Department of Psychology

A-L  | M-Z

M  N  O  P  Q  R  S  T  U  V  W  X  Y  Z

Main effect
In general what the overall effect of the treatment is.

Maturation
Change due to ageing or developing of subject(s) during experiment, either within groups or between groups. A threat to internal validity.

Mean
The sum of all scores divided by the number of scores. Requires interval or ratio data

Median
The number in a range of scores that falls exactly in the middle such that 50% of the cases are above and below it. Requires interval or ratio data

Mode
The number that occurs most often in a data set. A distribution can have more than one mode

Mortality
A threat to internal validity caused by loss of subjects which leaves unequivalent groups.

Multiple treatment interference
That the treatments interact with each other, thus producing false or misleading results

Multiplicative rule
the probability of the joint occurrence of two or more independent eventis is the product of their individual probabilities

Multistage sampling
a combination of these different methods

Mutually exclusive
Events that occur independently of each other and as a result of chance.

n
the number of participants

Negative skew
A frequency curve in which the mean is lower than the median, and the median is lower than the mode. The result is a "tail" towards the more negative side of the graph.

Nominal measurement
"naming:" assigns arbitrary numbers to different categories in order to differentiate them. The numbers themselves have no meaning. For example, you may bubble in the number "1" if you're a female, "2" if you're a male. This doesn't mean that either category is better or worse than the other.

Non-directional
A hypothesis which predicts that there will be a difference between or among groups.

Non-equivalent control group design
Designs with experimental and control groups that are designated before the treatment occurs and are not created by random assignment

Non-experimental design
A design in which no treatments are given, instead studying naturally occurring variation in the independent and dependent variables. Used when an experimental design would be unethical

Normal distribution
A frequency curve in which the mean, median, and mode all have the same value

Null hypothesis
The assumption that there is no true difference between groups and any difference (statistically) is due to sampling errors. A researcher tries to disprove this

One-tailed
The type of test used with a directional hypothesis, using +/- 1.65 as the critical value

Operational definition
A definition that is clear and specific such that it can be replicated by another researcher

Ordinal measurement
"rank:" orders participants from high to low (or vice versa) but does not indicate how much higher or lower one subject is from another.

Parallel forms reliability
Two tests of different forms that supposedly test the same material will give the same results.

Pearson r
Pearson Product-moment correlation. A test which calculates the degree to which two variables are related.

Placebo effect
Improvement due to expectation rather than the treatment itself; can occur when participants receive a treatment that they consider likely to be beneficial.

Positive skew
A frequency curve in which the mean is higher than the median, and the median is higher than the mode. The result is a "tail" towards the more positive side of the graph.

Precision
The ability of a measurement to be consistently produced

Predictive validity
The extent to which a test predicts a known association between what your measuring and something else, based on empirical data. Measured after the examinees have had a chance to exhibit the predicted behavior.

Probability
The number of times an event is likely to occur out of the total number of possibilities

Purposive sampling
This is usually done for the purpose of selecting (not randomly) the individuals that will provide the best information for the study.

Quantitative
Can be measured and analyzed statistically

Quasi experimental
A design in which treatments are given but random assignment is not used

Range
the lowest and highest points of a set of data

Ratio measurement
Much like interval, uses a set scale. The researcher knows the order of the data points both relative to each other and in absolute terms. Both the zero and the average have meaning.

Reactive effects of experimental arrangements
If the experimental setting is not the same as the natural setting that the participants would usually be in, external validity may be threatened by the participants reactions to the different environment, I.e. results can not be generalized to the natural setting.

Reactive effects of testing/pretest sensitization
The pretest may influence the participant's response to experimental treatment. Also, the general population is not receiving the pre-test, and so the sample response cannot necessarily be generalized to the rest of the population.

Reliability
The extent to which a test yields consistent results and thus is replicable

Research hypothesis
A statement which indicates that there is an expected relationship between the independent and dependent variables

Sample size
The more heterogeneous a population, the larger the sample needs to be. A large sample is needed when looking for small differences.

Sampling distribution of means
The distribution of the means from samples drawn from a population

Sampling errors
Random chance errors that occur due to random variation in the population

Selection
A threat to internal validity caused by the non-random assignment of subjects to groups. When subjects are not assigned at random, there is a strong possibility that the two groups are not initially the same in certain important respects.

Selection bias
The selection process did not yeild a sample that is representative of the population demographically

Simple random sampling
Participants are selected on a completely random basis, such as a random number table. Every member of a population is given an equal chance of being included in a sample.

Snowball sampling
Find one individual to study who can then connect you to others like him/her; used for hard-to-locate participants.

Spearman rho
A test which calculates the degree to which two ranked variables are related

Split-half reliability
If the items are divided in half (e.g., odd vs even questions) the two halves give the same results.

Standard deviation
On average, how far the scores are from the mean.

Standard error of the mean
The standard deviation of the hypothetical normal distribution of sample means (from the Central Limit Theorem). Can also be calculated by dividing a sample's standard deviation by the square root of the number in the sample

Statistical regression
The tendency to regress towards the mean score of a group. Those who have extreme scores will most likely tend to be closer to the mean upon retesting. A threat to internal validity

Stratified random sampling
The researcher samples equally from each group of distinctly different individuals (strata) in a population.

Survey
A measure that describes attitudes, beliefs and ehaviors of a population.

Testing
The physical or menta effects that a first test has on the subject's performance on subsequent identical tests. A threat to internal validity

Test-retest reliability
A measure at two different times with no treatment in between will yield the same results.

Treatment

True experimental design
A design in which treatments are given and participants are randomly assigned to groups.

T-test for dependent means
the type of t-test used when each score in a one set of data is paired with scores in another set of data

T-test for independent means
the type of t-test used when the groups or samples are not related in some relevant way

Two-tailed
The type of test used with a non-directional hypothesis, using +/- 1.96 as the critical value

Type-I error
When the researcher rejects the null hypothesis even though it was true

Type-II error
When the researcher does not reject the null hypothesis even if there is a true difference-- i.e. the test does not have enough power to find a difference that is truly there.

Unbiased sample
A sample in which every member of the population has an equal chance of being included.

Validity
The extent to which a test measures what it is supposed to measure

Variability
The degree of homogeneity or heterogeneity within a given sample; The diversity of a sample

Variable
A trait or characteristic with two or more categories that can be measured--e.g. "gender"

Within groups design
A design that compares a group's results to a measure taken before treatment

Z-score
The conversion of a score to a standard deviation. This number tells how many standard deviations a score is from the mean.

Z-score (significance)
Answers this question: Given a population with a certain mean, how likely is it that I could draw a sample with my given sample mean?


A-L  |  M-Z