Exam 1 Review Flashcards
Treatment effectiveness is demonstrated when there is is clinical improvement from the treatment in the
Real-world context
Compares two or more conditions to determine a cause and relationship and allows the researcher to draw conclusions about observed differences
Experimental research
If you have a highly homogenous distribution of participant scores you will likely have a
Small standard deviation
An occupational therapist is attempting to determine the treatment efficacy for a previously developed method of intervention for spastic dysarthria. In order to determine an accurate measure of treatment efficacy, he should research
META-ANALYSIS AND SYSTEMATIC REVIEWS Meta-analyses and systematic reviews that synthesize the
_______ _______ would occur if a first treatment condition affected participant performance on a second treatment condition
Carryover effect
if a research participant’s performance in a study was influenced by their awareness of being in a research study
Hawthorne effect
potential change in data that occurs sometime from the beginning to the end of an experiment. These changes can arise due to factors such as participant fatigue or familiarity with assessment and/or intervention materials.
Order effect
clinical decision based on research evidence, clinical expertise, patient values and preferences, and clinical circumstances.
Evidence based practice
should include a study design, criteria for selecting participants, how she selected her participants, description and number of participants, measurement techniques, data collection techniques, and data analysis procedures
Methods section
should include a narrative description of statistical outcomes, tables and figures that summarize findings, and statements that support or reject the hypothesis
Results section
◦To establish the measure as having good reliability, it should have:
High reliability coefficient and a low standard of error
If a researcher is analyzing data collected during his research study and has found that p<.05, he may decide to reject the
Null hypothesis
refers to how well a test detects a condition that is actually present
Test-sensitivity
there is a normal distribution of data in this statistical procedure
parametric statistical procedures
Any factor that is NOT directly related to the purpose of the study, but may affect the dependent variable. When these factors are not controlled, they exert a confounding influence on the independent variable, that is they contaminate the independent variable in such a way that their separate effects are obscured.
◦Example: Study with adhesive capsulitis, patient was taking pain meds and did NOT disclose this
Extraneous Variable/Confounding factor
◦analysis of variance statistical procedure appropriate for comparison of three or more treatment groups or conditions, or the simultaneous manipulation of 2 or more independent variables
◦this is the best measure to use when utilizing Simultaneous Comparison of several means
ANOVA
refers to how well the measure reflects a theoretical construct of the characteristic of interest
Construct validity
PICO stands for what?
Population, Intervention, Comparison, Outcome
when the researcher reports that no relationship (or improvement/progress) exists between the intervention and the outcome, when there really was a relationship or improvement
Type 2 error
refers to how well the test items measure the characteristics or behaviors of interest
Content validity
A variable that will predict or cause an outcome. A condition, intervention, or characteristic that will predict or cause a given outcome. The variable can be described as a condition that can change behavior
IV
the response or outcome related to the effect of the IV. The dependent variable can be described as the behavior that may change.
DV
refers to test stimuli, methods, or procedures reflecting the assumptions that all populations have the same life experiences and have learned similar concepts and vocabulary.
CONTENT BIAS
a parametric test for comparing 2 means (for example this test is used when there is a single dependent variable, but a comparison between groups)
◦Example: Best means of analysis to use when you have a study of a new treatment technique, but have 2 groups – one participating for 30 minutes a day and one group participating for 60 minutes a day.
T-test
The Collaborative Institutional Training Initiative and is dedicated to promoting the public’s trust in the research enterprise.
CITI
3 categories of quantitative research
1.Experimental
2.Descriptive
3.Mixed Experimental-Descriptive research
Standard deviation is the average amount that all scores in the distribution deviate from the mean. What does a small standard deviation indicate?
more homogeneity
there is a normal distribution of data
parametric statistical procedures
there is not a normal distribution of data
nonparametric statistical procedures
Which is more powerful? Parametric or nonparametric statistics?
Parametric statistics
just means the probability of the findings.
For example, if the value is p<.05, that means the probability of that finding being true is 95% and the probability of the finding being false is 5%. And if we say that p<.01 that just means the probability of the findings being true are 99% and only 1% chance of the findings being incorrect. That is a very brief explanation of statistical findings
P value
considered to be the “gold standard” of true experimental designs. This type of design is considered the most rigorous
Randomized control trial
CAN be manipulated
IV
a perspective to explore and understand human behavior
Qualitative Research
Three measures of central tendency
Mean, median, mode
Four Scales of Measurement:
- Ratio
- Ordinal
- Nominal
- Interval
Main sections of a research article:
1.Abstract
2.Introduction
3.Methods
4.Results
5.Discussion
6.References
should include a narrative description of statistical outcomes, tables and figures that summarize statistical findings, and statements that support or reject the hypothesis
Results section of RA
the response or outcome related to the effect of the independent variable
Dependent variable
p<.05 means the null hypothesis
is rejected
A parametric test for comparing two means is
A t-test
statement of the expected relationship between variables
Hypothesis
tool, assessment, or instrument used to test and see if the dependent variable was affected or changed by the independent variable
Outcome measure
how consistent one researcher is when making the same measurement more than once
Intra-Rater Agreement
2 potentials sources of error
SYSTEMATIC and UNSYSTEMATIC
equipment needing to be calibrated
SYSTEMATIC ERROR
equipment malfunction
UNSYSTEMATIC ERROR
disparity between the language or dialect used by the examiner, the child, and/or the language or dialect expected in the child’s response.
LINGUISTIC BIAS
refers to how well the measure reflects a theoretical construct of the characteristic of interest
CONSTRUCT VALIDITY
when the researcher reports a relationship between the intervention and the outcome (or progress) when no relationship (or progress) really exists.
TYPE 1 ERROR
refers to how well the measure correlates with an outside criterion
The ability of an assessment to produce results that are in agreement with or predict a known criterion assessment
Criterion validity
analysis of covariance- statistical procedure used to compare 2 or more treatment groups while controlling for the effect of 1 or more confounding variables (called covariates)
ANCOVA
estimates the degree to which null hypothesis is false
Effect size
