null hypothesis
in a hypothesis testing, a statement that there is no difference between populations
alternative/experimental hypothesis
states that there is a change, a difference, or relationship in the general population
alpha level
level of significance" is a probability value used to define "very unlikely" the alpha level sets the critical region (composed of the extreme sample values that are very unlikely)
M e
mean of experimental
SD e
standard deviation of expeiment
statistical difference
extreme difference between the two data points
hypothesis testing consists of how many steps?
5
what is the first step in hypothesis testing?
restate the question as a research hypothesis and a null hypothesis about the populations
what is the second step in hypothesis testing?
determine the characteristics of the comparison distribution
what is the third step in hypothesis testing?
determine the cutoff sample score on the comparison distribution at which the null
what is the fourth step in hypothesis testing?
determine your sample's score
what is the fifth (last) step in hypothesis testing?
decide whether to reject the null hypothesis
how different/how unusual??
average ~ 5%
when to reject the null hypothesis?
when p < 0.05
one tailed tests
when you predict that the sample is specifically greater or lesser than mu
two tailed tests
when you predict that the sample is different than mu
cherry picking the data
purposely picking certain data
distribution of sample means
the distributions of all possible means of all possible samples of a given size
samples are never?
perfect
sampling error
a sample will never perfectly represent a population
x with a line over it?
sample mean
the larger the sample size leads to?
a smaller sampling error
the mean of all possible sample means of size n is?
the same a the population mean
central limit theorem (CLT)
applies to any population
effect size
rejecting the null hypothesis when the research hypothesis is false
um
the mean of all the means of all the samples at a give sample size (ex: all possible samples on n=42)
when does sample size matter?
when trying to find standard error
confidence intervals (CI)
calculate a range of data in which we believe the population mean exist
how do we calculate confidence interval
1 - alpha = CI
alpha
how we define the area outside of the CI
if p-value is low
that means that the probability that your findings are due to chance is very low
if that probability is very low
reject the null hypothesis
p > .05
fail to reject the null hypothesis
type 1 error
you declare significance, but there is none; "false positive
type 2 error
declare non-significance when it actually is significant; "false negative
statistical power
the likelihood of finding significance when you really should reject the null hypothesis
power
the likelihood of committing the type 2 error
aplha
your likelihood of committing type 1 error
what is an accurate description of hypothesis testing?
it is a central theme in the statistical analysis of virtually all psychology research
when a psychologist sets up a hypothesis testing problem, the intent is to?
determine whether the opposite of the predicted behavior will occur
if a psychologists tests whether there is any difference between how fast people work in the morning versus how fast they work in the evening, the null hypothesis is that?
there is no difference in the speed at which people work
what is the research hypothesis?
the exercise will reduce the rate of heart attacks
what is the comparison distribution?
the distribution of people who do not participate in the exercise program
when a psychologist rejects the null hypothesis at the .05 level, teh results of a study indicate that
there is less than a 5% chance of getting such an extreme result if the null hypothesis is true
a result is considered statistically significant when
the sample score is so extreme that the null hypothesis is rejected
if the cutoff Z-score on the comparison distribution is 1.64 and the sample Z-score is 1.32 on the comparison distribution, the correct decision is to?
fail to reject the null hypothesis
if the null hypothesis is rejected, the researcher can conclude that the results
support the research hypothesis
a one-tailed test is associated with
a directional hypothesis
alternative hypothesis
sometimes , a research hypothesis may be referred to this
significance/alpha
if the cutoff sample score is set of the most extreme 5% of the comparison distribution, then the 5% is what level?
the mean and variance of a comparison distribution that would be used to test the hypothesis that the mean obtained in a study involving 10 participants is different from a known population having a mean of u=100 and sigma^2=25 would be?
mean =100
variance= 2.5
dividing the variance of the population of individuals by the number of individuals in each sample yields
the variance of the distribution of means
the standard deviation of a distribution of means is sometimes called "the standard error of the mean", or the "standard error," because
it represents the degree to which particular sample means are "in error" as estimates of the mean of the population of individual scores
as the umber of people in a sample gets larger, the distribution of means
becomes a better approximation of the normal curve
distribution of means
the comparison distribution when testing a hypothesis involving a sample of more than one participant
setting the significance level cutoff at .10 instead of the more usual .05 increases the likelihood of
accepting the null hypothesis when, in fact it is false
a child psychologist conducts a study to test whether infants born prematurely begin to walk earlier than infants in general. which of the following scenarios represents a type 1 error?
the psychologist concludes that premature infants do walk earlier than infants in general when the true situation is that they actually do not
a cognitive psychologist tests whether memory for abstract ideas improves when the information is presented both verbally and visually. What is a type 1 error?
the psychologist concludes that memory does improve when the true situation is that it does not improve
using the .01 level of significance means that, in the long run
a type 1 error occurs 1 time in 100
one important advantage o fusing effect sizes is that
they are standardized scores that make comparisons of different studies easier
a psychologist conducts a study and finds that d= -.63. This effect size would most likely be considered?
medium
if an experimenter CANNOT manipulate the effect size of an experiment to increase power, the aspect of a study can usually be changed easily to increase power is
the sample size
while no research hypothesis is ever definitely false, failing to reject the null hypothesis in a study that has a high level of power allows one to?
conclude that the research hypothesis is most likely false
some psychologists have argued that simple significance tests are misleading, and that a better statistic to evaluate the outcome of an experiment would be the
effect size
p < .05 means that there is less than a 5% chance of making which type of error?
type 1 error
failing to reject the null hypothesis when in fact it is false is which type of error?
type 2 error
the probability of making a type 2 error is?
beta, B
a researcher obtains a statistically significant result. However, if he used a large sample, then the test result may not?
have practical importance
what is <0.5?
This is how we determine statistical significance. The cutoff point for significance is 5%
Central Limit Therom
the number of samples of the same size. They take on the shape of the normal curve. Our sample sizes have to be 30 or greater in order for CLT to be proven.
Confidence Interval (CI)
hope that they true mu falls in most 90%
p-value falls into outer most 5%
why 5%?
it is conservative