Abstract
Medical statistics deals with applications of statistics to medicine and the health sciences including epidemiology, public health, forensic medicine, and clinical research.
Access provided by Autonomous University of Puebla. Download chapter PDF
Similar content being viewed by others
Keywords
- Randomized controlled trials
- Cohort studies
- Case-control studies
- Case studies
- Meta-analyses
- Validity
- Sensitivity
- Specificity
- Odds ratio (OR)
Randomized Controlled Trials
-
Has high internal validity
-
Reduced risk of confounding variable
-
Reduced external validity
-
Expensive, time-consuming variables
Cohort Studies
-
Useful for sequential events
-
Can study multiple outcomes from exposures
-
Retrospective: less expensive
-
Require large sample size
-
Risk of confounding variables
-
Difficult to study rare outcomes
-
Prospective: expensive
Case-Control Studies
-
Useful for rare outcomes
-
Can study several exposures
-
Inexpensive
-
Risk of confounding variables
Cross-Sectional Studies
-
Can study multiple outcomes and exposures
-
Cannot infer causality
-
Risk of confounding variables
-
Less useful for rare exposures or outcomes
Case Studies
-
Useful for rare outcomes
-
Convenient and inexpensive
-
Lack of a comparison group
-
Cannot infer causality
-
Risk of confounding variables
Systematic Reviews
-
Summarize existing studies descriptively
-
A descriptive results section summarizing the findings and addressing the qualities of the included studies
Meta-analyses
-
Use statistics to combine the results from each included study and generate a single summary statistic
-
Compilation of evidence that potentially has greater power to inform clinical decisions than would an individual study in the systematic review or meta-analysis
-
If the quality of the studies included in the systematic review or meta-analysis is poor, the summary conclusions are similarly inadequate
-
Case Reports
-
Aid in recognizing and describing new disease processes or rare manifestations
-
Describe the disease in the context of comorbidities and individual characteristics
-
Identify drug adverse effects
-
Help to illustrate the diagnostic process and help students apply the literature to an individual patient
-
Help identify emerging health conditions
-
Show how exposures and disease outcomes are related
-
Can stimulate important research questions and help guide hypotheses
-
Are purely descriptive and one of the weakest forms of evidence
-
Cannot be used to make inferences about the broader population
-
Cannot prove causality
Anecdotal Evidence
-
A clinician’s personal experience
-
Shares some characteristics with case reports
-
Lacks the strength of data collected via rigorous methodology that also involves significant numbers
anecdotal evidence can suggest hypotheses and leads to the creation of credible studies
Descriptive Epidemiologic Studies
-
Follow up on case reports
-
Used to describe patterns of disease in the population according to person, place, and time
-
Do not test a predefined hypothesis or determine a cause-and-effect relationship
-
Used to develop hypotheses for subsequent analytic studies
-
Use a variety of tools, including surveillance reports, cross-sectional analyses, and surveys
Validity
-
Addresses whether an instrument or test actually measures what it is intended to measure
-
Criterion validity is the degree to which the measurement correlates with an external criterion or another instrument or test that is considered valid
-
Convergent validity is the degree to which independent measures of the same construct are highly correlated
-
Predictive validity is the ability of an instrument or test to predict some future criterion
-
Discriminant validity requires that an instrument or test shows little or no correlation with measures from which it differs
-
-
Content validity refers to the extent to which aspects of items that make up an instrument or test are representative of a particular construct
-
Face validity is a judgment about whether elements of an instrument make intuitive sense
-
Sampling validity refers to whether the instrument incorporates all of the aspects under study
-
Reliability
-
The consistency or repeatability of scores
-
Test–retest reliability assesses whether an instrument or test yields the same results each time it is used with the same study sample under the same study conditions
-
Internal consistency reliability is a measure of the consistency of the items within a test
-
Interrater reliability is the degree to which two raters independently score an observation similarly
Sensitivity: Screening
-
Probability of correctly identifying those who truly have the disease
-
True positives/disease
-
TP/(TP + FN) (Fig. 1)
Specificity: Confirmation
-
Probability of correctly identifying those who do not have the disease
-
True negatives/disease
-
TN/(FP + TN)
Positive Predictive Value (PPV)
-
Probability of correctly identifying those who truly have the disease amongst those whose tests are positive
-
True positives/test
-
TP/(TP + FP)
Negative Predictive Value (NPV)
-
Probability of not having the disease given a negative test
-
True negatives/test
-
TN/(FN + TN)
Predictive values are dependent on the prevalence of the disease. The higher the prevalence of a disease, the higher the PPV of the test.
p Value
-
The p value is the probability of obtaining a test statistic result at least as extreme as the one that was actually observed, assuming that the null hypothesis is true.
-
A researcher will often “reject the null hypothesis” when the p value turns out to be less than a predetermined significance level, often 0.05 or 0.01. Such a result indicates that the observed result would be highly unlikely under the null hypothesis.
-
Many common statistical tests, such as chi-square test or Student’s t test, produce test statistics which can be interpreted using p values.
-
An informal interpretation of a p value, based on a significance level of about 10 %, might be:
-
p ≤ 0.01: very strong presumption against null hypothesis
-
0.01 < p ≤ 0.05: strong presumption against null hypothesis
-
0.05 < p ≤ 0.1: low presumption against null hypothesis
-
p > 0.1: no presumption against the null hypothesis
-
False Positive
-
A false positive occurs when the test reports a positive result for a person who is disease free.
False Negative
-
A false negative occurs when the test reports a negative result for a person who actually has the disease.
Odds Ratio (OR)
-
Calculates the relative risk (RR) if the prevalence of the disease is low. It can be calculated for case-control study (retrospective study)
-
The OR can be used to determine whether a particular exposure is a risk factor for a particular outcome and to compare the magnitude of various risk factors for that outcome
Relative Risk (RR)
-
Disease risk in the exposed group divided by disease risk in unexposed group. It can be calculated for cohort study (prospective study)
-
The 95 % confidence interval (CI) is used to estimate the precision of the OR
-
If the 95 % CI for OR or RR includes 1, the study is inconclusive
-
A large CI indicates a low level of precision of the OR, whereas a small CI indicates a higher precision of the OR
-
For a rare disease, OR approximates RR
Suggested Readings
Perry-Parrish C, Dodge R. Research and statistics: validity hierarchy for study design and study type. Pediatr Rev. 2010;31:27.
Hernandez RG, Rowe PC. Research and statistics: cohort studies. Pediatr Rev. 2009;30:364.
Moore EM, Johnson SB. Research and statistics: case reports, anecdotal evidence, and descriptive epidemiologic studies in pediatric practice. Pediatr Rev. 2009;30:323.
Copeland-Linder N. Research and statistics: reliability and validity in pediatric practice. Pediatrics in Review. 2009;30:278.
Palaia A. Research and statistics: study design and data sources. Pediatrics in Review. 2013; 34:371.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Kukoyi-Maiyegun, S. (2015). Research and Statistics. In: Naga, O. (eds) Pediatric Board Study Guide. Springer, Cham. https://doi.org/10.1007/978-3-319-10115-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-10115-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10114-9
Online ISBN: 978-3-319-10115-6
eBook Packages: MedicineMedicine (R0)