Research Design, Statistics, and Measurments Flashcards
Who founded the first psych lab?
William Wundt
Who showed higher mental processes can be studied by experimental method?
Hermann Ebbinghaus
Oswald Kulpe
believed that whenever you thought of something, an image of that thing formed in your mind; hat is there could be no thought without mental image
First intelligence test
simon-binet
Who introduced mental testing to US
James McKeen Cattell
Who developed IQ
William Stern
Who revised Binet-Simon test for use in the US
1916, Lewis Terman
Hypothesis
tentative/testable explanation of the relationship between 2+ variables
Variables
a characteristic/property that varies in amount or kind, and can be measured.
Operational Definitions
State how researcher will measure the variables
Variable being studied
IV
Variable changes due to variation (measured)
DV
Correlations mean that the researcher does not
manipulate the IV
2 conditions of true experiment
random assignment
manipulates the IV
Correlational
IV not manipulated
Quasi-experiment
IV manipulated; subject not randomly assigned to groups
Sample
subset of population we’re ACTUALLY testing
Random Selection
each population member has equal chance of being selected
Stratified random sampling
assure each subgroup of population randomly sampled in proportion in size
Between-Subjects Design
Each subject is exposed to only one level of each independent variable.
Matched-subjects design
Between-subjects, but match on one important variable, like intelligence.
Within-Subjects design/repeated-measures design
all subjects in all conditions
Solve within subject problem of which group got which thing first
counterbalance
unintended IV
confounding variable
nonequivalent group design
control group is not necessarily similar to the experimental group since researcher doesn’t use random assignment
Experimenter bias
due to their expectations, experimenter might treat groups differently, avoid by double blind
Demand Characterisitics
Cues in research situation that suggest to subject what is expected
Solution? Deception
Hawthorne effect
tendency of people to behave differently if they know they are being controlled.
External validity
how generalizable results are
Descriptive stats
concerned with organizing, describing, quantifying, and summarizing collection of actual observations
Inferential stats
researchers generalize beyond actual observations
Frequency distribution: descriptive stats
a measure of how often each value occurs
Ex: 3x red. 2x blue
Central tendency: descriptive stats
Mode- most frequent score
mean- average score
median-middle score
bimodal
2 modes
Variability/dispersion: descriptive stats
Range- smallest number in distribution subtracted from the largest
Standard deviation- measure of typical distance of score from mean
variance- square of the standard deviation and describes how much each score varies from the mean
Standard deviations on normal distributions
0 –> 1/-1 are 34%
1/-1 –> 2/-2 are 14%
2/-2 –> other are 2%
z-score
another way of calculating how many standard deviations above/below the means your score is.
Subtract mean of distribution from your score, and divide the difference by the standard deviation.
-z score below mean
+z score above mean
T-scores
T-score distribution has a mean of 50 and a SD of 10. For instance T-score of 60 is 1 SD above the mean.
Because of round numbers, T-scores often used in test score interpretation.
Correlation coefiicients
type of descriptive stat that measure to what extent if any, 2 variables are related.
What attempts to account for the interrelationships found among various variables by seeing how groups of variables “hang together”
Factor analysis
Variables close together are assumed to be measuring _____, also called ____
the same thing, also called factor
Significance test
one tool researchers use to draw conclusions about populations based upon research conducted on samples
Show one hypothesis is supported by data by showing null hypothesis is inconsistent with data collected.
significance tests can tell us probability of observed difference is
due to chance
When we see statistically significant difference
reject null hypothesis
Criterion of significance
5% p
Criterion of significance is also called
alpha level
Type 1 error
Reject null, but null is true
likelihood = to criterion of significance
Type 2 error
accept null, but it’s false
beta
T-test
used to compare means of 2 groups
ANOVA
2+ groups
estimate how much group means differ from each other by comparing the between-group variance to within-group variance using F factor.
F= BG/WG
Chi-squared
test equality of 2+ frequencies/proportions
Categorical/nominal > numerical data
Factorial design
each IV level occurs with each level of other IV
Interaction
effects of 1 IV are not consistent for all levels of the other IV
Meta-analysis
statistical procedure
make conclusions on basis of data form different studies
Norm reference testing
assessing an individual’s performance in terms of how that individual performs in comparison to others
(I just need to be better than you)
one problem: population to whom the tests will be administered can, and often does, change
Domain-reference/ Criterion-reference testing
what the test taker knows about a specific content domain (do you actually know stuff)
Reliability
CONSISTENCY with which a test measures whatever it is that the test measures (SAME SCORES)
Test-retest
First score: test 1
Second score: test 1
Both given to same person, 2 different times
Alternate-form
First score: Test 1
Second score: Test 2 (given to same person as Test 1)
Split-form
First score: Score on one-half of test 1
Second score: score on the other half of test 1
Validity
extent to which a test actually measures what it purports to measure
Validity: Does test cover what it ACTUALLY is supposed to measure?
Content validity
Validity: refers to whether or not the test items APPEAR to measure what they are supposed to?
Face validity
Validity: does written road test relate to actual road test
concurrent validity (Criterion validity given at same time)
Validity: does test predict future success (ex: GPA/college)
predictive validity (criterion validity)
Criterion validity
predict in future, or on different measure of same skill/knowledge
Cross Validity
testing the criterion validity of a test on a second sample, after you demonstrated validity using an initial sample
Construct validity
how well performance on test fits into theoretical framework related to what it is you want to test to measure.
Validity: is test performance correlated with performance on tests measuring related variables?
Convergent validity
Validity: is test performance NOT correlated with performance on a test measuring a theoretically unrelated variable?
Discriminate validity
Nominal/Categorical Scale
Characteristics: Names
labels and categorizes observations
ex: political affiliation, gender
Ordinal scale
observations are ranked in terms of size or magnitude
1st place, 2nd place, 3rd place
Interval scales
uses actual numbers (not ranks)
Equal intervals
No zero (ex: 0 degree F does not mean no temp)
Addition/subtraction
Ratio
true zero point that indicates the total absence of the quantity being measured
Multiplication/division
aptitude tests
used to predict what one can accomplish through training (ex: intelligence tests)
achievement tests
attempts to assess what one knows/can do now
adaptive test
computerized achievement test that adapts to test taker’s ability by assessing accuracy on previous questions
Stern’s Ratio IQ
IQ 100= mental age equal to chronological
problem: after certain age, chronological age increases while mental age does not.
mental age/chronological age x 100
Stanford-binet’s deviation quotients
Deviation IQ: tells how far away a person’s score is from the average sore for the particular age group the subject is a member of.
Wechsler tests
IQ test which has all items of given type grouped into subtests. Items in subtests are arranged in order increasing in difficulty
Minnesota Multiphasic personality inventory (MMPI)
10 clinical scales
also indicates careless, faking answer, misrepresentation, and if done intentionally.
Hathaway/McKinley MMPI: empirical criterion-keying approach
compare to how people with depression acutually score.
MMPI-2’s content scales
formed using theoretical concerns
California psych inventory CPI
20 scales, 3 validity scales
all score standardized
how are projective tests different from personality
1) stimuli ambigous
2) test taker not limited to small number of posible response
ex 1: Rorschach inkblot
projective: Thematic Apperception Test (TAT)
Morgan and Murray
20 pictures with ambiguous meanings tell a story
Projective: Blacky pictures
dog named blacky in pics each designed to correspond to stage in psychosexual development
Rotter incomplete sentences blank
sentence completion test
40 sentence stems and is asked to complete them.
Theory is that test taker will fill in blanks with whatever is on her/his mind
Barnum effect
tendency of people to accept and approve of the interpretation of their personality that you give them.
Interest testing
used to assess individual’s interest in different lines of work ex: Strong-Campbell
RIASEC
