Class 9: research 1 Flashcards
what is the best form of evidence
Meta anaylsis
what is the wrost type of evidence
case studies and cade reports
what are the next best two type of studies
systematic review
RCT
what is the difference between meta anayalsis and systematic review
Meta-Analysis: Statistics is performed
Systematic reviews: Statistics is NOT performed
what is a RCT
Determine efficacy of
intervention, participants are randomly allocated into different
groups to help minimize bias
what are Cohort Studies:
Observational study that compares a cohort who share a common characteristic; with and without the exposure.
what are Case Control Studies:
Compares a group of individuals with a specific condition with a group of people without the same condition
(controls).
Cross Sectional Studies:
Observation study where data is collected from a population or a representative subset at a single point in time.
Unlike cohort studies or longitudinal studies, which follow
participants over an extended period, cross-sectional studies provide
a “snapshot” of information at a specific moment.
Longitudinal Studies:
Observational study involving repeated observations or measurements of the same individuals or groups
across extended time periods to understand the patterns and factors
influencing those changes.
what is the purpose of cross sectional studies
Estimate the prevalence of
diseases, health behaviors and
explores associations between
variables at a specific point in time.
what is the purpose of Longitudinal study
Examines development of traits,
behaviors, or outcomes over time
and develops cause-and-effect
relationships
Case Series/Case Reports:
Document clinical case of a single
patient or a series of patients
what is Qualitative Research
Collecting and analyzing non-numerical data
QuaLitative: Love (emotions)
(categorical data)
what are some examples of Qualitative Research
Analysis of text, video, audio,
observation, questionnaires, interviews
to understand concepts, opinions,
experiences, emotions
what is Quantitative Research
Collecting and analyzing numerical data
QuaNtitative: Numbers
example of Quantitative Research
Analysis of quantifiable outcome
measures
Quantitative Research stat?
yes
Qualitative Research stat?
Statistical analysis is NOT performed
types of Qualitative research
Nominal and Ordinal
Nominal
- Data that can be labelled or
classified into mutually exclusive
categories within a variable - Used to label variables without any
quantitative value - Ex. Gender, blood types
Ordinal
- Data measured in rank
- Order of the variables matters
- No quantifiable differences between
subsequent ranks - Ex. MMT grades, level of assistance,
joint laxity grades
what is Interval
- Data where the difference
between two values is
meaningful - Hold no true zero and can
represent values below zero - Ex. Temperature, IQ test score
what is ratio
- Has all the properties of an
interval variable and a clear
definition of true zero - Highest level of measurement
- Ex. Height, money, age, weight
RatiO: True 0
what is Reliability
- Consistency of an instrument or measure
- Extent of the research instrument to consistently have the same
results when used in the same situation on repeated occasions
Intra-rater:
Test performed by 1 person several times
Inter-rater:
- Test performed by 2 or more individuals on different subjects for testing 1 variable
Test-retest reliability:
Same test to the same individuals on two occasions
same score with each measurement on something that should stay the same over time
what is Validity
- Consistency of an instrument or measure
- Extent to which the instruments used in the experiment measure
exactly what you want them to measure
what is the strongest type of validity
Concurrent validity:
what is Concurrent validity:
Test performed and compared to the GOLD standard test and
results are matched
Ex. Heart rate measured by peripheral pulses and compared with
ECG readings
what is Content validity
Test should measure specifically what the patient problem is.
Ex. For testing functional balance/fall-risk, Timed up and GO test
can be used
Extent to which test accurately assesses what it’s supposed to assess
what is Construct validity
Test should measure what it’s supposed to measure
Ex. Goniometer should measure ROM only (nothing else)
What the test is supposed to measure?
what is the weakest form of validity
Face validity
what is Face validity
- The outcome measure should measure what is looks like it will
measure related to patient problem - Weak form of validity, does NOT consider the gold standard of
measurement - Ex. Survey to measure the regularity of dietary habits
What the test APPEARS to measure?
what is type 1 error
When you incorrectly reject a
true null hypothesis. This would
be a “false positive.”
man - you are pregnant
“I” can be converted to “P”
what is type 2 error
Failing to reject a false null
hypothesis. This would be a
“false negative.”
pregnant women - you are not pregnent
“II” can be converted to “N”
Sensitivity:
̶Helps in ruling conditions “out” (SnOut)
̶Few false negatives
Specificity:
̶Helps in ruling conditions “in” (SpIn)
̶Few false positives
what are Clinical Prediction Rules (CPRs)
are tools designed to improve
decision making in clinical practice by assisting practitioners in
making a particular diagnosis, establishing a prognosis, or matching
patients to optimal interventions based on a parsimonious subset of
predictor variables from the history and physical examination.
wainner’s, Ottowa ankle rules
what is the * Dependent Variable:
Is the outcome or variable of interest in an experiment or study.
what is the Independent Variable:
Variable that is manipulated or changed by the researcher to observe its effect on the dependent variable.
what is the Covariate:
Considered as an independent variable in an analysis
but is not of primary interest. It is a potential source of variation
or confounding factor that potentially influences the dependent
variable.
what is the Null Hypothesis:
No significant differences in group means.
what is the Alternative Hypothesis:
Significant differences in group means.
Parametric
Equal distribution - Bell shaped curve: Normal distribution
Randomization of sample
Quantitative data
(Usually interval, ratio)
More powerful
Non-Parametric
Unequal distribution - Skewed curve: Non-normal distribution
No randomization of sample
Qualitative data
(Usually nominal, ordinal)
Less powerful than parametric
what are three types of parametric test
T-test
Analysis of Variance (ANOVA):
ANCOVA:
T-test
statistical tool that determines if the difference between two groups’ means is statistically significan
Analysis of Variance (ANOVA):
at least 3
Non-Parametric Test
Chi square test:
Mann Whitney U test:
Kruskal Wallis test:
Chi square test:
- Use of nominal/categorical data to find difference between groups
- Ex. 20 males vs 30 females
Mann Whitney U test:
- Use of continuous or ordinal data to test the null hypothesis with two
independent samples from the same population - Similar to Independent samples t-test
Kruskal Wallis test:
- Three or more groups compared
- Similar to One-way ANOVA
Internal consistency
a statistical measure that indicates how well a set of items on a test or survey are measuring the same thing
Bell curve
68
95
99.7
what si the best test for inteventions
randomized control trial
does a cohort study have an intervention
no it is a observational study
does a cross sectional study have a intervention
no it is an observational study
is a cohort study a longitudinal study
yes
what are examples of observational studies
cohort
cross sectional
case- control
are long study prospective or retro
prospective
what are the types of long studies
cohort
case control
what is the difference between cohort and case control studies
cohort - incidence of disease in response to exposure
case control - risk factor analysis
what are the two classification for quantitative data
discrete - interval and ratio
continous - interval and ratio
what is discrete
something that you can count - whole numbers
what is continous
something that you can measure - decimals
measure the amount of weight- 124.2
what are the three types of reliability
intra
inter
test restest
what is an important factor for test retest relaibility
time
Same test to the same individuals on two
occasions
content vs construct validity
content - lookst at the domains of the test
construct - looks at the tools, only measuring what it is supposed too
what are some example of thing that use face validity
survery or questionairres
this based off judgement
what does dysphalgia mean
hard time swallowing