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;
43 Cards in this Set
- Front
- Back
random sampling
|
process of selecting a sample such that the selection of one observation is independent of the selection of any other observation
|
|
parameters
|
characteristics of populations
|
|
inferential statistics
|
statistical procedures used to make decisions about a population based from a sample
|
|
sampling distribution
|
hypothetical distribution of the values of a statistic if it were computed repeatedly with similar samples
|
|
absolute research
|
research with the purpose of measuring some phenomenon
|
|
comparative research
|
research that compares the results from two or more groups
|
|
scientific method
(steps according to stats) |
1. encounter and identify the problem
2. formulate the hypotheses and define variables 3. think through the consequences of the hypotheses 4. design and run the study, collect data, compute stats, test hypotheses 5. draw conclusions |
|
continuous variable
|
can take on an INFINITE number of values between 2 lengths
|
|
discreet variable
|
finite number of values between two sites
|
|
independent variable
|
values manipulated by the researcher
|
|
dependent variable
|
values measured by the researcher
|
|
extraneous variable
|
not manipulated or measured but they are affecting what you're measuring
|
|
Three ways to control the extraneous variables (EV)
|
1. hold the participants constant on the EV
2. include EV in your design 3. randomize participants to groups |
|
subject bias
|
subjects change their behavior based on what group they're in
|
|
observer bias
|
researcher changes how they treat participants based on what group they're in
|
|
single-blind experiment
|
subjects do not know what group they're in
|
|
double-blind experiment
|
both the researcher and the subjects do not know which group they're in
|
|
causal relationship
|
studied when there is manipulated variables and controlled EV
*manipulation of the IV is key! IV -> DV |
|
predictive relationship
|
a relationship that exists when a researcher can assert only that a change in one variable predicts a change in another variable
PV -> CV |
|
predictor variable
|
variable in a predictive relationship that is analogous to the independent variable; the researcher predicts from this variable
|
|
criterion variable
|
variable in a predictive relationship that is analogous to the dependent variable; the researcher predicts to this variable
|
|
true experiment
|
research that uses an IV and a DV and controls EV by randomization; causal relationships can be asserted when a true experiment is conducted
|
|
observational research
|
research that can assert only predictive relationships because of the absence of manipulation and randomization
|
|
Quasi experimental designs
|
designs in which the researcher can manipulate the IV but cannot randomly assign participants to groups
|
|
Property of measurement:
Identity |
your data is named and has meaning
|
|
Property of measurement:
Order |
a meaningful order in the values
ex. 1st place and 2nd place |
|
Property of measurement:
Distance |
a positive, consistent difference between values
|
|
Property of measurement:
true zero |
it lacks that variable
ex. temperature does not have this... children - do have this |
|
internal validity
external validity |
In a QED:
how valid are your results generalizability of your results to other groups |
|
Scales of Measurement
|
1. Nominal
2. Ordinal 3. Interval 4. Ratio |
|
nominal
|
has the characteristic of identity
|
|
ordinal
|
has identity and order
|
|
interval
|
has identity, order, and distance
|
|
ratio
|
has identity, order, distance, and a true-zero
|
|
Characteristics of a bar graph
|
use with qualitative data
bars DON'T touch categories on X-axis frequency on Y-axis |
|
Characteristics of a histogram
|
use with QUANTITATIVE data
bars do touch intervals on X-axis frequency on Y-axis |
|
kurtosis
|
deals with the peak of the distribution: mesokurtic
patykurtic leptokurtic |
|
characteristics of median
|
depends on frequency of scores and not their actual value
recommended for skewed data not affected by outliers |
|
characteristics of the mean
|
balance point in the distribution
sum of the deviations = 0 sum of the squared deviations is a minimum the sample mean gives you the smallest amount of deviation |
|
sample standard deviation
|
in original units
as variability increases, st.dev. increases = 0 if no variance indicates relative standing |
|
sample variance
|
a positive number
= 0 if no variability as variability inc., st.dev. inc in squared units |
|
Least Squares Criterion
|
E(x - mean)^2 is a minimum
|
|
Z-score
|
something minus its mean divided by the st. dev.
expressed in terms of st. dev. units variance of the z scores is 1 st. dev. of z-scores is 1 Z is undefined the shape of the z-score distribution = x distribution |