Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
98 Cards in this Set
- Front
- Back
Most valuable type of research
|
Experiment-used to discover cause and effect relationships
|
|
Factor Analysis
|
statistical procedures that use the important or underlying factors in an attempt to summarize a lot of variables
|
|
Chi square
|
nonparametric statistical measure that tests whether a distribution differences significantly from an expected distribution
|
|
parsimony
|
interpreting the results in the simplest way (in an experiment)
|
|
Occam's razor
|
interpret the results in the simplest way
|
|
confounded
|
a participant ins invalid due to extraneous variables
|
|
nondirective
|
similar to person-centered in that both are rogerian techniques
|
|
IV,
DV |
independent variable,
dependent variable |
|
ex-post-facto
|
data gathered after an experiment.
|
|
statistical analysis used with ex post facto research
|
t-test or ANOVA
|
|
variable which is changed
|
IV
|
|
control group
|
does not receive any treatment/experiment
|
|
quasi-experiment
|
cannot randomly assign participants to groups
|
|
R.A. Fisher
|
pioneered hypothesis training
|
|
percentile rank
|
descriptive statistic that tells the counselor what percentage of cases fall below a certain level
|
|
test of significance
|
tests the differences in control group from experimental group
-t-test -ANOVA |
|
P stands for
|
probability
|
|
probability
|
level of significance
|
|
parameter
|
summarizes a characteristic of a population, obtained from the value drawn from a sample.
|
|
probability levels are usually
|
.05 or less
|
|
variable which is changed
|
IV
|
|
control group
|
does not receive any treatment/experiment
|
|
quasi-experiment
|
cannot randomly assign participants to groups
|
|
R.A. Fisher
|
pioneered hypothesis training
|
|
percentile rank
|
descriptive statistic that tells the counselor what percentage of cases fall below a certain level
|
|
test of significance
|
tests the differences in control group from experimental group
-t-test -ANOVA |
|
P stands for
|
probability
|
|
probability
|
level of significance
|
|
parameter
|
summarizes a characteristic of a population, obtained from the value drawn from a sample.
|
|
probability levels are usually
|
.05 or less
|
|
P=.05 means
|
there is 5% or less chance that the differences in groups is due to chance factors, although differences exist
|
|
best probability level
|
P=.001
|
|
Type I error
|
-Alpha
-When researcher rejects the null when it is true |
|
Type II error
|
-Beta
-When you accept the null when it is false |
|
Increased sample size effect on type I and II errors
|
decreases
|
|
probability level on type I and II errors
|
decreases
|
|
t test
|
used to ascertain whether two sample means are significantly different
|
|
ANOVA
|
used with more than two groups in an experiment to test significance
|
|
two-way ANOVA or MANOVA
|
used to test experiments with two or more IV's
|
|
f-values
|
help tell differences when using an ANOVA
|
|
positive correlation
|
when one variable increases, the other does as well
|
|
correlation and causality
|
do not imply each other
|
|
N
|
number of persons being measured
|
|
correlation illustrates
|
degree of relationship
|
|
Gaussian curve
|
normal bell shaped curve
|
|
bimodal distribution
|
two humps, like a camel
|
|
point of maximum concentration in a distribution
|
mode
|
|
abbreviation for mean
|
X with bar over it, also most used
|
|
mean is misleading when...
|
there are extreme scores or the distribution is skewed
|
|
factorial design
|
several experimental variables are investigated and noted
|
|
Solomon four-group design
|
-created by L. solomon
-the researcher uses two control groups, and only one control and one experimental group are pretested |
|
negatively skewed
|
tail points to the right, or positive side
|
|
positive skewed
|
tail points to left, negative side
|
|
histogram
|
distribution with class intervals
|
|
horizontal line drawn under a distribution
|
x-axis, or abscissa
|
|
vertical line drawn next to distribution
|
y axis, or ordinate
|
|
reliable
|
experiment can be replicated with nearly identical findings
|
|
range can be calculated by..
|
subtracting the lowest from highest score
|
|
scattergram
|
pictorial diagram of two variables being correlated
|
|
John Henry effect
|
threat to internal validity of an experiment when subjects strive to prove that an experiment could effect their livelihood
|
|
Standard Deviation distributions
|
68% fall between -/+1 SD of mean
95% fall within 2 SD of mean 99% fall within 3 SD of mean |
|
variance
|
standard devision squared
|
|
z-score
|
same as standard devisions, or called standard scores
|
|
T-scores
|
has to do with what area of distribution the score falls in
|
|
platykurtic distribution
|
like the upper half of a hot dog
|
|
kurtosis
|
peakedness of a frequency
|
|
leptokurtic distribution
|
tall, like a hot dog standing up
|
|
Stanine
|
standard and nine, having to do with where the frequency falls
|
|
nominal measurement scale
|
names, like DSM
|
|
ordinal scale
|
in order, like first, second, third
|
|
interval scale
|
in scales such as IQ scores or measurement scores
|
|
ratio scale
|
time height, weight, temperature, and psychological features
|
|
naturalistic observation
|
no manipulation
|
|
simplest form of resarch
|
survey
|
|
survey return rate
|
50-75%
|
|
Hawthorne effect
|
if subjects know they are in an experiment, their performance improves
|
|
Rosenthal effect
|
experimenter expectancy effect
|
|
Halo effect
|
occurs when a trait which is not being evaluated influences a researcher's rating on another trait
|
|
ANOVA
|
-controls for sample differences
-helps remove confounding -statistically eliminates differences in averages related to covariates |
|
causal comparative research
|
not randomly assigned and IV is not controlled, but observed via treatment
|
|
regression towards the mean
|
if retested, extreme scores will become closer to the mean
|
|
standardized tests always have
|
formal procedures for test administration and score
|
|
ipsative
|
within person analysis, rather than between individuals
|
|
demand characteristics
|
any bit of knowledge that the subject in an experiment is aware of that may effect their behavior in the experiment
|
|
Duncan's multiple range, Tukey's, or Scheffe's test
|
tests significant F values when using ANOVA tests to test significant differences in between group means
|
|
Pygmalion effect
|
Rosenthal effect
|
|
counterbalancing
|
used to control for the fact taht order of an experiment could have an effect on the outcome
|
|
ahistoric therapy
|
connotates any therapy that focuses on the here and now
|
|
multiple treatment inference
|
if subject receives more than one treatment, it is unsure which modality caused the differences
|
|
stratified sampling
|
"special characteristic" or strata is accounted or chosen from
|
|
operational definition
|
outlines a procedure
|
|
systematic sampling
|
using a system to draw from your sampling, ex every tenth person
|
|
non parametric measures
|
-Mann-Whitney U-test
-Wilcoxon signed-rank test -Solomon and the Kruskal-Wallis H-test |
|
non parametric means...
|
distribution free
|
|
inductive
|
research goes from the specific to a generalization
|
|
deductive
|
reduces general to specific
|
|
SEM
|
standard error of measurement, or what would most likely occur if the individual took the test again
|
|
Likert scale
|
-Rensis Likert, 1930s
-scale helps improve the degree of measurement -scale system |