Probability Review for the final
Basic terms:
Exclusive events, exhaustive events, sample space
Dependent/independent events
Union
Intersection
Conditional probability:
Probability tables
Probability trees
Combinatorial analysis:
Basic idea of mult
Lessons 23: one way ANOVA
An independent samples t-test examines whether two samples were
drawn from two populations.
How can we compare the means of more than two independent
samples?
For instance, how do we examine whether threat affects the desire for
Lessons 14: hypothesis testing
Parameters and statistics
Parameters = population measures
Statistics = sample measures, estimate the population parameters
A statistic used to estimate a population parameter is unbiased if the
mean of the sampling distribu
- Lesson 22
t-tests
one sample t-test
The sample variance is a biased estimate of the population variance
An unbiased estimate of the population variance
When the population variance is unknown, we can use the sample
variance as an estimate for the popula
Lessons 15: hypothesis testing
Steps in hypothesis testing
1. State the hypotheses
2. Set the criteria for a decision
3. Collect data and compute sample statistics
4. Make a decision
Step 1: State the hypotheses
We state two opposing hypotheses.
These opp
Lessons 16: hypothesis testing, one and two tailed tests, p-value, effect size
A research question: Is the IQ of psychology students higher than that of the
business school students?
IQ for business school students population: = 105, = 20.
The average IQ
Lessons 17: hypothesis testing, effect size and power
When research reflects reality - 1
Information on psychology students IQ is
not available for the researcher!
True state
Business school
Psychology
=105
95
115
=120
130
110
In Research
Busi
Lessons 18: one sample t-test; biased and unbiased estimates
In statistics, bias of an estimator is the difference between this estimator's expected
value and the true value of the parameter being estimated. Expected value describes
the result of performi
Lessons 21: Dependent Samples t-test
T-test for dependent samples
There are two main situations where we consider samples to be dependent:
Same participants: repeated measures (improvement in marital
satisfaction before and after couple counseling).
Match
Lesson 19 - effect size, errors, power,
And one sample t-test
Decisions and the probability of
errors - power
TEST RESULT
H0 True
H0 True
Confidence level
1-
Type I Error
H0 False
TRUE
STATE
H0 False
Type II Error
Power
1-
(B = P)
(B < P)
Correct decision
Mutually
exclusive
events
Me winning an second place in a
first place
d marathon.
they
Events are mutually exclusive when they
A and B are mutually
A and B are not mutually
overlap
cannot occur together.
exclusive:
exclusive:
A no
Being pregnant and no
Lessons 20: Independent Samples t-test
Two samples t-test
The questions we have examined so far have tested whether a single
sample was drawn from a given population (H0) or from a population that
differs with regard to the variable examined (H1). For ins