-
A statistical value that indicates differences in results found in the sample when compared to the population from which the sample was drawn
Sampling error
-
A consequence of selecting subjects whose scores are different, or vary in some specific way from the population at large
sampling bias
-
A condition that occurs when subjects are selected for a study or assigned in groups in a way that is not impartial. This may pose a threat to the validity of the study.
Selection bias
-
the potential participants who meet the definition of the population and are accessible to the researcher
Sampling frame
-
separate sample scores or groups of scores (example: differences between men and women)
independent sample
-
two sets of scores on the same subject or pairs (example: pre-post test measures)
dependent sample
-
the measurement of the magnitude of the impact of an intervention
Effect size
-
an analysis that indicates how large a sample is needed to adequately detect a difference in the outcome variable
power
-
a listing of every member of the target ppopulation, using the sample criteria
sampling frame
-
the aggregate of cases about which the researcher would like to make generalizations
target population
-
a nonprobability method of selecting a sample that includes subjects who are available conveniently to the researcher
convenience sampling
-
the researcher randomly selects entire groups and then randomly selects subjects from only those groups
Cluster sampling
-
each subject is asked to recruit other subjects
Snowball sampling (referral sampling)
-
guidelines for choosing subjects with a predetermined set of characteristics that include major factors important to the research question
inclusion criteria
-
a sampling process used in quantitative research in which every member of the available population has an equal probability of being selected for the sample
probability sampling
-
useful when the researcher is unsure how many individuals will eventually be in the population or if there is an indefinitie sampling grame.
Systematic random sampling
-
population divided into two or more subgroups, then representative picks sample from each group
Stratified random sampling
-
data that can be named and placed into categories but cannot be ranked or measured on a scale
nominal
-
categorical data that can be put in rank order. The scales contain intervals between entries that vary, limiting statistical analyses and comparisons across the scales or between subjects (pain scale)
ordinal
-
data measured on a scale that has consistent intervals between measurement units and allows for broad selection of mathematical operations and analytic options
Interval
-
data measured on interval scales that have a true zero
ratio
-
a segment of population established by one or more specifications
strata
-
used in studies in which several groups, such as experimental and control or comparison groups, will be involved
Random assignment
-
the point at which no new information is being generated and the sample size is determined to be adequate
saturation
-
a ____ error occurs when thre is a difference between groups but the researcher does not detect it (the intervention works, but the researcher does not conclude that is does)
type II
-
A researcher is very careful to recruit subjects for the sample so that it will represent the population well. This is done to:
minimize sampling error
-
When subjects elect not to participate or drop out of a study, it can lead to:
sampling bias
-
Which sampling strategy is most often used in qualitative research?
purposive sampling
-
What is the main limitation of using a convenience sample?
selection bias
-
In qualitative studies, sample size is determined by:
saturation
-
How can you decrease the risk of a Type II error?
increase the sample size
-
When a study lacks power, what is most likely to occur?
Type II error
-
the extent to which an instrument is consistent across raters, as measured with a percentage agreement or a kappa statistic
Interrater reliability (scorer agreement)
-
_____ do not affect the average scores in a data set but do affect the variation that exists around the average.
Random error
-
a measure of discriminate validity in the biomedical sciences that indicates an instrument has the capacity to detect disease if it is present
sensitivity
-
a measure of discriminate validity in the biomedical sciences that indicates an instrument has the capacity to differentiate when the disease is not present
specificity
-
_______ tells us that the differences or relationships are NOT due to chance
Statistical significance
-
asks respondents to express agreement or disagreement on a 5 or 7 point scale (stongly disagree, disagree, agree.. etc.)
Likert scale
-
a scale with a set of items on a continuum or statements ranging from one extreme to another. Responses are progressive and cumulative (yes or no questions)
guttman scale
-
_______ provide choices that are mutually exclusive and encompass the total range of answers
Forced- choice questions
-
rating type scale in which respondents mark a location on the scale corresponding to their perception of a phenomenon on a continuum
visual analog scale
-
gender is an example of what type of data?
nominal data
-
A score of 20 on the Beck's Depression Inventory is an example of what type of data?
ordinal data
-
A subject answers a questionnaire based on a desire to be socially desirable. This is an example of what type of error?
systematic error
-
a type of frequency distribution in which variables with different values are plotted as a graph on x-axes and y-axes, and the shape can be visualized
Histogram
-
a graphic presentation that indicates the nature of the relationship between two variables
Scatter plot
-
______: bell shaped graph, mean is at 0 and the standard deviation is 1
Normal distribution
-
Measure between extremes, loks at difference between lowest and highest value
Range
-
Represents the variability of data, the average distance of values from the mean
variance
-
the most easily interpreted measure of variability of scores around the mean; represents the average amount of variation of data points about the mean
Standard deviation
-
_____: statistical tests that are appropriate for data that are normally distributed (fall in a bell curve)
parametric tests
-
a measure that depicts the strength and nature of the relationship between the two variables
correlational analysis
-
statistical tests to determine if results found in a sample are representative of a population
inferential analysis
-
______ allows the researcher to recommend that an intervention be used and to do so with an identified level of confidence. Fundamentally it is an analysis of differences that occur between samples and populations, between groups, or over time b/c something changed.
Inferential analysis
-
a range of values that includes, with a specified level of confidence, the actual population parameter
confidence interval
-
a statistic derived from a sample that is used to represent a population parameter
point estimate
-
analysis of a single variable in descriptive statistics or a single dependent variable in inferential analysis
univariate analysis
-
analysis of two variables at a time, as in correlation studies
bivariate analysis
-
analysis of the effects of an independent variable on two or more dependent variables simultaneously
multivariate analysis
-
Determining if BP is different in the morning or evening, and is associated with sodium intake, weight, and stress level, is an example of a ________ analysis.
multivariate
-
the risk of erroneous conclusions that the researcher is willing to accept; the standard for statistical significance
alpha
-
Differences between groups exceed standard error; the probability that differences are due to chance is less than 5 percent
statistically significant
-
When a result has an identified level of error that is lower than that which was set before the experiment began (alpha), then the results are called _____, and it is assumed the intervention had an effect
Statistically significant
-
concluding that a null hypothesis is false when in fact it is true; claiming a treatment has an effect when it does not
type 1 error
-
concluding that a null hypothesis is true when in fact it is false; claiming a treatment does not have an effect when it does
type 2 error
-
Setting alpha appropriately would most likely avoid which type of error?
Type 1 error
-
Using and adequate sample size would avoid which type of error?
Type 2 errors
-
what is the only measure of central tendency that can be applied to nominal data?
mode
-
The largest proportion of values of a variable are in the middle of the distribution
normal distribution
-
The __________ is a measure of the variability of scores around the mean
standard deviation
-
If a distribution of scores has a small variance, how will the histogram of the scores appear?
The largest proportion of scores will be clustered in the center around the mean
-
A researcher want to determine the effect of exercise on mood and blood pressure. What type of analysis will be conducted?
multivariate analysis
-
Determining if blood pressure is associated with sodium intake is what type of analysis?
bivariate analysis
-
__________ are based on the comparison of observed differences between groups in the study to the standard error.
inferential statistics
-
What does the p value represent when conducting inferential analyses?
the probability that the results are due to the standard error
-
A researcher reports that the findings from the study are statistically significant. What does this mean?
Differences in the scores between groups exceed the standard error.
-
a highly structured and controlled search of the available literature that minimizes the potential for bias and produces a practice recommendation as an outcome
systematic review
-
a methodology that synthesizes quantitative, theoretical, and qualitative research to provide a comprehensive understanding of the human condition
integrative review
-
a statistical method of aggregating the results of quantitative studies so an overall effect size can be evaluated
meta-analysis
-
the development of overarching themes about the meaning of human events based on synthesis of multiple qualitative studies
qualitative meta-synthesis
-
a process of statistically pooling the results from previous studies into a single quantitative analysis that provides a high level of evidence for an interventions efficacy
meta-analysis
-
a process and product of systematically reviewing and formally integrating the findings from qualitative studies
qualitative meta-synthesis
-
a statistical method of determining an overall effect size for a given intervention from a group of studies.
meta-analysis
-
What is a benefit from conducting a meta-synthesis?
It develops new knowledge from existing qualitative findings.
|
|