants following their completion of 4 years of college. The final 2 studies involved respectively 147 high, middle and low achieving high school seniors, and 385 academic, public and school library users. Methods – This paper presents the foundation for the ISP model by reviewing the relationship between Kelly’s personal construct theory, Belkin, Brooks, and Oddy’s investigation of cognitive aspects of the constructive information seeking process, and Taylor’s work on levels of information need (“Question-negotiation”) and value-added information (“Value-added”). This is followed by a review of Kuhlthau’s five foundational studies, which investigated the common information seeking experiences of users who were seeking to expand knowledge related to a particular topic or problem. The first of these studies was a small-scale exploration in which participants were given two assignments. Questionnaires, journaling, search logs, and reflective writing were used to collect data throughout the process of assignment completion. Data collection was augmented by case studies involving in-depth interviews and construction of timelines and flowcharts with six study participants. The six-stage ISP model was developed from qualitative content analysis of participants’ perceptions and experiences (Kuhlthau, “Library Research Process”). In the second study, the same questionnaire was used to determine how students’ perceptions of the ISP had changed over time. Post-college responses were compared to responses given in high school and statistical significance was determined through t Tests (Kuhlthau, Perceptions). Four of the original 6 case study participants were interviewed in the third study, in which interview data and search process timelines were compared with high school case studies (Kuhlthau, Longitudinal). In the fourth and fifth studies, large-scale field studies were conducted to verify the ISP model. Process surveys elicited participants’ thoughts and feelings at initiation, midpoint, and closure of a search task. Data were analysed using descriptive and inferential statistics including measures of significance and analysis of variance (Kuhlthau, Information Search; Kuhlthau et al.). Following a summation of these 5 research studies, this article details and discusses the ISP model. Main results – Based on the data from the five studies, the ISP presents a constructivist approach to information seeking and incorporates affective, cognitive, and physical dimensions at each of six information searching stages: initiation, topic selection, pre-focus exploration, focus formulation, information collection, and presentation. Individuals become aware of an information need at initiation. Feelings of uncertainty and apprehension are common as wide-ranging task exploration begins. At topic selection a general topic is selected and users frequently experience initial optimism, which is commonly followed by confusion and doubt as pre-focus exploration commences and users struggle to extend personal knowledge through initial investigation of the general topic. A turning point occurs during focus formulation as constructs become clearer and uncertainty decreases. During information collection the user is able to articulate focused need and is able to interact effectively with intermediaries and systems. Relief is commonly experienced at presentation stage when findings are presented or used. Although stages are laid out sequentially, Kuhlthau notes that the ISP is an iterative process in which stages merge and overlap. Central to this model is the premise that uncertainty is not due merely to a lack of familiarity with sources and technologies, but is an integral and critical part of a process of learning that culminates in finding meaning through personal synthesis of topic or problem. Conclusion – Kuhlthau provides evidence for a view of information seeking as an evolving, iterative process and presents a model for purposeful information searching which, if understood by users, intermediaries and information system designers, provides a basis for productive interaction. While users will benefit from understanding the evolving nature of focus formulation and the affective dimensions of information seeking, intermediaries and systems are challenged to improve information provision in the early formative stages of a search. Although Kuhlthau identifies this research on the ISP as exploratory in nature, this article affords methodological insight into the use of mixed methods for exploring complex user-oriented issues, presents a model that effectively communicates an approximation of the common information-seeking process of users, and provides ongoing impetus for exploring the user’s perspective on information seeking.


Sign in / Sign up

Export Citation Format

Share Document