Research Flashcards
A systematic review that uses a statistical technique to derive an estimate of effect size by combining the result of several randomized controlled trials to determine the overall effectiveness of treatment
Meta analysis 1st
Experimental research method used to assess the relative effect of a specific intervention compared to a controlled condition
Randomized controlled trial- 2nd
A type of longitudinal, observational study in which individuals with a risk factor or exposure or followed overtime to compare the occurrence of a disease in the expose group to that of a group of unexposed individuals. Limitations include excessive length and the influence of other lifestyle variables
Cohort study- 3rd
A type of retrospective, observational study in which individuals who already have a particular disease or mashed with a comparison group of individuals without the disease
Case control study- 4th
An observational study that aims to describe relationships between a disease or condition and factors of interest that exist in the specified population at a given time. The studies can describe the prevalence of disease or conditions and demonstrate associations
Cross-sectional study- 5th
These descriptions may be used to generate theories and hypotheses for future research. However they cannot test hypothesis or establish cause-and-effect relationships
Case reports
Case series- case reports- opinion/ideas
Data that can assume any value along a continuous scale the covers a range of values without gaps or interruptions examples are weight distance range of motion
Continuous data
Data that is measured in whole units ie hr, number of pt visits
Discrete data
A type of discrete data limited to only two values is gender , smoker or non smoker
Dichotomous data
A measurement scale where there is no true zero point
Interval
A measurement scale where did intervals between adjacent values equal and there is a true zero point
Ratio
Rom, distance walked, velocity
The degree to which a measurement appears to test what it is supported to
Face validity
Tube McGill pain questionnaire may have greater _________ than a visual analogue scale because, in addition to pain intensity, it assesses the location, quality, and duration of pain
Content validity
MMT scares would have _________ as indicators of innervation status of muscle if there was a relationship between MMT scores and the results of EMG testing
Construct validity
A form of criterion related validity in which an interpretation is justified by comparing a measurement to a gold standard measurement
Concurrent validity
A form of criterion related validity in which the measurement is considered to be valid because it is predicted of a future behavior or event
Predictive validity
The sampling method often relies on a table of random numbers or a random number generator
Simple random sampling
Subjects are selected by taking every nth subject from the population
Systemic sampling
The population is divided into homogenous subgroups (strata) and then a simple random sample is drawn from each
Stratified random sampling
The population is divided into clusters or areas and a random sample of the clusters is selected
Cluster sampling
The intervention / condition is what variable
Independent
The outcome or response is what Variable?
Dependent variable
A type of research design where the subject receives both treatment and control in random order separated by a period of no treatment. Subject serves as their own control
Cross Over design
A type of research design in which two or more independent variables are investigated with different subjects assigned to the various combinations of levels of the independent variables
Factorial design
A type of research design in which subjects are tested under all conditions, therefore, each person acts as their own control.
Repeated measures design
A type of research design in which the data are analyzed as they become available so the trail can be stopped as soon as the evidence is sufficient to show a significant difference between treatments
Sequential clinical trail
A type of research design without a control group
Quasi-experimental design
An untreated subject experiences a change simply from participating in a research study
Hawthorne effect
A phenomenon in which an inactive treatment or procedure that is intended to mimic a real treatment causes an improvement in the pt’s condition simply because the pt has the expectation that it will help
Placebo effect
If the p value is less than or equal to the level of significance what should the researcher do
Reject the null hypothesis in favor of the alternate hypothesis
A false positive finding… Researcher rejects the null hypothesis concluding that there is a difference or relationship when there actually IS NOT
Type I error
A false negative finding when he researcher accepts a null hypothesis, concluding there is no difference or relationship when there actually IS
Type II error
A type of graph used to show the magnitude or frequency of categories of the data
Bar graph
A type of graph that illustrates the distribution of values within a group through five numbers: minimum score, lower quartile, median, upper quartile, and maximum score.
Box and whiskers plot
Type a graph used in a meta-analysis that shows the results of the individual studies as well as a cumulative summary of all studies. The width of a horizontal line represents the upper and lower confidence limits
Forest plot
A graphical display of a frequency distribution. These graphs display the distribution of data by plotting the frequency on the Y axis for each interval represented on the X axis
Histogram
The demonstrates the relationship between two or more quantitative variables. The dependent variable is typically on the Y axis
Line graph
A graphical display that illustrates the relationship between two quantitative variables. Each pair XY value is plotted on the graph as a single point
Scatter plot
A graphical display which enables the reader to observe the entire distribution of data without losing any information. Most commonly this is done by organizing data into categories and then dividing into two digits
Stem and leaf plots
Approximately _____ percent of all values fall within one SD above and below the mean?
68
Approximately _____ percent of all values fall within two SD above and below the mean?
95
Approximately _____ percent of all values fall within three SD above and below the mean?
99
A distribution with a _____ kurtosis has a sharper peak and longer, fatter tails, while a _____ kurtosis distribution has a more rounded peak and shorter, thinner tails.
High
Low
A ______ skewed distribution is when the mean and median are to the left of the mode and the left tail is elongated.
Negatively skewed distribution
A ratio of the SD of a distribution to the mean, expressed as a percentage
Coefficient of variance
A descriptive measure of the spread or dispersion of data
Standard deviation
A Relative Risk (RR) of .8 means
RR of less than one means that exposure to whatever decreases the risk
A measure used in studies to find out if being exposed to a certain substance or other risk factor increases the risk of developing a certain disease
Odds ratio (OR)
What is the ideal Number Needed to Treat
1- everyone improves with treatment
The higher the NNT- the less effective the treatment is
Leant ing that occurs when an unconditioned stimulus is repeatedly preceded by a neutral stimulus ( bell)
Classical conditioning
What is used to test hypotheses and to make inferences from the sample to the population
Inferential statistics
These two are examples of parametric inferential statistics used to test the significance of the differences in two or more means
The t-test and analysis of variance
A comprehensive review of medical literature that uses explicit methods to systematically search identified appraisal and summarize all research and literature on a specific issue?
Systematic review- 1st
If 100 pt how don’t have the disease take a diagnostic test and 43 test positive, the test is considered 43% _______?
Sensitive
