Reading...
Play button
Play button
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;
38 Cards in this Set
- Front
- Back
|
What are statistics
|
tools used to describe, organize, and interpret information
summarize and predict compare and relate |
|
|
Descriptive Statistics
|
summarizes
organizes a lot of information simplifies data Types : mean, median, mode, correlation, z score, range, standard deviation |
|
|
Inferential Statistics
|
Generalize and predict
z tests, t tests, regression, confidence intervals, chi square |
|
|
Descriptive vs inferential
|
describe vs infer
summarize vs predict |
|
|
Primary purpose of descriptive statistics
|
to simplify
does this by placing on a frequency distribution |
|
|
Frequency Distributions
|
Descriptive Statstics
Summarize and organize data some form of list of data |
|
|
Frequency Distributions chart
|
Measure how many people (frequency) something happens at different levels
|
|
|
Frequency Distributions:
Relative |
Measures % of people out of the entire frequency for each level
|
|
|
Frequency Distributions:
Cumulative |
measures as frequency goes up
ex: amount under 100 amount under 200 amount under 300 number accumulates |
|
|
Most common graph used for frequency distributions:
|
Histogram
|
|
|
Three main things used to describe a histogram or a distribution
|
Shape (bell, normal distribution, mean)
Middle (mean) Spread (how spread out is the data) |
|
|
Positive Skew
|
Most scores low, tail points right
high and then low |
|
|
Negative Skew
|
Most scores high
low and then high |
|
|
Measures of central tendency
|
Mean
Median Mode |
|
|
Mode
|
Most frequently chosen
Represents where most data will cluster around Rarely Used Barely tells anything |
|
|
Median
|
Middle point
To find, order all observations low to high, find middle point Not susceptible to outliers Not mathematically interesting |
|
|
Mean
|
Average
If you add or subtract from constant, the mean will move exact amount If you multiply or divide, the mean will move the exact same Balance point, usable, value Ouliers |
|
|
Positive skew
|
Mean > Median> Mode
On graph, it goes mode, median mean |
|
|
Negative skew
|
Mean<Median< Mode
On graph, it goes mean, median, mode |
|
|
If the shape and central tendency is normal then....
|
mode=median=mean
|
|
|
Variation
|
Spread of scores
|
|
|
Range
|
Highest score - lowest score
susceptible to outliers because uses most extreme values |
|
|
Standard Deviation
|
Most common measure of variability
How scores vary around the mean Know formula |
|
|
rule for St Dev in a normal curve
|
68-95-99.7 rule
|
|
|
% in one st dev
% in 2 st dev % in 3 st dev |
68% (34% +/ -)
95% (47.5% +/- ) 99.7% (49.9% +/-) |
|
|
Correlation
|
Describes relationship between 2 variables
how strongly or weakly NOT causation |
|
|
Scatterplots
|
Show the relationship between two variables
used with correlation |
|
|
Characteristics of Correlation (3)
|
Direction
Form Strength |
|
|
Direction of Correlation (2)
|
Positive (line comes from middle diagonal)
Negative (line forms triangle in center) |
|
|
Correlation
Form |
Linear (straight line form)
Curvilinear (curve or no straight line) |
|
|
Strength of Correlation
|
The closer correlation is to 1, the stronger
0 equals no correlation |
|
|
r strength small med large
|
small r= .1
med r= .24 large r= .37 |
|
|
Valdity
|
Intent, thermometer, whether it is right or not
does it mean the right thing content, criterion, construct |
|
|
Validity:
Content |
subjective
examines content of the meaurement to see if it appears to be related to what the researcher wished |
|
|
Validity:
Criterion Related |
predictive
concurrent (agreeing) how accurately can a new messages predict a well excepted or previously validated concept |
|
|
Validity:
Construct related |
Broadest
Judgement is it measuring what it is supposed to measure |
|
|
Reliability
|
consistency, stability
necessary for validity, but not enough to be valid |
|
|
Reliability
Test- Retest |
Do the same test twice and test the correlation between the results
|
