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;
51 Cards in this Set
- Front
- Back
Statistics
|
refer to numbers that describe a sample
|
|
Descriptive Statistics
|
organize data from a sample by showing it in a meaningful way. You cannot draw conclusions from data beyond the sample. Examples are percentiles, frequency distributions, graphs, measures of central tendency, an variability.
|
|
Parameters
|
refer to numbers that describe populations
|
|
Nominal Variables
|
A type of frequency distribution. No order or relationship among the variables other than to separate them into groups. ex: male, female, repub, democ.
|
|
rejecting the null hypothesis
|
null hypothesis says no relationship exists
|
|
Ordinal Variables
|
type of frequency distribution. Variables are arranged b order.
|
|
Alpha level of significance
|
<.05 or <.01
|
|
Interval Variables
|
type of frequency distribution. Can show order AND spacing because equal spacing lie between the values. There is no real zero. Ex: temperature
|
|
Type 1 errors
|
incorrectly rejecting the null hypothesis
|
|
Ratio Variables
|
type of frequency distribution. Have order, equal intervals, and a real zero. Ex: Age
|
|
Type 2 errors
|
wrongly accept null hypothesis
|
|
Mean
|
Average of a set. Standard error of the mean calculates how "off" the mean might be in either direction
|
|
t-tests
|
compare means of 2 groups
|
|
Median
|
Value that lies in the center of a number set organized in ascending order. If there's an even number of values, take the average of the two middle values.
|
|
chi-square tests
|
n-cases in a sample. Will tell us whether groups are significantly different in size
|
|
Mode
|
the most frequently occurring value in a set
|
|
ANOVA (Analysis of variance)
|
flexible. like a t-test in that it analyzes differences among means. can do more than 2 groups
|
|
Variance or Standard Deviation
|
tells us how much variation there is among n number of scores in a distribution.
Variance = (((Score 1-Mean)^2+...(Score n-Mean)^2)/n)^1/2 |
|
One-way ANOVA
|
tests whether the means on one outcome or dependent variable are sig different across groups
|
|
The Normal Distribution
|
bell curve. It's unimodal (one hump) and majority of scores fall in the middle range.
|
|
Two-way ANOVA
|
test the effects of two independent variables or treatment conditions at once
|
|
Z-scores
|
on a normal distribution refer to haow many standard deviations a score is from the mean (range from -3 to 3)
|
|
factorial analysis of variance
|
used when an experiment involves more than one independent variable. This analysis can separate the effects of diffeent levels of different variables. Can isolate main effects and can identify interaction effects. You can combine the independent variables
|
|
Standard normal distributions
|
normal distributions can be standardized so that one can compare tests with different standard deviations. Standardizing makes the mean 0 and the standard deviation 1.
|
|
Analysis of Covariance (ANCOVA)
|
tests wheteher at least two groups covary. Can adjust for pre existing differences between groups.
|
|
z-scores and percentile ranks on the normal distribution
|
68% scores live within one standard deviation of the mean.
from -3 to -2 = 2% -2 to -1 = 14% -1 to 0 = 34% 0 to 1 = 34% 1 to 2 = 14% from 2 to 3 = 2% |
|
Criterion referenced tests
|
measure mastery in a particular area
|
|
positively skewed distribution
|
hump skewed to the left
|
|
Domain referenced tests
|
measure less defined properties (like intelligence) and need to be checked for reliability and validity.
|
|
Negatively skewed distribution
|
hump skewed to the right
|
|
Bimodal distribution
|
two humps
|
|
Reliability
|
How stable a measure is
|
|
Platykuric distribution
|
Flat equal frequency across all values.
|
|
Test-retest reliability
|
measured by the same individual taking the same test more than once. on a test with high test-retest reliability that person would get approx the same score each time.
|
|
Correlations
|
show relationships NOT CAUSALITY between variables.
|
|
Split-half reliability
|
measured by comparing an individuals performance on two halves of ht esame test. This reveals the internal consistency of a test. Can also increase internal consistency by item analysis (analyzing how a large group responded to each measure item)
|
|
Positive Correlation
|
As one variable increases so does the other one
|
|
Validity
|
how well the test measures a construct
|
|
Negative Correlation
|
As one variable increases the other variable decreases
|
|
Internal validity
|
measures the extent to which the different items within a measure "hang together" and test the same thing
|
|
Curvilinear correlation
|
variable relationship looks like a curved line. Example: Arousal and performance. Low arousal and high arousal lead to poor performance, but a medium amt of arousal leads to successful performance.
|
|
External Validity
|
the extenet to which a test measures what it intends to measure. 4 aspects are concurrent validity, constuct validity, content validity, face validity.
|
|
Zero correlation
|
no relationship
|
|
Concurrent validity
|
whether scores on a new measure positively correlate with other measures known to test the same construct. Process is cross validation.
|
|
Pearson r correlation coefficient
|
expresses correlation. r ranges from -1 to 1. -1 indicates perfect negative correlation, 1 indicates perfect positive correlation, 0 indicates no relationship. Strength of relationship measured by how far away it is from zero.
|
|
Construct Validity
|
whether the test really taps the abstract concept being measured
|
|
Spearman r correlation coefficient
|
correlation used when the data is in the form of ranks. Detemines the line that describes a linear relationship
|
|
content validity
|
whether the content of the test covers a good sample of the construct being measured
|
|
Regression
|
the step beyond correlations. A statistical regression allows you to identify a relationship between two variqables and make predictions about one variable based on another variable.
|
|
face validity
|
whether the test items simply look like they measure the construct
|
|
Campbell and Fiske
|
created the multitraitmultimethod technique to determine th validity of tests
|