Research: Measurements and Analysis Flashcards
Nominal
Category of measurement used when 2 or more named variables exist (male/female, pass/fail)
Ordinal
Used with a hieracrchy is present but when the distance between each value is no necessarily equal (i.e., first, second, third place)
Interval
Hierarchal values that are at equal distance from each other
Ratio
one value divided by another providing a realtive association of one quantity in terms of the other
Statistic
Numerical representation of an identified characteristic of a subject
Descriptive Statistics
mathematically derived values that represent characteristics identifed in a group or population
Inferential statistics
Mathematical calculations that produce generalizations about a group or population.
What is a measure of central tendency
Identifies the relative degree to which certain characteristics in a population are grouped together
What are the 3 types of measures of central tendency?
- Mean - the arthmetic average
- Median - the middle, 50% of the population is above this point and 50% are below this point.
- Mode - the most frequently appearing value (score).
What are the 3 measures of variability
- Range - the arithmetic difference between the largest and the smallest value (outliers are often excluded).
- Interquartile range - the different between the upper and lower quartiles
- Standard deviation - the average distance that numericl values are disperesed around an arithmetic mean.
Define correlation
The strength of relatedness when a relationship exists between 2+ numerical values.
Correlation coefficient
The numerical value assigned to a correlation.
What is a perfect correction and its “r” value
Perfection correlation is a 1:1 value and it’s r value is 1.0.
Statistical significance
Numbers that indicate the likelihood of getting the same or better results under the conditions of the null hypothesis. If the likelihood is very small, the null hypothesis is rejected. Alpha for a small chance is either 0.05 or 0.01 and then the research hypothesis is accepted.
Three tests of sitatistical significance
- Chi square test
- t-test
- Analysis of variance, ANOVA, “F test”
Chi square test
Assesses if 2 samples are sufficiently different to be geenralized to a large population in a nonparametric (cannot be put on a distribution) study. The scale is from 0 (impossibility) to 1 (certainty).
t-test
Used in two samples to determine if they are sufficiently different from each other tro be statistically significant
ANOVA (analysis of variance) or “F test”
Used for multiple groups (more than 2) to determine if significant differences exist.
Reliability
The consistency of results
Validity
Indicates the degree that the study captures the actual characteristics the study intended to measure.
Method for testing validity: Concurrent validity
Compares results of studies that used different measurement instruments, but targeted the same features. (different meansures, same features)
Construct validity
The extent to which a research method or measure can accurately assess the concept it aims to measure.
Content validity
The degree to which an assessment instrument is relevant to, and representative of, the targeted construct it is designed to measure. (If measuring IQ, does the test actually measure that?)
Predictive validity
Can a test accurately predict a future outcome? To establish this type of validity, the test must correlate with a variable that can only be assessed at some point in the future—i.e., after the test has been administered.