Statistics And Research Design

Front 1

_________________ research is conduted to obtain a holistic description of the quality of relationshiops, actions, situations, or other phenomena. __________ research is conducted to obtain numerical data on variables.

Back 1

qualitative
quantitative

Front 2

Whenever observation is to be used to identify or meausre a behavior, an dimportant decision is how to record or mearue that behavior. ONe method is to obtain a narrativ record of the behavior as it actually occurs, with the record taking the form of detailed written descriptoin or an audio and/or visual recording. _____________, which involves organizing the data into categories, can then be used to summarize and interpret the informaiton containd in the narrative record. ___________ can be viewed as a type of content anaylsis. It is used by psychologists interested in the cognitive processes that underlie problem-solving and other complex tasks and involves aasking a subject to "think aloud" while solving a problem.

Back 2

content analysis
protocol analysis

Front 3

When using this method of sampling, every member of the population has an equal chance of being included in the sample, and the selction of one member from the pouulation has no effecton the selection of another member. It reduces the probablilkyt that a sample will be biased in some way, especially when the sample size is large.

Back 3

simple random sampling

Front 4

When the population of interest varis in terms of specific characteristics that are relevant to the research hypothesis, an invesntigator can use this sampoling to ensure that each characteristic is represented in teh sample. Theis invovles dividing the poulaiton into the approriate characteristic and readnomly selecting subject from each one. Typical characteristics indlude gender, age, educaiton level, SES, and racial, ethnic, or cultural background.

Back 4

stratified random sampling

Front 5

This sampling method entails selecting units of individuals rather than idnviiduals and either indcluding all individuals in those units in the reaserach study or randomly selecting indivduals from each unit. It is useful when it is not possible to identify or obtain access to the entire ouluation of interest.

Back 5

cluster sampling

Front 6

_____________ variable is a source of ____________ error. It is a variable that is irrelevant to the purpose of the study but confounds its results becasue it has a effect that corrleates with the dependent variable.

Back 6

extaneous (condounding)
systematic

Front 7

Randomization, holding ________ variable constant, mathinc gsubject on the __________ variable, building the ______ variable into the study, and statisitical contorl of the _________ variable are all methods to control the effects of _____________

Back 7

EXTRANEOUS VARIABLE

Front 8

A study has _________ validity when it allows an investigator to determine if there is a causal relationsihp between independent and dependent variables.

Back 8

internal

Front 9

"Can the relationshiop between the IV and DV be generalized to population?" This question refers to what type of validity?

Back 9

exteral

Front 10

Maturation, history, testing, and intsrumentation, statistical regression, selection, attrition, interactions with selection are all thrests to what type of validity?

Back 10

internal

Front 11

_________ validity refers to the genralizaability to other settings.

Back 11

ecological

Front 12

Interaction between testing and treatement, interaction between selection and treatment, reactivity, multiple treatment interference (order effects, carryover effects) are all threats to what type of validity?

Back 12

external

Front 13

__________ is when subjects resopnd to the IV becasue they know they are being observed. The behavior of reserach participants can also be altered by __________, or cuse in the experimental settings that inform subjects of the purpose of the study or suggest what behaviors are expected of them.

Back 13

reactivity
demand characterisitcs

Front 14

Whenevera a study includes two or more independent variables, it is called a ______________________. The major advantage of this is that it provides more thorough information about the relationships among variables by alowing an investigator to analyze the main effects of each indpendent variabel as well as the interaction between indipendent vairbles.

Back 14

factorial design

Front 15

A ________ effect is the ffect of one indpendent variable onteh dependent varialbe, disregrding the effects of all other indpendent variables, while an __________ effect refers to the effects of two or more indpendent variables considered together.

Back 15

main
interaction

Front 16

____________________ is used when the effects of different levels of an independent variable are assessed by administering each level to a differrent group of subjects and then comparing the status or performance of the groups on the dependent variable.

Back 16

between group design

Front 17

When using ________ all levels of the indpendent variable are administered sequentially to all subjects.

Back 17

within-subjects design

Front 18

A disadvantage of time-series and other within-subjects designs is that the analysis of the data can be confounded by ______________. IN other words subjects' performane on post-tests is likley to corrleate with their performance on the pretests. It can inflate the value of the inferential statitic, thereby resulting in an increased probablity of a type I error.

Back 18

autocorrelation

Front 19

The _______________ designs were derived primarily from the work of behavioral psychologists especially those engaged in applied behavioral analysis, which combines behavioral principles with the techniques of experimental psychology to solve socially-relevant problems. Rat study at UWM

Back 19

single subject design

Front 20

The simplest single-subject design is the _______ design., which includes a singel baseline phase and a singel treatment phase.

Back 20

AB design

Front 21

A psychologist tests an ADHD child's response to self-instruction training and observes attention span in three different setting before the administration then again in all three settings after. What type of reserach design is this?

Back 21

Single subject multiple baselin design

Front 22

Continuous vs. Discrete variable

Back 22

Continuous can take on an infinte number of values on measurment scale, while discret can't.

Front 23

A ________ scale of maeasurement divides varialbes into unordered categories. Male and Female

Back 23

Nominal

Front 24

An ________ scle is more mathematically complex than a nominal scale. It not only divides observations into categories but also provides information on the order of those categories. When using this scale, it is possible to say that one person has more or less of the characterisitc being measured than another person. A likert scale

Back 24

ordinal

Front 25

A ____ scale has the property of order as well as the property of equal intervals between successive points on the measurement scale. Scores on standardized IQ tests are examples, as a reslt, we can say that difference between 90 to 100 is equal to 90 and 95.

Back 25

interval

Front 26

The ______ scale is the most mathematically complex of the four measurement scales. It has the properties of order and equal intervals as well as the property of an absolute zero point. Examples include calories, number of correct items on a test, and reaction time in seconds.

Back 26

ratio

Front 27

IN a ____________ distribution more than half of the obeservations fall on one side of the distribution and a relatively few observations fall in the tail on the other side of the distribution. They can be positive or negative.

Back 27

skewed

Front 28

Measures of central tendency include the ______ which is the score that occurs most frequently in a set of data, the ________ is the middle number of an odd set of numbers and the number that falls in between the two middle numbers in a positive set of numbers, the _____ is the avearge.

Back 28

mode
median
mean

Front 29

Measures of variability include the _______ is subtracting the lowests score witht he highest, the ______ is a more thorough measure of variablity and its calculation includes all the scores in the distribution, it is also called mean square - it provides a measure of the average amount of variablity in a distribution by indicating the degree to which the scores are disperesed around the distribution's mean, and the __________ is most often used as a meausre of variablity. It is calulated by taking the square root of the vairance, which converts it to the same unit of measurement as the original scores.

Back 29

range
variance
standard deviation

Front 30

The larger the the standard deviation, the greater the dispersion of scores around the distribution's _____.

Back 30

mean

Front 31

When the distribution is normal __% of the scores fall between the scores that are plus and minus one stardard deviation from the mean; _____% between plus or minus two standard deveiations away from the mean; ___% 3 stardard deviations away from the mean.

Back 31

68
95
99

Front 32

The ________________ makes the following predictions:
- regardless of the shape of the distribution of individual scores in teh population, as the sample size increses, the samipling distribution of the mean approches a normal distritubtion.
- The mean of the sampling distrubion of the mean is equal ot the population mean.
- The standard deviation of the sampling distribution of the mean is equal to the population standard deviation deivided by the square root of the sample size.

Back 32

central limit theorem

Front 33

THe standard deviation of a sampling distribution of teh mean is known as the __________ of the mean. It provides an estimate of teh extent to which the mean of any one sample randomly drawn from a population can be expected to vary from the population mean as teh result of sampling error.

Back 33

standard error of teh mean.

Front 34

With a standard deviation of 10 and a sample size of 25, what is the standard error?

Back 34

SEM = O
____
N in bracket squared thingy

2

Front 35

Scores falling in the retention vs rejection region.
The size of the rejection region is defined by _____

Back 35

rejection region - lies in one or both tails of the sampling not due to error.
rejection - central may be due to error
ALPHA .05 OR .01

Front 36

Type I vs. Type II error

Back 36

Type one error is when you reject a true null hypothesis and Type II error is when you retain a false null hypothesis.

Front 37

Parametric tests vs. nonparametric tests

Back 37

parametic are for interval and ratio and non are for nominal and ordinal

Front 38

The _____ test is used to copare only two means at a time and that the choice of this test depends on how the two means were obtained.

Back 38

t-test

Front 39

The _________ is used to compare two or more means. An advanteage of this is that it simultaneaously makes all comparisons of group means while holding the probabiliy of making a type I error at the level of signficance set by the investigator.

Back 39

ANOVA

Front 40

Construct Validity

Back 40

most important kind. If a measure has contruct validity it measures what it purports to measure. Establising construct validity is a long and complext process.

Front 41

Criterion validity

Back 41

Criterion validity consists of concurrent and predictive validity.
Concurrent validity: "uDoes the measure relate to other manifestations of the construct the device is supposed to be measuring?"
Predictive validity: "uDoes the test predict an individual’s performance in specific abilities?"

Front 42

convergent validity

Back 42

It is important to know whether this tests returns similar results to other tests which purport to measure the same or related constructs.

Does the measure match with an external 'criterion', e.g. behaviour or another, well-established, test? Does it measure it concurrently and can it predict this “behaviour”?

Observations of dominant behaviour (criterion) can be compared with self-report dominance scores (measure)
Trained interviewer ratings (criterion) can be compared with self-report dominance scores (measure)

Front 43

Discriminant validity

Back 43

Important to show that a measure doesn't measure what it isn't meant to measure - i.e. it discriminates.

For example, discriminant validity would be evidenced by a low correlation between between a quantitative reasoning test and scores on a reading comprehension test, since reading ability is an irrelevant variable in a test designed to measure quantitative reasoning.