Experimental Research
Central tendency - the tendency for scores to migrate toward the mean
mean - 1. generally called the “average.” It is equal to the sum of the scores divided by the total number of scores. 2. Provides a single, most typical, or representative score to characterize the performance of the entire group
mode- the number that occurs the most
median – half of the observations are greater than or equal to this number, and half are less than or equal to this number
spread or dispersion (variability) - dispersion or spread in a variable or a probability distribution. Common examples of measures of statistical dispersion are the variance, standard deviation and interquartile range.
standard deviation - an average of deviation scores or the root mean square deviation
variance -
range -
random -
standard score (z score, z distribution) -
pecentile -
reliability - the degree to which one obtains the same result with a measure device when the same variable is measure twice (or more). Sometimes computed as the relationship of agreement between two independent observers.
validity - the degree to which a test actually measures what it purports to measure
interjudge agreement - Measures that take account of the similarity of the ratings as well as the similarity of their rank order
independent variable – 1. the variable that is varied or manipulated by the researcher; 2. is said to cause an apparent change in, or simply affect, the dependent variable
dependent variable – 1. is the response that is measured; 2. a variable dependent on another variable: the independent variable. In simple terms, the independent variable
multi-variat - multiple dependent variables
* The dependent variable (what you choose to observe) is a value choice.
baseline, intervention -
reversal design (return to baseline) -
neull hypothesis -
p< or = .05 -- The standard level of significance used to justify a claim of a statistically significant effect is 0.05.
statistical significance - has become synonymous with P≤ 0.05
t test – used to compare statistically the difference between two means (2 groups).
generalization
sampling
threats to internal validity
- maturation - Too much time between pre-test and post-test. Controlled through pre and post test with no intervention (control group)
- testing - taking the pre-test sensitizes you to the process of the study.
- selection - participants in a study. random selection is best. ex: study on health food, but use volunteers for selection. The average person won't sign up to be a part of the study.
- history - an event during the study effects the results.
- instrumentation - tools used for measurement are in error.
- regression - regressing to the mean. if you get very bizarre scores, by retesting, you may gravitate toward the mean.
- mortality - dropouts. can be problematic in educational research because of transience.
Correlation (r) – a form of descriptive research data, when something happens in one variable, a very similar thing happens in another variable.
Can be misleading if not used properly. Don’t speculate.
Inverse correlation – when the opposite happens
Correlations:
+1 = a perfect relationship
0 = random
-1 = inverse correlation
r =.85 strong correlation, r = -.92 strong inverse correlation
Historical Research:
primary source
secondary source
external criticism
internal criticism