Research Methods #1.5

Front 1

nominal

Back 1

lowest level of measurement .

may be thought of as "naming" level

respond with words, not numbers

Front 2

ordinal

Back 2

measurement place participants in order from high to low

Front 3

interval

Back 3

equal interval without an absolute zero

Front 4

ratio

Back 4

equal interval with an absolute zero

Front 5

reliable

Back 5

a test is said to be _________ if it yields consistent results

Front 6

validity

Back 6

accurately measures what you're testing

Front 7

1. A test with high realiability may have low validity

2. Validity is more important than reliability

3. To be useful, an instrument must be both reasonably valid and reliable

Back 7

3 principles of realibility and validity

Front 8

interobserver reliability

Back 8

when two or more researchers agree on the realiability of the measurments taken

Front 9

correlation coefficient

Back 9

check the degree of relationship between 2 quanatative results.

1.00=perfect reliability

Front 10

test-retest reliability

Back 10

obtain measurments at two different points in time

Front 11

parallel forms of reliabilty

Back 11

some published tests come in two parallel forms that are designed to be interchangable with each other; they have different items that cover the same content

Front 12

split-half reliability

Back 12

checks on the consistency of scores within the test itself

Front 13

test-retest reliability
parallel forms of reliability

Back 13

which measure the consistency of scores over time?

Front 14

split-half
alpha

Back 14

which measures the consistency of items within a test at a single point in time?

Front 15

instrument

Back 15

any type of measurment device

Front 16

content validity

Back 16

researchers make judgements on the appropriateness of its contents

*essential for achievement tests

Front 17

face validity

Back 17

judgement is based on whether the instrument APPEARS to measure what it is supposed to measure

Front 18

content and face validity

Back 18

what two types of validity rely on judgements?

Front 19

predictive validity

Back 19

To what extent does the test predict the outcome it is supposed to predict

Front 20

construct validity

Back 20

the type of validity that relies on subjective judgements and empirical data

Front 21

1. origante question
2. develope rationale
3. fesability of answering question

Back 21

3 steps to formulate a question

Front 22

efficacy research

Back 22

the process of demonstrating under ideal conditions

Front 23

outcomes measurement

Back 23

the process of demonstrating under average or less than average conditions

Front 24

comparative or standard group

Back 24

*type of descriptive research

strategy to measure behvior of two or more types of participants at one point in time in order to draw conclusions about similarities and differences between them

Front 25

cohort studies

Back 25

pateints who presently have a condition and/or receive treatment are followed over a period of time and compared with another group who are not affected by the condition under investigation

Front 26

developmental or normative

Back 26

designed to measure changes over time in behavior or characteristic, usually with reference to aging and maturation

Front 27

cross-sectional

Back 27

select participants from various age groups and observe differences

*norms should be established on random selected participants who are a representative of population

*sample size must be appropriate to to population

Front 28

semilongitudinal

Back 28

compromise of longitudinal, divide total age span into overlapping age spans

Front 29

correlational

Back 29

-asks two basic questions
1. how closely related are the variables
2. how well can performance on one variable predict performance on another

Front 30

survey

Back 30

use questionaires, interviews, or combinatons

Front 31

retrospective or post facto

Back 31

done after the fact, IV occured in the past and investigator starts with effect

Front 32

case-control study

Back 32

a type of design often used in epidemiology

Front 33

case history

Back 33

examine one person in depth. looking at an unusual phenomen, hard to generalize

Front 34

frequency

Back 34

measures how many instances there were and what was the time frame
ex) he said ball 8 out of 10times

*good for nominal and ordinal data
*useful and objective

Front 35

duration

Back 35

count the duration of a type of behavior
ex) client was dysfluent for 15 minutes during 30 minutes of speaking time

*good for contineous behaviors

Front 36

interresponse time

Back 36

time lapse between any two discreet events or responses

ex)want kid to sit in chair
-count time elapsed between last time left seat to when he sits down to when he gets back up agaiin

Front 37

latency or reaction time

Back 37

how long it takes for a client to respond to a stimulus

Front 38

response amplitude

Back 38

intensity of response
ex)voice intensity, sweaty palms,

Front 39

utility

Back 39

is the date useful for your purpose?
will you be able to answer your research question with the data you're collecting

Front 40

sensitivity of test

Back 40

rarely fails to identify disorder or disease

mathmatically defined as a proportion of people who likewise test positive for disorder or disease

*gather all people with that trait (false-positives)

Front 41

speciicity of test

Back 41

seldom identifys a person having a disease or a disorder or when they don't

mathmatically defined as ratio of people who test negative on a screening test to people without disease or disorder

*might miss more (false positives)

Front 42

floor effect

Back 42

test so hard, no one can pass it

Front 43

ceiling effect

Back 43

test so easy, everyone can pass it

Front 44

precision

Back 44

the reliability aspect of a test, will it give you the same scores with each administration of test

Front 45

accuracy

Back 45

both reliablity and validity; tests what you want it to test and scores are reliable

Front 46

scaling power

Back 46

refers to scale of measurement

Front 47

test-retest

Back 47

methods to estimate reliability: stability

Front 48

parallel forms

Back 48

methods to estimate reliability: equivalence

Front 49

split-half
alpha
kuder-richardson #20 formula

Back 49

methods to estimate reliablity: internal consistency

Front 50

standard error of measurement

small SEM related to high levels of reliability

Back 50

SEM

Front 51

kappa

Back 51

statistic that takes into account fact that some agreements may occur by chance, especially in very frequently or less frequent occuring behaviors

Front 52

direct replication

Back 52

same investigator repeats same research with same or similar participants, in same physical setting, to confirm realiability of original results

Front 53

systematic replication

Back 53

try to extend generalization across participants, settings, measurments, or treatments

manipulates 1 or 2 variables

Front 54

threats to external validity

Back 54

the ability for research to be generalized

Front 55

selection bias

Back 55

generalizing the results to a population when an experiment is conducted on a nonrandom sample

Front 56

reactive effects of experimental arrangements

Back 56

if the experimental setting is different from the natural setting in which the population usually operates, the effects there were observed in the experimental setting may not be generalized to the natural setting

Front 57

reactive effect of testing
pretest sensitization

Back 57

a pretest might affect how a participant will respond to experimental treatment

Front 58

multi-treatment interference

Back 58

when a group of participants receive more than one treatment which could ultimately affect their responses to later treatment

Front 59

threats to internal validity

Back 59

explains how aspects other than the treatment actually working could interfer with the validity of an experiment

Front 60

history

Back 60

other enviormental influences on the participants between the pretest and the posttest

Front 61

maturation

Back 61

participant got older, wiser, or smarter between pre and post test

Front 62

instrumentation

Back 62

possible changes in the instrument

Front 63

testing

Back 63

effects of the pretest on the performance exhibited on the post test

Front 64

statistical regression

Back 64

occurs when participants are selected on the basis of their extreme scores

Front 65

intact groups

Back 65

researcher uses previously existing groups, so they are not random

Front 66

selection

Back 66

two different groups are not initially the same in all important aspects