KIN 4310: TEST 1
33 Cards in this Set
| Front | Back |
|---|---|
|
Statistics
|
Data collection;
methods of data collection, organization, analysis and presentation of data
|
|
Statistic
|
numerical summary characteristic of a sample
|
|
Parameter
|
a number that describes a characteristic of a population
|
|
Census
|
The collection of data from every member of the population
|
|
Data
|
a collection of observations
|
|
Types of Statistics
|
Descriptive Statistics
Inferential Statistics
|
|
Standard of Deviation
|
Set of a sample values is a measure of variation of values about the mean
|
|
Variance
|
Variance = standard deviation squared
|
|
Variability
|
Variability has to do with how spread out the number are
How much does each individual value differ from the center
|
|
Range
|
A measure of variability.
R=Max-Min
|
|
If there is no standard deviation, s= __?
|
0
|
|
MethodologicalApproaches
|
Descriptive
X is Y
Correlational
X is related to Y
Experimental
X Causes Y
|
|
Samples should be selected _____.
|
Randomly
|
|
Random selection corrects for ______ ________ that may confound results.
|
systematic bias
|
|
Methods of Sampling
|
Random
Systematic
Convenience
Stratified
Cluster
|
|
Random Sampling
|
Members of the population are selected in such a way that each individual member has an equal chance of being selected
Best and usually takes the most resources
|
|
Systematic Sampling
|
Select some starting point and then select every Nth element in the population.
Considered to be arbitrary
so it seems unbiased
|
|
Convenience Sampling
|
Data or results that are easy to get
People that are in your immediately vicinity
|
|
Stratified Sampling
|
Subdivide the population into at least two different subgroups, then draw a sample from each subgroup (or stratum)
Then you randomly sample inside that strata
Done so you can have an equal amount of balanced groups
|
|
Cluster Sampling
|
Divide the population into sections (or clusters) randomly select some of those clusters choose all members from selected clusters
usually clustered by geography
|
|
Strategies to avoid confounding
|
Blinding
Matching
Randomized controlled trial
|
|
Randomized controlled trial is the ____ ______ of research.
|
Gold standard
|
|
Causal Relationship:
Changes in x ____ changes in y
|
Causes
|
|
Relationships may be _______ & _______
|
Bivariate
Multivariate
|
|
Which variable is manipulated by the investigator?
|
Independent
|
|
Heteroscedacity
|
Condition where the variance of the residuals is not constant
|
|
Common Errors Involving Correlation
|
1.) Causation: It is wrong to conclude that correlation implies causalty.
2.) Averages: Averages suppress individual variation and may inflate the correlation coefficient.
3.) Linearity: There may be some relationship between x and y even when there is no linear correlation.
|
|
Classical test theory
|
O = T + E
O = Observed Score
T = True Score
E = Error
|
|
Levels of Measurement
|
(Lowest to highest)
nominal
ordinal
interval
ratio
|
|
Nominal
|
Mutual exclusive, unordered categories
Ex.
Gender
Movie Genres
|
|
Ordinal
|
Characteristics that can be put in order, but there is no consistent difference between adjacent scores
Ex.
Movie Ratings
Olympic Medals
|
|
Interval
|
Variables refer to quantities of units on a continuum
Distance Between variables is meaningful
Cannot get a ratio
Ex.
Dates
Temp. (in F or C)
|
|
Ratio
|
Variable refer to quantities of units on a continuum
Has an absolute zero
Ex.
Annual Salary
Distance traveled
|
KIN 4310: Statistics