Statistic Terms Flashcards
Clinical significance
The practical importance of a treatment effect—whether it has a real, genuine, palpable, noticeable effect on daily life. It was originally anchored to the patient’s perception but has since expanded beyond this boundary.
Clinical trial
Any research study that prospectively assigns human participants or groups of humans to one or more health-related interventions to evaluate the effects on health outcomes. Clinical trials are divided into four phases which are designed to keep patients safe and to answer dedicated questions about the eficacy or effectiveness of an intervention.
Confidence intervals
A range of values so deined that there is a speciied probability that the value of a parameter lies within it.
Data
Recorded factual material commonly retained by and accepted in the scientiic community as necessary to validate research indings.
Effect Size
This is the magnitude of an intervention relected by an index value. It can be calculated from the data in a clinical trial and is mostly independent of sample size. Most interventions have small to moderate effect sizes.
Effectiveness
The performance of an intervention under “real-world” circumstances.
Efficacy
The performance of an intervention under ideal and controlled circumstances.
False negative
A test result which incorrectly indicates that a particular condition or attribute is absent.
False Positive
A test result which incorrectly indicates that a particular condition is present.
Fidelity
This is described two ways. The extent to which delivery of an intervention adheres to the protocol or program model originally developed and how close the intervention relects the appropriateness of the care that should be provided.
Implementation Science
The science of putting (executing) a project or a research inding into effect.
Methodology
Within the research domain, this relects the speciic procedures or techniques used to identify, select, process, and analyze information about a research topic.
Minimally clinically important difference
The smallest difference in score in the domain of interest which patients perceive as beneicial and which would mandate, in the absence of troublesome side effects and excessive cost, a change in the patient’s management.
Outcomes research
A broad umbrella term without a consistent de nition. However it tends to describe research that is concerned with the effectiveness of public-health interventions and health services.
P value
The probability, under an assumption of no difference in groups of obtaining a result equal to or more extreme than what was actually observed. Usually depicted at 5%.
Personalized medicine
Within research, this involves the study of tailoring of medical treatment to the individual characteristics of each patient.
Precision medicine
A form of medicine that uses information about a person’s genes, proteins, and environment to prevent, diagnose, and treat disease.
Reliability
This is measured in several ways. It is the degree to which the result of a measurement, calculation, or speciication can be depended on to be precise.
Statistical assumptions
Characteristics about the data that need to be present before performing selected types of inferential statistics.
Statistical significance
Refers to the claim that a result from data generated by testing or experimentation is not likely to occur randomly or by chance, but is instead likely to be attributable to a speciic cause.
Statistics
The practice or science of collecting and analyzing numerical data in large quantities, especially for the purpose of inferring proportions in a whole from those in a representative sample.
True negative
A test result that accurately indicates a condition is absent.
True positive
A test result that accurately indicates a condition is present.
Variable
A variable, or data item, is any characteristic, number, or quantity that can be measured or counted.
Validity
The extent that the instrument measures what it was designed to measure. There are multiple types of validity, each representing a different construct.
Nominal
Two categories, such as “yes or no”, boy or girl
Ordinal
Has order but not rank. Such as strongly agree, agree, disagree, and strongly disagree
Interval
Has rank and order. 1-4, 5-8, 9-12, etc.
Ratio
Has rank, order, and is countable. Examples include weight, temperature, or age.
Parametric versus non parametric
Parametric tests are used when data are normally distributed. Nonparametric tests are also called distribution-free tests because they don’t assume that your data follow a speciic distribution. They also can be used with smaller sample sizes, and when you want to be more conservative with your analyses. Parametric analyses test group means, whereas, nonparametric analyses test group medians.
Sensitivity
The proportion by percentage of patients who have the disease of interest who register a positive test inding
Specificity
The proportion by percentage of patients who do not have the disease of interest who register a negative test inding
Positive predictive value
Positive predictive value is the probability that subjects with a positive screening test truly have the disease
Negative predictive value
Negative predictive value is the probability that subjects with a negative screening test truly don’t have the disease
Positive likelihood ratio
A positive likelihood ratio (LR+) relects the probability of a patient with the disease and a positive test divided by the probability of a patient without the disease and a positive test. It is commonly used to rule in a condition.
Negative likelihood ratio
A negative likelihood ratio (LR-) is the probability of a person who has the disease testing negative divided by the probability of a person who does not have the disease testing negative. It is commonly used to rule out a condition.
Accuracy
The accuracy of a test can be calculated by examining the proportion of true positive and true negative in all evaluated cases. Accuracy=TP+TN / TP+TN+FP+FN
Type 1 error
A type 1 error is also known as a false positive and occurs when a researcher incorrectly rejects a true null hypothesis. This means that your report that your findings are significant when in fact they have occurred by chance.
Type 2 error
A type II error is also known as a false negative and occurs when a researcher fails to reject a null hypothesis which is really false. Here a researcher concludes there is not a significant effect, when actually there really is.
Norm referenced
Standard point scores
Compares individual performance with group performance
Normal distribution of scores desired
Maximizes differences among individuals
Requires diagnostic skills of the examiner
May not be sensitive to effects of therapy or instruction
Not concerned with task analysis
Summative
Criterion referenced
Cutoff scores
Compares performance with described criteria
Variability of scores not obtained, mastery of skills desired
Discriminates between successive performances of one individual
Provides information to plan therapy/instruction
May be sensitive to effects of intervention
Depends on task analysis
Formative
Construct validity
is the measure accurately representing the trait to be studied
Concurrent validity
two tests administered at the same time to determine correlation
Criterion related validity
the degree to which the characteristic in question correlates with other indicators or criterion measures
Content validity
relationship between test items or rating and the definition of the construct to be tested
Predictive validity
correlation between one measure taken at a particular time to another measure taken at some future time
Responsiveness
ability to measure to detect a clinical change. Depends on sensitivity to change
Standard error of measurement
Function of a test’s reliability. Measures how much a child’s observed score is expected to vary even when the child doesn’t change: 95% of scores will fall +/-2 standard errors.
Confidence interval
Gives range within which 95% of a test score will fall. Usually use 90 or 95%
Minimum detectable change
Smallest difference in scores that would be greater than by change alone. Important for determining change over time or with specific intervention.
Item response theory
methods of constructing tests that differentiate the difficulty of items and how well the items can detect differences among subgrounds
Rasch analysis
one type of IRT. These methods test the reliability, validity, and item difficulty with individuals from subgroups such as children with disabilities.