Measurement/Methodology (15-19%) Flashcards
Who invented the concept of IQ and the first intelligence test?
Alfred Binet
What was the first intelligence test?
The Binet scale
What is Binet’s equation?
(metal age/chronological age) * 100
The highest chronological age used in the Binet scale is
16
The mean American IQ is…
100
What is the standard deviation of IQ score?
15
Who was the first to revise Binet’s IQ test?
Lewis Terman
Terman’s edited version of the IQ test is called…
The Stanford-Binet Intelligence Scale
The Stanford-Binet Scale is the best known predictor of…
Future academic achievement (also appears to be associated with better adjustment)
What is the most commonly intelligence test for adults
The Wechsler Adult Intelligence Scale (WAIS)
What is characteristics of Weschler intelligence tests?
They are organized by subtests and have subscales that identify problem areas.
The current WAIS scale or adults is #
4
The current WAIS for children is #
5
The Weschler Intelligence Scale for Children is intended for children from what ages?
6 to 16
The Weschler Preschool and Primary Scale of Intelligence (WPPSI) is intended for children from what ages?
4 to 6
What intelligence test is cross-cultural and simple?
The Goodenoguh Draw-A-Person Test
When evaluating the draw-a-person test, what is assessed?
Detail and accuracy not artistic talent
IQ is correlated with…
Parent’s socioeconomic status (income or job type), and IQ of biological parents.
What is crystallized intelligence?
knowing a fact
What is fluid intelligence?
knowing how to do something
How does intelligence change over age?
fluid intelligence declines, while crystallized intelligence does not decline.
Which researchers found what kinds of intelligence changes over time?
John Horn and Raymond Cattell
Who studied the correlation between birth order and intelligence?
Robert Zajonc
What is the correlation between birth order and intelligence?
Usually the eldest is the most intelligent in the family, the more children in the family, the lower the intelligence overall, the more children are spaced, the greater their intelligence.
This individual believed that intelligence was quantifiable, normally distributed, and influenced by heredity
Sir Francis Galton
What is “g” as it is relates to intelligence
general factor
Who hypothesized in a general intelligence factor?
Charles Spearman
Who devised the theory of multiple intelligences?
Howard Gardner
What are the 8 intelligences
Logical/Mathematical
Linguistic
Musical
Spatial
Bodily-Kinesthetic
Naturalist
Interpersonal
Intrapersonal
Who suggested a triarchic theory of intelligence?
Robert Sternberg
What are the three intelligence factors in triarchic theory?
1) analytical ability
2) practical ability
3) creative ability
What does emotional intelligence refer to?
the ability to identify and manage one’s own emotions as well as those of others.
What is the difference between achievement tests and aptitude tests?
Achievement tests measure how well you know a particular subject vs. Aptitute tests measure your innate ability to learn.
Why might “objective” personality inventories not truly be objective?
Because they are often self-reported, which allows for bias their answers.
What are some objective/structured personality inventories
1) Q-sort or Q-measure
2) Minnesota Multiphasic Personality Inventory (MMPI)
3) California Personality Inventory (CPI)
4) Myers-Briggs Type Indicator (MBTI)
5) Internal-External Locus of Control Scale
Who created the internal-external locus of control scale?
Julian Rotter
How does a q-sort or q-measure personality inventory work?
A set of cards are placed in a normal distribution as the individual considers them more or less characteristic of themselves.
A personality inventory that is used based on a set of cards where they characterize themselves.
q-sort or q-measure
Why does the Minnesota Multiphasic Personality Inventory have high validity?
highly discriminatory items and 3 validity scales to assess lying, carelessness, and faking
What is it like to take the Minnesota Multiphasic Personality Inventory
550 true/false/not sure questions
What was the initial purpose of the Minnesota Multiphasic Personality Inventory
originally used to look for evidence of psychological disorders
Who developed the California Personality Inventory
Harrison Gough at the University of California Berkley
What is the California Personality Inventory used for?
used for less clinical and more “normal” groups than the Minnesota Multiphasic Personality Inventory
Myers-Briggs Type Indicator was derived from whose personality theories?
Carl Jung
What is it like to take the Myers-Briggs Type Indicator?
93 questions which has 2 answers.
What are the dual characteristics of the Myers-Briggs Type Indictor?
Extroversion vs. Introversion
Sensing vs. Intuition
Feeling vs. Thinking
Judging vs. Perceiving
What is the difference between objective and projective personality tests?
Objective tests do not allow individuals to make up their own answers and are more structured. Projective personality tests allow subjects to create their own answers.
What is the supposed benefit of the projective personality tests?
Allows there to be a greater expression of conflicts, needs, and impulses.
What are some of the projective personality tests?
The Rorschach Inkblot Test
The Thematic Apperception Test
The Rosenzweig Picture-Frustration Study
Word Association Test
Rotter Incomplete Setence Blank
Draw-A-Person Test
The inkblot test is associated with
Rorschach
Describe the Rorschach test
subjects describe what they see in each of ten inkblots.
scoring is complex
the validity of the test is questionable
Who invented the Thematic Apperception Test?
Henry Murray
What is it like to take the Thematic Apperception Test
30 cards with pictures, one blank card. The pictures show ambiguous personal scenes and the taker tells a story about each of the cards.
What is the usual purpose of the Thematic Apperception Test?
To test the need for achievement
In Henry Murray’s personality theory define presses
environmental stimuli impacting needs.
What was Henry Murray’s personality theory called?
Personology
The Picture-Frustration Study is associated with…
Rosenzweig
What is it like to take the Picture-Frustration study?
Look at cartoons in which one person is frustrating another person, the subject is asked to describe how the frustrated person responds.
The incomplete sentence blank is associated with who?
Rotter
How does the draw-a-person test work as a personality assessment (and what group is it targeted to?)
It’s targeted toward children, they are asked to draw a person of each sex and then tell a story about them.
Can the Beck depression inventory used to diagnose depression?
No, just the severity of depression
How does the empirical-criterion-keying approach work?
Select traits that may discriminate between various groups, then give the assessment to those groups to see which factors are indeed differentiating, then keep those factors to create a differentiating instrument.
What is an example of an instrument that is empirically derived?
The Strong Interest Inventory
How do lie detector tests work?
They measure the arousal of the sympathetic nervous system, which becomes stimulated by lying or anxiety.
Who felt that situations much more than traits define actions (and thus was highly critical of personality trait theory?)
Walter Mischel
What woman researched intelligence in relation to performance?
Anne Anastasi
What is a scale that measures the level of authoritarian personality?
The F-scale or F-ration (F for fascism)
What exactly does a vocational test do?
How much does an individuals interests and strengths match with those already found by professionals within a specific job field?
What DON’T the Bayley Scales of Infant Development measure?
They do not measure intelligence and are not linked to later intelligence.
What DO the Bayley Scales of Infant Development measure?
Development in order to look for potential issues - more particularly they look at these areas of development:
Cognitive
Language
Motor
Adaptive
Social-Emotional
Essentials to a scientific approach to a psychological study requires
1) a hypothesis
2) the ability to reproduce the study
3) an operationalized definition of the concept under study
What is an operationalized definition
an observable and measurable definition
What is the difference between longitudinal, cross-sectional, and cohort-sequential studies?
In longitudinal studies the same people are followed over time (and is usually more valid), in cross-sectional studies different subjects of different ages are compared, and the cohort-sequential design combines the two.
A longitudinal design is likely to have ____ design whereas a cross-sectional design is likely to have ____ design
within-subject design (same person, different times)
between-subject design (different groups, same time)
When might quasi-experimental design be used?
When it is not feasible or ethical to randomly assign individuals to treatment vs. control groups.
Define placebo
for the control group an inactive substance or condition is disguised as a treatment substance or condition
Define predictive value (for experimental design)
the degree to which the independent variable can predict the dependent variable.
the degree to which an independent variable can predict a dependent variable is known as its…
Predictive value
What makes a study double-blind?
Neither the participant or the experimenter knows what group they are in
The degree to which the results of an experiment can be applied to larger populations and to the real world is known as its…
Generalizability
What are types of qualitative or nonexperimental research research conducted in psychology
Case studies, observational studies, ethnographic studies, and phenomenological studies.
Define mixed methods research
Research in which a combination of approaches - usually qualitative and quantitative research - are used.
When both qualitative and quantitative research is used this is often known as
Mixed methods
Define acquiescence as it applies to psychological research?
The tendency for subjects to respond positively to survey questions without considering the full context of the question.
All else being equal people are usually more likely to answer survey question to the affirmative or negative? This phenomenon is known as…
To the affirmative. Acquiescence.
What is the cohort effect as it applies to psychological research?
Outcomes associated with being a member of a group whose members all undergo similar experiences
Define cohort
a group of people who share some type of common identity (though usually refers to an age cohort)
What is it called when the subject act in the way they think the experimenter expects?
The demand characteristic
What effect is minimizer in a double-blinded experiment?
Experimenter Bias / The Rosenthal Effect
What is it called when simply being observed changes subject behavior?
The Hawthorne Effect
When a true control group can not be isolated then a ____ is the best you can manage
A nonequivalent control group
Define reactance?
in response to a perceived threat to—or loss of—a behavioral freedom, a person will experience a motivational state characterized by distress, anxiety, resistance, and the desire to restore that freedom.
May manifest as negative response to a lack of options OR as unnatural behavior in response to experimental conditions.
A potential problem that could bias a longitudinal study could be…
selective attrition
Define selective attrition
those who drop out of an experiment are different from those that remain.
What people respond with what they think is socially acceptable (instead of what they really think/feel) this shows the experimental impact of…
Social desirability
What is it called when a relationship is inferred between variables when none actually exists?
Illusory correlation
When is meta-analysis most commonly used in psychological research?
consolidating various studies on the effectiveness of psychotherapy.
When is meta-analysis potentially most helpful?
When studies find conflicting results and when different studies use different methods.
What group approves psychological studies within an organization?
An institutional review board (IRB)
What study was a catalyst for higher ethical standards in psychological research?
The Milgram experiment
Describe different kind of variables in research
Nominal variables (categories or labels)
Ordinal variables (1st, 2nd, 3rd etc.)
Interval variables (Show order and equal spacing)
Ratio variable (Absolute numbers, order, intervals, and fixed 0)
What are the 3 primary measures of central tendency?
Mean, Median, Mode
What is the standard error of the mean
a statistic that indicates how much the average value (mean) for a particular sample is likely to differ from the average value for the larger population from which it is drawn. It is equal to σ/√n, where σ is the standard deviation of the original distribution and n is the sample size.
What are the 2 primary measures of variability
Range
Variance, Standard deviation
Define standard deviation
√variance
Average extent to which scores were different from the mean.
Define variance (regarding measurement)
sum of squared deviations from the mean divided by n
What is a Z-score?
the number of standard deviations a score is from the mean (most scores fit between -3 and +3)
What is a T-score?
How a Z score may be transformed into a number on a 100 scale.
T = 10(Z)+50
What is the purpose of standard normal distributions?
a normal distribution whose values have undergone transformation so as to have a mean of 0 and a standard deviation of 1
What % lie within 1 SD of the mean, between 1-2? between 2-3?
34, 14, 2 (34.13%, 13.59%, 2.02%)
Which direction are positively skewed vs. negatively skewed distributions?
Positively skewed distributions have the MEAN skewed RIGHT away from the peak.
Negatively skewed distributions have the MEAN skewed LEFT away from the peak.
What distribution looks like a trapezoid?
A platykurtic distribution
Why might a platykurtic distribution occur?
A distribution that is flattened, having more scores at the extremes and fewer in the center compared to a normal curve.
A two hump camel curve is called?
A bimodal distribution
What does a curvilinear correlation look like?
Think parabola, with extremes having a different impact than the middle.
What are some common types of general correlation relationships?
Positive, negative, zero, or curvilinear
What are the two r correlation coefficients?
Pearson and Spearman
When is a Spearman correlation appropriate?
Only when data is in the form of ranks.
What is the range of the Pearson correlation coefficient?
-1 to 0 to 1
What does an r of 0 signify?
No correlation
A perfect negative Pearson correlation would have what value?
-1
What is the difference between correlation and regression
Correlation - relationships between variables
Statistical regression - make predictions about one variable based on another variable
The ability to generalize findings from a sample to a population is called…
inferential statistics
What is the difference between statistics and parameters?
Statistics are numbers that describe samples
Parameters are numbers that describe populations
Statistics are used to estimate parameters
Generally statistics can only be generalized to larger populations if they are…
statistically significant
A significance level is also known as…
an alpha level
Type I errors regarding null hypotheses would involve…
incorrectly rejecting a null hypothesis
Type II errors regarding null hypotheses would involve…
incorrectly accepting a null hypothesis
what are some of the most common tests of significance?
1) t-tests
2) chi-squared tests
3) ANOVA (analysis of variance) … including factorial analysis of variance
4) Analysis of covariance (ANCOVA)
5) Linear regression
What is the use of a t-test for significance?
compare the means of two groups (with continuous data) to see if they are truly different. Particularly helpful with small sample size.
When can t-tests NOT be used?
1) with discrete (vs. continuous) data
2) when comparing more than 2 groups
3) (works under the assumption of normality right?)
A test that compares the means of two (and only two) groups of continuous data to tell if they are statistically significantly different is…
The t-test
What kinds of data is analyzed by the chi-squared test?
Categorical or discrete data (thus usually positive, whole values) that are classified into categories
What can Chi-Squared tests tell you?
1) whether specific groups are significantly different in size
2) assess the goodness of fit of a distribution (basically whether this fits the distribution you expect, including the expectation that groups would be of a different, specific size)
The categories that data are sorted into for a Chi-squared test are also known as…
cells
What does the ANOVA statistical test stand for?
Analysis of variance
Why is the ANOVA statistical test so popular?
Because it is flexible
What does the ANOVA statistical test analyze?
Differences among means of continuous variables, but can analyze difference among more than two groups (even if those groups have different sample sizes)
What statistical test is used when there is more than one independent variable?
Factorial analysis of variance
What are the two types of effects analyzed by factorial analysis of variance?
main effects (the effect of each independent variable on the dependent variable)
interaction effects (the combination effect of independent variables together on dependent variables)
What is the method generally used to create a linear regression?
The least squares method to create a line fit that minimizes the distance between each point and the line.
How are the norms for measures created?
STANDARDIZING tests by trying them out on huge groups of people.
Tests that help recognize whether someone has passed the criteria to show mastery in a specific area are called (pass/fail, board exams, etc.)
Criterion-referenced tests
Tests that assess how deeply someone understands a specific subject area (50%, 70%, 90%?) is called…
Domain-referenced tests
Tests that compare individuals to others who have taken the tests are called
Norm-referenced tests
What is the difference between a criterion-referenced test and a domain-referenced test?
A criterion-referenced test provides a categorical assessment, a domain-referenced test provides a quantitative assessment.
What does reliability mean when it comes to psychological measurement?
How stable the measurement is.
What is the validity of a psychologic measurement?
the degree to which a test measures a construct
what are types of reliability for a measure?
1) test-retest reliability
2) split-half reliability
What is split-half reliability?
When you compare an individual performance on two halves of the same test to see if they have similar scores (checks the internal consistency of a test)
What is a way of weeding out problematic questions in a measure?
Item analysis
How does item analysis work?
It looks at how a large group answered each question on a measure to look for problematic questions
What does test-retest reliability mean?
That if the same individual were to take the same test multiple times, ideally they would approximately the same score each time.
What is the difference between the internal vs. external validity of a measure?
Internal - how well do the different items within the measure, measure the same thing?
External validity - how does it measure what it’s intended to measure?
What are types of external validity that can be assessed for a measure?
- concurrent validity
- construct validity
- content validity
- face validity
Who created the multitrait-multimethod technique to determine the validity of tests?
Donald Campbell and Donald Fiske
What is concurrent validity?
cross validation - how well scores on a measure positively correlate with measures known to test for the same construct collected at the same point in time.
What is construct validity?
The degree to which the test really taps the abstract concepts being measured
What is content validity?
The degree to which the content of the test offers a good sample of the concept/construct being measured (not just part of it)
What is face validity?
the extent to which the items or content of the test appear to be appropriate for measuring something
What is empirical validity?
the degree to which the accuracy of a test, model, or other construct can be demonstrated through experimentation and systematic observation (i.e., the accumulation of supporting research evidence) rather than theory alone.
What can interfere with construct validity of a measure?
1) mismatch between the construct and its operational definition
2) various types of bias
3) confounding experimenter effects or participant reactions to the experimental situation.
When two constructs are based on different concepts and their measures are also different this is called…
divergent or discriminant validity
What is the difference between concurrent validity and congruent/convergent validity
Concurrent validity is specifically matching the new test to a related test in terms of time, congruent/convergent is more general and simply shows a strong relationship.
What is the purpose of the multitrait multimethod technique?
To show the degree of convergent and divergent validity of a measure by showing that same traits assessed with different methods correlate, but different traits using the same method do not.
What do you call a variable that may impact the dependent variable but that you cannot completely control for in an experiment?
concomitant variable or covariant
How an ANCOVA different from ANOVA?
It helps take into account potential covariants that adjusts for the possible influence of covariants.
What are the 4 assumptions of a Pearson correlation coefficient?
1) interval/ratio data (ie. continuous data)
2) normally distributed
3) linear
4) no or minimal outliers
When is a Spearman correlation preferred over a Pearson correlation?
1) the data is not normal
2) there are outliers
3) the data is not continuous (but still must be ranked)
4) The data is monotonic, but need not be linear
A spearman coefficient is notated as
rs or 𝛒 (rho)
Neither the Pearson NOR Spearman correlation will work for what kind of relationships?
Parabolic or Sinusoid
When should you use a histogram vs. a bar chart?
The areas within each “bar” of a histogram should be a bin or range.
The variables of a histogram should not be able to be logically reordered, because they are continuous vs. categorical.
There are no gaps between bars in a histogram.
The width of histogram bars do NOT need to be the same.
How does cohort sequential design combine the benefits of cross-sectional and longitudinal design?
It creates overlapping groups of cohorts and studies them over a shorter period of time than a longitudinal study normally would.
Are ethnographic studies, qualitative, quantitative, or mixed. Describe this approach.
Qualitative.
A strategy frequently used by anthropologists for studying a community as a way of life. The method requires extensive residence in the community, fluency in the local languages, and active participation in community life to develop insight into its total culture.
Are phenomenological studies qualitative, quantitative, or mixed? Describe this approach.
An approach wherein mental experiences are described and studied without theoretical presuppositions or speculation as to their causes or consequences.
In general, such an approach will favor observation and description over interpretation; it will also attempt to understand a person’s experience from the point of view of that person, rather than from some abstract theoretical perspective
Walter Mischel is most famously known for…
The Marshmallow Test (studies of self control)
Draw the standard normal distribution
Who is considered the mother of psychological testing?
Anne Anastasi
