Review Flashcards
What are the 2 types of research?
- basic/fundamental
- applied
Describe basic research
This type of research is motivated by a desire to expand knowledge and involves the acquisition of knowledge for knowledge sake
Describe applied research
This type of research is directed towards functional applications and testing
How basic and applied research compliment each other?
Basic research answers the initial question of how things work. This knowledge is then applied to make improvements on existing products, technologies and processes.
Define blind study
A test or experiment in which information about the test that might lead to bias in the results is concealed from the tester, the subject, or both until after the test.
When does a blind study become double blind?
When both the tester and subject are unaware of specific information that may lead to biases
Define control group
The group that receives either no treatment or the “standard treatment”
Define experimental group
The group of subjects who are exposed to the variable during a study
What is a pilot study?
a small scale preliminary study conducted in order to evaluate feasibility, time, cost, and adverse events in an attempt to improve upon the study design prior to performance of a full-scale research project
Define validity
The ability of a measure to capture what is intended to capture
What are the 4 forms of measurement validity?
- face validity
- content validity
- construct validity
- criterion validity
Describe face validity
A simple form of validity in which researchers determine if the test seems to measure what is intended to measure.
Essentially, researchers are simply taking the validity of the test at face value by looking at whether a test appears to measure the target variable.
How is content validity determined?
Based on whether or not all of the relevant facets of the variable being measured in represented.
What is construct validity?
the degree to which a test measures what it claims, or purports, to be measuring
How is criterion validity determined?
Based on the degree to which it’s scores are related to sources from a reference standard
What are the 2 methods for evaluating criterion validity?
- Concurrent
- Predictive
What is concurrent validity?
A measure of how well a particular test correlates with a previously validated measure
What is predictive
The extent to which a score on a scale or test predicts scores on some criterion measure
Comparing the test with an established measure is known as _____ validity; testing it over a period of time is known as ______ validity.
concurrent
predictive
What is internal validity?
the degree to which the relationship between two independent and dependent variables is free from the effects of extraneous factors
What does internal validity refer to?
the machines, subjects, etc. that are used and under your control
What does external validity refer to?
the extent to which the results of a study can be generalized or extended to others outside the experimental situation
Define sensitivity
the fraction of those with the disease that are correctly identified as positive by the test
Define specificity
the fraction of those without the disease that are correctly identified as negative by the test
_____ ______ are the people who have the disease and whose test came up positive
True positives
_____ ______ are the people who do not have the disease and whose test came up negative
True negatives
_____ ______ are the people who have the disease but their test came up negative
False negatives
_____ ______ are the people who do not have the disease but their test came up positive
False positive
A _____-referenced test judges an individual’s performance off of the group’s performance
norm
A _____-referenced test judges an individual’s performance based off of an absolute standard
criterion
The independent variable is labeled as what?
x
The dependent variable is labeled as what?
y
What are the 4 levels of measurement from most to least specific?
- ratio
- interval
- ordinal
- nominal
Describe the ratio scale
This scale classifies things in rank order with a known equal distance between categories and a known empirical zero point
What are a few examples of ratio data?
- height
- weight
- circumference
- blood pressure
Describe the interval scale
This scale classifies things in rank order with a known equal distance between categories but lacks a known empirical zero point
What are a couple examples of interval data?
- temperature
- calendar year
Describe the ordinal scale
This scale classifies objects things in rank order but lacks the mathematical properties of a known equal distance between categories
What are a few examples of ordinal data?
- weight-bearing status
- level of assistance needed
- MMT grades
- patient satisfaction
Describe the nominal scale
This scale classifies objects things but lack rank order and a known equal distance between categories
What are a few examples of nominal data?
- Gender
- Race/Ethnicity
- Religious affiliation
Describe the Likert scale
It is a psychometric scale commonly involved in research that employs questionnaires.
- agree, somewhat agree, disagree, etc.
What are 3 measures of central tendency?
- mean
- median
- mode
What is the best measure of central tendency?
the mean because it is more precise
Which measure of central tendency is preferred if the data is severely skewed?
the median
What are 3 measures of dispersion?
- range
- variance
- standard deviation
What can be defined as the variability of a score within a distribution?
variance
How is standard deviation calculated?
By taking the square root of the variance
What does the area under the curve equal?
1.0
What percentage of scores fall within one standard deviation of the mean?
68%
What percentage of scores fall within two standard deviations of the mean?
96%
What percentage of scores fall within three standard deviations of the mean?
99.7%
What is the research hypothesis?
The initial research question developed in the intro
What does the null hypothesis state?
There is no difference between populations
When are the null and alternate hypotheses developed?
in the methods section
When does a type I error occur?
when you reject a null hypothesis that is true
Therefore, a type I error is aka what?
a false positive
What Greek letter represents a type I error?
alpha
When does a type II error occur?
when you accept a null hypothesis that is false
Therefore, a type II error is aka what?
A False Negative
What Greek letter represents a type II error?
beta
What are correlation coefficients used to do?
quantitatively describe the strength and direction of a relationship between two variables
Given y = a + bx
What does y equal?
What does a equal?
What does b equal?
What does x equal?
y is the dependent variable
a is the constant (y-intercept)
b is the slope
x is the independent variable
What does r² represent?
The coefficient of determination
What is the coefficient of determination?
the amount of variance that can be accounted for by the value of another variable
What does R represent?
The Multiple Correlation Coefficient
What is a Multiple Correlation Coefficient?
a measure of the strength of the association between the independent variables and the one dependent variable
What is regression analysis?
a statistical process for estimating the relationships among variables
What is a likelihood ratio?
the likelihood that a given test result would be expected in a patient with the target disorder compared to the likelihood that that same result would be expected in a patient without the target disorder
In regards to research designs, what does A represent?
the baseline data
In regards to research designs, what does B represent?
the treatment data
When is an A-B-A design used?
to examine before, during and after a treatment
When is an A-B-A-B design used?
When there is an improvement (decrease in pain, increase in ROM, etc.) following the A-B-A design
When is an A-B-C design used?
When there are 2 experimental treatment groups
What are 2 approaches to subject selection?
- probabilistic sampling
- non-probabilistic sampling
What does probabilistic sampling refer to?
the method for randomly selecting subjects for participation in a study
What are 4 types of probabilistic samplings?
1) Simple Random Sampling
2) Systematic Sampling
3) Stratified Sampling
4) Cluster Sampling
Describe a simple random sample
A completely random form of sampling in that every object has the same probability of being chosen
Describe a systematic sampling techniques
A type of sampling technique in which subjects are chosen at a specified interval (evens, odds, every three, etc.)
Describe stratified sampling techniques
Individuals are grouped into homogeneous groups (freshmen, sophomores, juniors, seniors) and then randomly selected from each group
Describe cluster/multistage sampling techniques
Large subgroups (clusters) are randomly selected first, and smaller units from these clusters are selected.
10 schools are chosen at random. 1 class from each school is selected at random. 4 students from each class are selected at random
What does non-probabilistic sampling refer to?
the method for choosing subjects that does not involve a random selection process
What are 3 types of non-probabilistic samplings?
1) Convenience Sampling
2) Snowball Sampling
3) Purposive Sampling
Describe convenience sampling
subjects are selected because of their convenient accessibility and proximity to the researcher
Describe snowball sampling
Research finds one subject, that one subject then finds a few more subjects, who then go and find a few more, to where the sample group snowballs
Describe purposive sampling
Type of non-probability sampling in which the researcher has a specific subject in mind and choices are made carefully
What test compares parametric (ratio or interval) data arranged in 2 independent groups?
unpaired t-test
What test compares parametric (ratio or interval) data arranged in 3 or independent groups?
ANOVA (f-test)
What test compares ordinal data arranged in 2 independent groups?
Mann-Whitney U
What test compares ordinal data arranged in 3 or more independent groups?
Kruskal-Wallis ANOVA
What test compares nominal data arranged in frequency counts?
Chi-Square
What test compares parametric (ratio or interval) data arranged in 2 dependent groups?
paired t-test
What test compares parametric (ratio or interval) data arranged in 3 or dependent groups?
repeated measures ANOVA
What test compares non-parametric (ordinal or nominal) data arranged in 2 dependent groups?
Wilcoxon test
What test compares non-parametric (ordinal or nominal) data arranged in 3 or more dependent groups?
Friedman’s test
Define Meta Analysis
The statistical procedure of combining data from multiple sources
Define systematic review
The process of searching, appraising, and summarizing information on a selected topic
