ERMS Exam 2 Flashcards
Variability
how much the scores in a distribution are spread out or clustered together.
Variance
measure of variability
Standard deviation
a measure of how dispersed the data is in relation to the mean
Sampling error
differences between what is present in a population and what is present in a sample
Standard error
indicates how different the population mean is likely to be from a sample mean
Alpha level
the level of significance.
the probability of obtaining your results due to chance.
P-value
the probability under the assumption of no effect, of obtaining a result equal to or more extreme than what was actually observed
Critical regions
sample values that are very unlikely to be obtained if the null hypothesis is true.
Z-score
standardized scores that make different distributions comparable. Z-scores take a mean and provide a probability.
Central limit theorem
tells us if the population you drew the sample from is a normal shape or the number of scores in your sample(n) is relatively large.
The mean of sampling distribution: expected value of m
what parts of study is ethics involved with?
Measurement
Participant selection
Strategies & design
Procedure
Analysis
Reporting
What does APA stand for?
American Psychological Association
generally define psychcology ethics
honest & respectful to people affected by their research,
- care & maintenance of non-human subjects
what are the basic principles of research ethics
protecting participants from psychological or physical harm.
Assent
agreement of someone not able to give legal consent
Consent
given by those who have reached the legal age of consent (usually 18 in the US)
Beneficence
Benefits and risks should be balanced
Justice
Everyone should be able to access and benefit from the contributions of psychology
Deception
hiding the true nature of the study, because revealing it will result in participants altering their behavior
Little albert ethical issues
hiding the true nature of the study, because revealing it will result in participants altering their behavior
Tuskegee Syphilis Study
Tracking progression of syphilis among nearly 400 low-income African American men, Told they had “bad blood”, Withheld from treatment and cure from penicillin
Tearoom Trade Study
Investigating motivations to have anonymous sexual encounters with men in public restrooms, Acted as a lookout while making observations and recording license plate numbers, After a year, visited men at their homes under a disguise for interview
what does IRB stand for?
Institutional review baord
Institutional Review Board (IRB)
Human subjects research is now reviewed by an impartial 3rd party to protect participants, Examines protocols to ensure that they will not be harmful to participants, and provides sanctions for those who break the rules, Composed of scientists & non-scientists (including a community member)
Institutional Animal Care & Use Committee (IACUC)
Oversight of research using animal subjects
Always must include a veterinarian, a scientist with animal subject experience, and a member of the general public
What does IACUC stand for?
Institutional Animal Care & Use Committee
what are the 3 r’s of animal research?
Replacement – employ methods which avoid or replace the use of animals
Reduction – use methods that enable researchers to obtain comparable levels of information from fewer animals
Refinement – use methods that alleviate or minimize potential pain, suffering, or distress, and enhance animal welfare for the animals used
Fraud
the explicit effort of a researcher to falsify or misrepresent data (not a mistake)
HARKINING
Hypothesizing After Results are Known
Type 2 errors
Researcher fails to reject a null hypothesis that is actually false
Type 1 errors
Researcher rejects a null hypothesis that is actually true
true or false: A Type I error is like convicting an innocent person in a jury trial.
TRUE – Innocence is the null, conviction is rejecting the null, this would be a false positive error
true or false: A Type II error is like convicting a guilty person in a jury trial.
FALSE – convicting a guilty person would not be an error; you’d be correctly rejecting their innocence
Factors that affect statistical power
effect size, sample size, alpha level.
The power of a statistical test is the probability of _____ null hypothesis.
rejecting a false
Practical significance
whether the effect is large enough to be important in your field
Probability
When several outcomes are possible, the probability of any specific outcome is the number of times that outcome happens out of all total outcomes
Iris has a z-score of -1. The original distribution had a mean of 5 and a standard deviation of 2. What was Iris’s original score?
3
Z-distribution
Every score in a distribution could be transformed into a z-score
This would transform the distribution to a z-distribution.
`
Hypothesis testing skeleton
- state hypothesis
- set criteria for decision
- collect data and compute sample statistics
- make a decision
- state hypothesis
Null hypothesis: no sig diff
alt Hypothesisi: sig diff
- set criteria for a decision
- critical regions
- alpha .05 unless stated otherwize
- one or two tailed
- sig if p < a
- collectdata and compute sample stats
p:value: tells you the probably null is true
t: v-value?
Makr a decision
- fail to reject p>
-reject null p<a
(UNLESS IT IS A ONE TAILED) Then directinality plays a role.
Directional
must hypothesize that the value will be smaller or larger
You’re running an independent samples t test and both conditions have n = 10. How many degrees of freedom do you have?
df = (n1 – 1) + (n2 – 1) = 9 + 9 = 18
nominal
numbers represent named differences, not value differences
- number have no qualitative value or intrinsic order
ordinal (ranked)
number represent differences in rank or order
continious variables
a variable that can be an infinite or uncountable set of variables (height, weight, tempature)
- Interval and ratio variables
interval or integer
number represent measurement along a scale when each unit is the same
ratio
quantitative data, measure varibales on continious scale, ratio has “true 0”
example: money
consistency
a reliability measurement in which items on a test are correlated in order to determine how well they measure the same construct or concept
Effect
a measure of the strength of the relationship between two variables.
Descriptive statistics:
analyse data to help describe, show or summarise it in a meaningful way
inferential statistics
ways of analyzing data using statistical tests that allow the researcher to make conclusions about whether a hypothesis was supported by the results.
parameter
A number derived from knowledge of the entire population, such as the minimum of the population, or the mean of the population. Parameters are characteristics in a population.
cohens d sizes
small effect .2
medium effect .5
large effect .8
independent sample
compare two seperate sampls between subject desiens
depenedent sample
compare 1 sample at 2 times
one sample
when we want to know whether our sample comes from a particular population but we do not have full population information available to us
one tailed
directional hypothesis: must hypothesis that the value wil become larger smaller (more or less)
two-tailed
non-directional alternative hyphteis: 2 critical regions not directional
test value
the important number
