-
study population
clearly defined collection of people, animals, plants, or objects; usually a specific group of people
-
response variable
the measurement of the attribute of interest
-
ratio scale
- measurement with the following properties:
- 0 represents comple absence
- ratio of any two scores correctly describes ratio of attribute quantites
- difference between two scores correctly describes difference in attribute quantities
-
interval scale
- measurement with the following properties:
- 0 does not represent complete absence
- ratio of any two scores does not correctly describe ratio of attribute quantites
- difference between two scores correctly describes difference in attribute quantities
-
quantitative measurement
ratio or interval scale measurement
-
population parameter
single unknown numeric value that describes the measurements that could have been assigned to all N people in a specific study population
-
population mean
an unknown value; the average of all N scores that could have been assigned to all N people in a study population
-
random sample
a set of a study population of size n, selected in such a way that any set of size n has an equal chance of being selected
-
sample mean
an estimate of µ; the average of all scores from the sample
-
standard error
-
- value that numerically describes the accuracy of a parameter estimate
-
sample variance
- describes the variability of the scores in the sample
-
sample standard deviation
- estimate of ơ; describes the variability of the scores in a sample
-
confidence interval
range of values that is believed to contain an unknown population parameter value with some specified degree of confidence
-
null hypothesis
H0: µ = h; states that the mean is equal to some specified value
-
three-decision rule
1a general hypothesis testing procedure in which one of the following decisions will be made: 1) accept H1, 2) accept H2, 3) fail to reject H0
-
test statistic
a value obtained from a t-test, used to determine whether or not to reject the null hypothesis
-
one-sample t-test
a test of the null hypothesis applied to a single population mean
-
p-value
a number determined by the test statistic; small p-values correspond to high test statistics and the researcher may reject the null hypothesis if p is less than α (usually .05)
-
significance testing
an alternative to hypothesis testing where results are declared "significant" if the p-value is less than some set value, usually .05
-
histogram
graph that visually displays a set of quantitative scores; displays the number of scores falling into specified ranges of scores
-
normal curve
- a curve in which:
- half of the scores are above the mean and half are below (the mean, median, and mode are identical)
- 68% of scores are within 1 standard deviation above or below the mean
- 95% of scores are within 2 standard deviations above or below the mean
- 99.7% of scores are within 3 standard deviations above or below the mean
-
sampling distribution
the set of all possible sample means obtained from all possible samples in the study population
-
central limit theorem
states that if the sample size is sufficiently larg, the distribution of the sample means will be closely approximated by a normal distribution
-
unbiased estimate
an estimate which overestimates the population parameter with about the same tendency as it underestimates the population parameter
-
probability
a number on a 0 to 1 scale that describes the likelihood of an event
-
classical definition of probability
the proportion of all possible events that are of the type in question
-
power
the probability of rejecting the null hypothesis
-
type I error
rejecting the null hypothesis when, in reality, µ = h
-
prediction interval
- a range of plausible scores for one randomly selected person
-
planning value
a value obtained from experts, preliminary studies, or previoiusly published research
-
target population
a population of interest to the researcher from which the study population is taken
-
convenience sampling
nonrandom samlle obtained for ease or availability
-
random sampling assumption
requires the sample to be a random sample from the study population or some hypothetical population
-
independence assumption
requires that the responses from each participant in the study be independent of each other
-
normality assumption
requires that the scores in the study population have approximately a normal distribution
-
coefficient of skewness
numerically describes the skewness of a set of scores; zero if scores are symmetrical, positive if scores are skewed right, negative if scores are skewed left
-
coefficient of kurtosis
describes to degree to which a distribution is more less peaked than the normal distribution; equal to 3 in normal curve (coefficient - 3 = excess kurtosis), excess kurtosis > 0 is highly peaked with long tails, excess kurtosis < 0 is lower peaked with short tails
-
data transformation
scores are all manipulated mathematically to reduce skewness and kurtosis
|
|