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;
29 Cards in this Set
- Front
- Back
population
|
the total number of observations sharing at least one trait in common
|
|
parameter
|
any measure obtained by having measured an entire population.
--Statisics is to sample as ___is to Population |
|
sample
|
smaller number of observations taken fromt he total number making up the population
|
|
statistic
|
any measurement made on a sample
|
|
outlier
|
when one or two scores in a large random sample fall so far from the mean ( say 3 or 4 SD units away)
|
|
bias
|
a nonrepresentative sample it often due to
|
|
central limit theorem
|
when successive random samples are taken from a single pop., the means of these samples assume the shape of a normal curve. It applies only when all possible samples have been randomly selected from a single population
|
|
sampling distribution
|
every point on the abscissa of a sampling distribution of means
|
|
M
|
sample mean
|
|
u
|
population mean
|
|
M - u
|
sampling error
|
|
Type 1 error
|
error made when the researcher incorrectly rejects the null hypothesis ( because in fact it should have been accepted.) The alpha level sets the probability of this error occurring.
|
|
Type 2 error
|
error made when the researcher incorrectly accepts the null hypothesis ( because in fact it should have been rejected). The beta level sets the probability of this error occurring.
|
|
z test
|
method of hypothesis testing that can be used when the parameter values are normally distributed and the mean and the SD of the distribution are already known.
|
|
One tail Test
|
the use of only one tail of the distribution for testing the null hypothesis.
|
|
Null Hypothesis
|
assumption that results are simply due to chance. States that no real differences exist int he population from which the samples were drawn.
|
|
Chi Square
|
statistical test of significance used to determine whether or not frequency differences have occurred on the basis of chance. Data has to be in NOMINAL form ( actual number of cases) that fall into 2 or more discrete categories. A non parametric test.
|
|
Beta Level
|
the probability of committing a Type 2 error
|
|
Alpha Level
|
the probability of committing a Type 1 error. The level is usually set beforehand and should NOT be higher than .05
|
|
Ha
|
alternative hypothesis
|
|
Ho
|
null or chance hypothesis
|
|
df
|
degrees of freedom--based on how many values are free to vary once the mean and the sample size are set.
|
|
point estimate
|
the use of a sample for predicting a single population value. For example, the use of a sample mean for estimating "u" is a point estimate
|
|
confidence interval
|
are determined on the basis of a probability value of .95 ( 95% certainty) or .99 ( 99% certainty)
|
|
significance
|
indicates that the results of a study are not simply a matter of chance.
|
|
effect size (ES)
|
the difference between 2 population means in units of the population standard deviations. has 2 major tests for computing effect size: 1. d for t test 2. eta square for ANOVA
|
|
alternate hypothesis
|
the opposite of the null hypothesis. It states that chance has been ruled out.
|
|
ANOVA
|
Analysis of Variance- a statistical test of significance developed by Sir Ronald Fisher.
aka "F" ratio. The test is designed to establish whether a significant (nonchance) difference exists among several sample means. |
|
t ratio
|
may be used for assessing the likelihood of a given sample being representative of a particular population. It is a test of the null hypothesis
|