Research Eval- Defintions Flashcards
Descriptive statistics:
used to characterize the shape, central tendency, and variability within a set of data, often with the intent to describe a population;
Measures of population characteristics are called parameters; A descriptive index computed from the sample data is called a statistic; Researchers utilize data
(statistics), to estimate population parameters.
External Validity
Ability to apply results obtained from a study population to a broader population. Also called generalizability.
Cohort Study
an epidemiologic investigation that follows groups with common characteristics over a specified period of time, strongest observational study design
Probability:
the likelihood that any one event will occur, given all the possible outcomes, shown as p.
Alternative hypothesis (Ha or H1)
The statement that establishes a relationship between variables being assessed
Biostatistics:
the branch of statistics that deals with data relating to living organisms; uses the tools of statistics to help answer research questions in medicine,
biology, and public health.
Ratio
characterized by the presence of absolute zero on the scale (no negative values); An absence of any of the trait being measured (e.g. ht/weight; Most precise
Quantitative Research:
follows logical positivism (logical controlled relationships between variables), Has numbers and real data and Can apply statistical evaluation. More objective.
Nominal
named categories with no implied order (classifications); Gender, race, ABO blood type, group; lowest level of data tyoe
Prospective Study
identify a group of people who are already taking a particular treatment or have an exposure, follow them forward over time, and then compare their outcomes with a similar group that has not been affected by the treatment or exposure being studied
A narrative in the professional literature that identifies a single incident and discusses pertinent factors related to the patient
Case-report (case-sudy)
Scientific Research:
the process of investigating facts and theories in a systematic way to examine relationships among clinical phenomena to generate evidence for decision-making.
Quasi-experimental studies:
degree of control limited by a variety of factors, but results remain obtainable.
Alternative hypothesis: AKA
the “research hypothesis”; Hypothesis stating the expected relationship between independent and dependent variables; If there IS
a statistically significant difference, then the researchers “ACCEPT” the alternative hypothesis and “REJECT” the null hypothesis.
Foreground Question
more common type of clinical question, focuses on specific knowledge to inform decisions about patient management (includes PICO).
Study Characteristics
Meta-analysis
A way of combining data from many different research studies. A meta-analysis is a statistical process that combines the findings from individual studies
A box plot graph is a useful way to….
Demonstrate visually the spread of scores in a distribution
Covariate
An extraneous variable that is statistically controlled in an analysis of covariance, so that the relationship between the independent and dependent
variables is analyzed with the effects of the extraneous factor removed.
Peer reviewed journals:
are scholarly journals that publish articles that have passed through this peer review process.
Impact factor:
measures how frequently a journal’s articles have been cited elsewhere in the previous 2 years.
Double blinding:
Allocation is concealed from both groups (researchers and subjects)
Sampling error
the tendency for sample values to differ from population values.
Measures of population characteristics are called
parameters
Frequency distribution:
a table of rank ordered scores that shows the number of times each value occurred.
Mode
represents the most commonly occurring score; May have two most common values = “bimodal distribution”; the most general and least precise measure
of central tendency
Correlation Coefficient:
Represented by “r ” (rho); The absolute value of the coefficient (its size, not its sign) tells you how strong the relationship is between the
variables; Tells us how strongly two variables are related; “r” can not be > 1 or < -1; Closer to -1 or +1: the stronger the relationship; Closer to 0 : the weaker the
relationship
Quasi-experiments:
In non-randomized controlled trials, the control group is predetermined (without random assignment) and compared to a control group
Null hypothesis (Ho):
The statement of no difference or no relationship between the variables
Chi Square
independence tests the null hypothesis that the variable are independent of each other; that there is no relationship between the two variable; does
not give any information about the strength of the relationship.
Relative risk
Basic risk statements express the likelihood that a particular event will occur within a particular population; Identifies what in our environment can
lead to beneficial or adverse medical outcomes; Relative risk measures the magnitude of an association between an exposed and non-exposed (control) group;is
calculated using cumulative incidence data to measure the probability of developing disease; Must have incidence information to calculate; Cohort or clinical trials
are conducted over time
Normative studies:
focus on establishing normal values for specific variables.
Meta analysis weaknesses
subject to bias based on the inclusion and/or exclusion criteria; Difficult and time consuming to identify appropriate studies; Not all studies provide adequate data for inclusion and analysis
Requires advanced statistical techniques; Heterogeneity of study populations; Age, gender, etc; Results are not always reproducible by other investigators; Subject to publication bias, selection bias, and misclassification bias; Can give a false sense of certainty regarding the magnitude of risk
Epidemiological Bias:
An incorrect assessment of the association between an exposure and an effect in the target population; Anything which erroneously
influences the conclusions about study groups and distorts comparisons
Variance (σ2 ):
quantifies the amount of variability, or spread, around the mean of the measurements; To calculate: take each difference from the mean, square it,
and then average the result
Explanatory Research:
utilizes various types of experimental designs to compare two or more conditions or interventions. These trials address both efficacy and effectiveness.
Basic Research:
Done in a lab to obtain empirical data used to develop, refine or test theor
Qualitative research definition:
Research dealing with phenomena that are difficult or impossible to quantify mathematically, such as beliefs, meanings, attributes, and symbols; it may involve content analysis
Incidence:
The proportion of people who develop a given disease or condition within a specified time period: The incidence of new COVID cases last week was 30. The prevalence of COVID in Bexar county was 300 cases out of 3 million.
Percentiles:
used to describe a score’s position within a distribution. Percentiles divide data into 100 equal portions. For example, if a student scores in 95th
percentile, that individual’s score was higher than 95% of those who took the test.
Independent Variable
The variable that is presumed to cause, explain or influence a dependent variable; a variable that is manipulated or controlled by the
researcher, who sets its “values” or levels.
Investigator and Interviewer Biases:
Lack of objectivity due to: beliefs, personality, personal involvement, etc.
Pragmatic Clinical Trial (PCT):
An effectiveness trial with a focus on real-world outcomes. Participants represent the patients that would typically receive treatment, and testing takes place in clinical practice settings. Outcomes focus on issues of importance to patients and stakeholders, including quality of life, cost, and implementation.
Systematic reviews:
are studies in which the authors carry out an extensive and focused search for research on a clinical topic, followed by appraisal and
summaries of findings, usually to answer a specific question.
Spearman Correlation:
non-parametric version of Pearson’s correlation. The calculation is based on the ranks of the data points of the x and y values; Can use if
variables aren’t normally distributed.
Paradigms:
Set of assumptions, concepts, or values that make a framework for reality
Confounder:
an extraneous variable whose presence affects the variables being studied so that the results do not reflect the actual relationship between the
variables under study. The aim of major epidemiological studies is to search for the causes of diseases, based on associations with various risk factors.
Epidemiology:
the study of the distribution and determinants of health-related events in specified populations and to apply this to control health problems.
Funding bias
Characterizing an association owing to the absence or withdrawal of financial and other types of support.
Cross-sectional Research:
Examines the relationship between outcomes and other variables of interest as they exist in a defined population at one particular point
in time; Simultaneous ascertainment of the exposure and the outcome; Determines prevalence (% of population) not incidence (rate); Enrolls a large number of
individuals. “The chicken or the egg?”: cannot show causality, does not separate cause/effect.
Cohort
a group of people who share a common characteristic or experience and all remain in the group for a period of time
Subject bias
Occurs when subjects or participants consciously or subconsciously act in a way they think they experiment or researcher wants them to act.
Confounding Variable
An extraneous variable that is related to the independent and dependent variable, but not in the causal pathway. Represents a form of bias.
Paradigm shift:
are fundamental transitions in the way disciplines think about priorities and relationships which stimulate change and approaches; in medicine: when we change the way we practice based on new clinical evidence.
Hawthorne Effect:
People may act differently when they know they are being watched
Measurement Error
The difference between the true value and the observed value.
Blinding:
: is the concealment of group allocation from one or more individuals involved in a clinical research study; Usually is used in research studies that compare
two or more types of interventions.
Information Bias:
Quality and extent of information is different for exposed person than for non-exposed person, a significant bias can be introduced.
interquartile range
The difference between the first and third quartile, represents the boundaries of the middle 50% of the distribution.
Prevalence:
the number of cases of a disease at a given point in time, expressed as a proportion of the total population at risk.
Pearson Correlation:
Most common measure of association. Results can be misleading if the relationship is nonlinear. Assumption is that both variables are normally distributed, very sensitive to outliers
Negative Predictive Value (NPV) :
Estimates the probability that a person who test negative is actually disease free.
Selection bias
Inappropriate selection of study participants that may lead to an erroneous association between an exposure and outcome.
Phase III trials:
compares the new treatment with standard care, larger group of patients.
Likelihood ratio:
Summarizes the same type of information as sensitivity and specificity, but can be used to calculate the probability of disease in a low prevalence setting.
Retrospective Study
start with a cohort and go back in time to evaluate past exposures to risk factors
Longitudinal Research:
researcher follows a cohort of subjects over time, performing repeated measurements at prescribed intervals
Case-crossover
A variant of a case-control study; Each case becomes their own individual control; Used for transient exposures during a discrete occurrence
Standard deviation (σ):
a measure of variation of scores about the mean; To calculate: take the √ of the variance; (the “average distance” to the mean); In practice,
the standard deviation is used more frequently than the variance; Primarily because the standard deviation has the same units as the measurements of the mean;
When comparing two groups, the group with the larger standard deviation exhibits a greater amount of variability (heterogeneous) while the groups with smaller
deviation has less variability (homogeneous).
Positive Predictive Value (PPV) :
Estimates the likelihood that a person who tests positive actually has the disease.
Distribution:
the total set of scores for a particular variable
Single blinding :
Allocation is concealed from only one group (researchers or subjects)
Specificity
The proportion of people without the disease who have a negative test; The ability of the test to identify correctly those who do not have the
disease; Screening test’s ability to truly identify absence of disease; A highly useful test when it is POSITIVE; High Specificity means low probability of a false
positive; With high Specificity, a Positive test rules in disease
Systematic Reviews and Meta-analyses are used to generate
practice guidelines
Misclassification Bias
Occurs when those that have the disease are mistakenly put in the control group, or those who really don’t have the diease are classified as cases.
Variability:
dispersion of scores
Relative Risk Reduction:
The percentage difference in outcome between control (C) and experimental (E) groups; Absolute Risk Reduction: The actual reduction in
events in the treated group (EER)
a risk factor for the disease independent of the exposure and is not part of the causal link between
the exposure and the disease.
Confounder
Qualitative Research:
follows social constructivism, tries to capture naturally occurring phenomena through Focus groups, Interviews, surveys, discussion and observation. May be subjective and is considered descriptive in design.
Multiple Controls:
Employ multiple control groups. Offers independent estimates of exposure among different samples of non-cases. Increases strength of the study.
Critical Appraisal:
purpose is to determine the scientific merit of a research report and its applicability to clinical decision making.
Statistical power:
The probability of finding an effect; The probability of correctly rejecting the null hypothesis; The probability of seeing a true effect if one exists
n :
n : the total number of scores in the distribution is given the symbol n = 48.
Cumulative Incidence
quantifies the number of individuals who become diseased during a specific time period
Prospective
identify a group of people who are already taking a particular treatment or have an exposure, follow them forward over time, and then compare
their outcomes with a similar group that has not been affected by the treatment or exposure being studied
Mean
the “average” – computed by summing the values of several observations and dividing by the number of observations.
Experimental Research
researcher manipulates and controls one or more variables and observes the resultant variation of other variables; provide a basis for comparing two or more conditions to determine cause and effect relationships.
Lost to follow up bias
Occurs when subject leaves a study at different based on exposure status.
Pretest probability :
is the chance that the patient has the disease, estimated before the test result is known; based on the probability of the suspected disease in
that person given their symptoms.
Confounding variable:
an outside influence that changes the effect of a dependent and independent variable. This extraneous influence is used to influence the
outcome of an experimental design. Simply, a confounding variable is an extra variable entered into the equation that was not accounted for.
Observational research:
phenomena are observed rather than manipulated.
Non-inferiority trial
done to show that the new treatment is as good as the standard (maybe it has less side effects).
Researcher/Observer Bias:
Occurs when the researcher/observer evaluates cases vs controls differentially
Case-Cohort:
Same as nested case-control design, except controls are randomly chosen from the cohort at the beginning of the study.
Intrarater reliability
refers to the stability of data recorded by one individual across two or more trials.
Sensitivity
The proportion of people with the disease who have a positive test for the disease; The ability of the test to identify correctly those who have the
test; A test with high sensitivity will not miss many patients who have the disease; With high Sensitivity, a Negative test rules out disease
MeSH heading:
Medical subject headings, provide a consistent search vocabulary in a set hierarchal tree.
Scoping Reviews:
includes a review of literature but with a broader focus on a topic of interest to provide direction for future research and policy considerations.
Meta-analysis strengths
Pooling of data strengthens statistical power; Confirmatory data analysis; Greater ability to extrapolate to the general population
Applied research
Directed toward solving immediate practical problems with functional application s
Descriptive Research:
Observes associations, Show patterns of disease occurrence, Natural history of disease; Helps to generate hypothesesExamples: developmental research, normative studies, qualitative research, case study, and case series.
Reliability:
Degree to which the measurements are reproducible
Non-experimental Research
refers to investigations that are generally more descriptive or exploratory in nature and that exhibit direct control over the studied
variables.
Evidence-based practice
or evidence-based medicine: the principle of making sound clinical decisions based on the best current medical evidence; The practice of health care in which the practitioner systematically finds, appraises, and uses the most current and valid research findings as the basis for clinical decisions; is a systematic approach to clinical problem solving which allows the integration of the best available research evidence with clinical expertise and patient values.”
Constructs
concepts that represent nonobservable behaviors or events, invented names for variables that cannot be seen directly, but are inferred by measuring relevant or correlated behaviors that are observable, for example, Intelligence.
Randomized” Allocation/Assignment:
The main purpose of randomization is to prevent any potential biases on the part of the investigators from influencing the
assignment of participants into different treatment groups.
Effect size
A statistical expression of the magnitude of the difference between two treatments or the magnitude of a relationship between two variables.
Translational Research
refers to the application of basic scientific findings to clinically relevant issues, and simultaneously, the generation of scientific questions based on clinical dilemmas.
Clinical Research:
a structured process of investigating facts and theories, producing validated results.
Fisher’s exact test:
A non-parametric test similar, similar to the chi-square tests, but can be used with small or sparsely distributed data sets.
Type II error
also known as an acceptance error or an β error; A Type 2 error is made if we fail to reject null hypothesis when the null hypothesis is false; The
probability of committing a type II error is represented by the Greek letter β
Quartiles:
divide a distribution into four equal parts, or quarters (25%, 50%, 75% of distribution)
Subject Biases:
Lack of objectivity due to: wanting to please investigators, ideas about treatments, personal involvement, failure to report negatives, etc.
Superiority trial:
compares one treatment to another directly.
Intent to treat analysis:
Compares subject outcomes based on their original group assignment even if they dropped out or were non-compliant; Primary reason is
to preserve randomization
Peer review:
the process by which an author’s peers read and evaluate a paper (article) submitted for publication and recommend whether the paper should be
published, revised, or rejected. Peer review is a widely accepted indicator of quality scholarship.
Case-Control:
Studies in which patients who already have a specific condition (cases) are compared with people who do not have the condition (controls).
Surveillance bias
Occurs when outcome ascertainment is better in a monitored population than in the general population. Can lead to erroneous statistical
estimates.
Efficacy:
the benefit of an intervention as compared to a control, placebo, or standard program, tested in a carefully controlled environment, with the intent of establishing cause-and-effect relationships.
Quasi-Experimental Designs:
Comparative designs that do not have a control group or randomization. Includes time-series designs that allow for repeated
measurements over prolonged periods to document trends.
Case-series:
study that analyzes a number of individual cases that share a commonality
Exploratory Research:
Using principles of epidemiology, observational designs used to examine a phenomenon of interest and explore its dimensions, often in populations or communities, to examine how it relates to other factors, and to predict risks or preventive strategies. Also used to establish associations between variables and to carry out methodological research to assess validity and reliability. Examples: cohort studies, case-control studies, methodological studies and historical research.
Internal Validity:
Within the confines of the study, results appear to be accurate and the interpretations of the investigators is supported.
Scientific Method
a systematic, empirical, and controlled critical examination of hypothetical propositions about the associations of natural phenomena.
Single-Subject Designs
Systematic study of one or more subjects with repeated measurements under controlled and experimental conditions to
show changes in responses with and without intervention, or comparing more than one intervention.
Retrospective
start with a cohort and go back in time to evaluate past exposures to risk factors
Empirical
documentation of objective data through direct observation.
Meta-analysis:
are systematic reviews that use quantitative methods to summarize the results from multiple studies; used in the construction of practice guidelines.
Observer bias
Systematic difference between a true value and the observed value due to observer variation.
Median
represents the 50th percentile in a ranked distribution of scores; that is, that point at which 50 percent of the score fall below and 50 percent above.
Number Needed to Treat:
The number of patients who need to receive the new intervention instead of the standard alternative in order for one additional patient
to benefit; Formula: NNT= 1/ARR; Expresses the likelihood of the treatment to benefit an individual patient
Voluntary Reponses Bias:
Arises when case subjects who think they have been exposed to responds at a higher rate to controls
Nested Case-Control:
A case control study within a large cohort; typically seen with large enrollment studies; Controls are a sample of individuals who are at risk
for the disease/outcome at the time each case of the disease develops
Confounding
is often referred to as a “mixing of effects”1 wherein the effects of the exposure under study on a given outcome are mixed in with the effects of an additional factor (or set of factors) resulting in a distortion of the true relationship.
Bias
a general statistical term meaning a systematic (not random) deviation from the true value
Background question:
related to etiology or general knowledge about a patient’s condition, cause of a disease or condition, history, signs and symptoms, or the mechanisms that relate to pathophysiology.
Selection Bias: Lost to follow up
People with disease are selectively lost to follow-up, and those lost to follow-up differ from those not lost to follow-up.
Regression analysis
A method of predicting change in the dependent variable by changing one or more independent variables
Randomized Control Trial RCT:
An efficacy trial involving the controlled comparison of an experimental intervention and a placebo, sham, or usual care. Through random assignment and restricted subject selection, the design controls for bias to allow cause and effect conclusions.
The five steps of Evidence-based practice:
- Ask a clinical question, 2. Acquire relevant literature, 3. Appraise the literature, 4. Apply findings to clinical decision-
making, and 5. Assess the success of the process.
Dependent Variable
A response variable that is assumed to depend on or be caused by another (independent) variable; outcome of interest
Effectiveness:
the benefits of procedures under “real-world” conditions in which circumstances cannot be controlled within an experimental setting.
McNemar’s Test for Matched Pairs:
Is a type of chi-square test used when the data comes from paired samples.
Intention-to-treat (ITT) analysis: i
: includes every subject who is randomized according to randomized treatment assignment. It ignores noncompliance, protocol
deviations, withdrawal, and anything that happens after randomization. ITT analysis maintains prognostic balance generated from the original random treatment
allocation.
Quantitative research definition:
Research involving formal, objective information about the world, with mathematical quantification; it can be used to describe test relationships and to examine cause and effect relationships.
Matching
Process of selecting the controls so they are similar to the cases in certain characteristics, such as age, race, sex, socioeconomic status, and occupation;
can be individual or group based.
Ordinal
sequenced or ranked data; Smallest to largest, lightest to heaviest, easiest to most difficult
Random Errors
are due to chance and can effect a subjects’ measurement in a unpredictable way.
Equivalence trial:
done to show the new drug is no more or less effective than the standard (generics).
T-Test:
Used to analyze continuous data, compares the means and standard deviations of two populations, assesses whether a difference between groups’ averages is unlikely to have occurred because of random chance in sampl selection
Prospective Research:
Variables are measured through direct recording in the present.
Type I error
also known as a rejection error or an α error; A type I error is made if we reject the null hypothesis when null hypothesis is true.
Range
The simplest measure of variability; the difference between the highest and lowest values in a distribution.
Retrospective Research:
Involves the examination of data that has been collected in the past, often obtained from medical records, databases, and surveys.
Histogram:
a bar graph, composed of a series of columns, each representing one score or class interval.
Recall Bias (Subject Bias):
main form of information bias in case-control studies. Occurs when there is differential recall of exposure between cases and controls;
The possible inaccuracy of recalling medical history or previous exposures; of particular concern in retrospective studies.
The five steps of the research process:
Identify the research question, design the study, implement the study, analyze the data and disseminate the findings.
Phase I trials
Looks at treatment safety in small groups.
Number Needed to Harm:
When an experimental treatment is detrimental, the term number needed to harm (NNH) is often used; The equations and approach
are similar to those described above, except that NNH will have a negative absolute risk reduction
Variables:
when concepts are assigned values and they can be manipulated so that their relationships can be examined.
Concepts:
abstractions allowing the classification of natural phenomena and empirical observations (eat, play, food.
Publication bias
Tendency of researchers and editors to treat positive results differently from negative or inconclusive results, often with a preference for
publication of positive findings.
Null hypothesis:
If there IS a statistically significant difference, then the researchers must “REJECT” the null hypothesis; If there IS NOT a statistically significant
difference, then the researchers must “RETAIN” or “FAIL to REJECT” the null hypothesis.
Phase IV trials:
Post-marketing, after the drug is approved, these look at long-term use.
Triple blinding:
Allocation is unknown to the subjects, the individuals who administer the treatment or intervention, and the individuals who assess the outcomes.
Phase II trials:
explores efficacy by measuring relevant outcomes, can be expanded to IIa and IIb.
Power analysis:
calculates the number of participants a study must have to draw accurate conclusions
Significance:
The probability of rejecting a true H0; α = .05 usually set, acceptable error (5% risk); Chance that 5 times out of 100 the H0 would be falsely rejected;
Means there is a 5% chance that the results happened by chance; Allows us to reject or accept the null hypothesis.; I.e. we said that someone has a disease,
when they really don’t.
Confidence interval (CI):
More important than the p value – a better determination of significance; Any statistic is simply an estimate of the true value of that
statistic; CI produces a range within which the true value most likely lies; 95% CI states that we can be 95% certain that the “true” value is within the CI range;
Narrower CI is better; If the CI includes 1 (null value) then the results is statistically insignificant.
