Sw 7009 Final Exam Fall 2013

Front 1

inaccurate observation

Back 1

self-explanatory; can be guarded against by using simple and complex measurement devices

Front 2

overgeneralization

Back 2

assuming that a few similar events are evidence of a general pattern; can be guarded against by using large sample sizes and replication of studies

Front 3

selective observation

Back 3

paying attention to only future events that correspond with the pattern you have generalized (e.g. only taking note of lazy Mexicans after hearing the generalization that all Mexicans are lazy)

Front 4

ex post facto hypothesizing

Back 4

making hypothesis after observing; perfectly acceptable as long as it is tested

Front 5

ego involvement in understanding

Back 5

being biased in the belief that your own work and techniques are effective; can be guarded against by consulting supervisors or other practitioners for an objective point of view

Front 6

Bottom-up searches

Back 6

search literature looking for any and all source that provide evidence pertaining to the practice question you formulated

Front 7

Top-down searches

Back 7

rely on the results of evidence-based searches that others have done

Front 8

Evidence Based Practice Process

Back 8

applying the scientific method to practice decisions

Front 9

Evidence based practices

Back 9

specific practices that have shown to be effective in working with a given client population

Front 10

Qualitative

Back 10

– procedures evolve as more observations are gathered; typically permit the use of subjectivity to demonstrate deeper understandings of meanings of human experiences

Front 11

Quantitative

Back 11

seek to produce precise and quantifiable findings; all or most procedures are formulated in advance; strict adherence to procedures with maximum objectivity

Front 12

Exploration

Back 12

provides a beginning familiarity on a topic; seldom provide conclusive answers

Front 13

Description

Back 13

to describe situations and events

Front 14

Explanation

Back 14

to explain a phenomenon

Front 15

Evaluation

Back 15

to evaluate the effectiveness of a policy

Front 16

Constructing Measurement Instruments

Back 16

to make measurement instruments for others to use

Front 17

Cross sectional studies

Back 17

examines a phenomenon by taking a “snapshot” of it at one time and carefully analyzing it (e.g. US Census)

Front 18

Longitudinal studies

Back 18

intended to describe processes occurring over time; observations are conducted over an extended period; important part is that observations occur at different points in time

Front 19

Aspects of good research questions

Back 19

1. narrow and specific; 2. answerable by observable evidence; 3. relevant; 4. feasible

Front 20

Concept

Back 20

mental image that symbolizes an idea, an object, an event, a behavior, a person, etc.; words that people agree upon to symbolize something

Front 21

Variables

Back 21

concepts investigated by researchers; must be expected to vary

Front 22

Attributes

Back 22

different variations of a concept

Front 23

concept, attributes

Back 23

A variable is a _________ being investigated that is characterized by different _________.

Front 24

hypothesis

Back 24

a tentative and testable statement about a presumed relationship between variables

Front 25

independent variable

Back 25

the variable being explained or caused; this is the variable we seek to measure

Front 26

control variable

Back 26

a moderating variable that we seek to control by holding it constant in our research design

Front 27

positive relationship

Back 27

both variables move in the same direction (e.g. time spent studying and test scores)

Front 28

negative/inverse relationship

Back 28

variables move in opposite directions; as one increases, the other decreases and vice versa (e.g. hours spent partying and test scores)

Front 29

curvilinear relationship

Back 29

a relationship in which the nature of the relationship changes at certain levels of the variables (e.g. anxiety and performance)

Front 30

nominal level

Back 30

attributes of variables are categorical and can be described in terms of how many but not degree of (gender, ethnicity, birthplace)

Front 31

ordinal level

Back 31

attributes may be rank-ordered according to degree (level of education in terms of: high school diploma/GED, some college, bachelor's degree, etc.)

Front 32

interval level

Back 32

differences between different levels have the same meanings (differences between IQ scores of 100 and 105 compared to 95 and 100)

Front 33

ratio level

Back 33

same attributes of interval measures but with a true zero point (number of arrests)

Front 34

measurement error

Back 34

data do not accurately portray the concept we attempt to measure

Front 35

systematic error

Back 35

type of measurement error; the info we collect consistently reflects a false picture (e.g. acquiescent response set; social desirability bias)

Front 36

random error

Back 36

type of measurement error; no consistent pattern of effects (e.g. cumbersome, complex, boring measurement procedures or measures use professional jargon which respondents are not familiar with)

Front 37

triangulation

Back 37

using several different research methods to collect the same information; useful in avoiding measurement error

Front 38

Interobserver and Interrater reliability

Back 38

degree of agreement or consistency between/among observers

Front 39

Test-retest reliability

Back 39

assessing a measure’s stability over time; acceptable reliability: above .70 or .80

Front 40

Internal consistency reliability

Back 40

assess whether the items of a measure are internally consistent (using the split halves method or parallel forms reliability)

Front 41

Validity

Back 41

whether a particular measurement measures what we seek to measure; (synonymous with “accuracy”)

Front 42

Face validity

Back 42

whether a measure appears to measure what is supposed to measure; subjective assessment

Front 43

Content validity

Back 43

the degree to which a measure covers the range of meanings included within the concept; subjective assessment

Front 44

Criterion-related validity

Back 44

based on some external criterion

Front 45

Predictive validity

Back 45

measure can predict a criterion that will occur in the future

Front 46

Concurrent validity

Back 46

measure corresponds to a criterion that is known concurrently

Front 47

Construct validity

Back 47

assess whether a measure fits theoretical expectations

Front 48

Convergent validity

Back 48

IDK

Front 49

Discriminant validity

Back 49

IDK

Front 50

Factorial validity

Back 50

whether the number of constructs and the items that make up those constructs measure what the researcher intends to measure

Front 51

Guidelines for asking questions:

Back 51

(1) Be specific and consistent;
(2) Use plain, simple language;
(3) Don't ask double-barreled questions;
(4) Don't lead the interviewee (no loaded questions)

Front 52

types of survey

Back 52

mail, online, interview (in-person), telephone

Front 53

strengths of mail survey

Back 53

cheaper and quicker; large samples; anonymity facilitates responses regarding sensitive areas

Front 54

weaknesses of mail survey

Back 54

expensive and time consuming; lower response rates than face-to-face

Front 55

strengths of online survey

Back 55

less expensive and time consuming; largest samples; automatic data entry; anonymity facilitates responses regarding sensitive areas

Front 56

weaknesses of online survey

Back 56

representativeness (especially among poor and elderly); lower response rates than face-to-face

Front 57

strengths of interview (in-person)survey

Back 57

higher response rate; minimizes "don't know" or "no" answers; allows interviewers to observe respondent while asking questions

Front 58

weaknesses of interview (in-person) survey

Back 58

more expensive and time-consuming; lack of anonymity can impede responses regarding sensitive areas; interviewer safety

Front 59

strengths of telephone survey

Back 59

inexpensive; more honest answers; interviewers have more support; opportunity to probe/clarify; personal safety; opportunity for supervision; can be computer-assisted

Front 60

weaknesses of telephone survey

Back 60

bogus surveys; survey discontinuation; ease of hanging up; answering machines; caller id; cell phones

Front 61

Sample

Back 61

subset of a population that is observed for purposes of making inferences about the nature of the total population

Front 62

Probability Sampling

Back 62

random selection; each participant has an equal chance of selection

Front 63

Overgeneralization

Back 63

sampling frames are not consistent with what we seek to generalize

Front 64

Cultural bias

Back 64

unwarranted generalization of research findings to the population as a whole when one culture or ethnic group is not adequately represented in the sample

Front 65

Gender bias

Back 65

unwarranted generalization of research findings to the population as a whole when one gender is not adequately represented in the sample

Front 66

Nonresponse bias

Back 66

substantial number of people chosen choose not to participate

Front 67

Nonprobability Sampling

Back 67

used when probability or random sampling is not possible or appropriate (e.g. homeless individuals)

Front 68

Availability or convenience sampling

Back 68

sampling from subjects who are available (e.g. college students)

Front 69

Purposive or judgmental sampling

Back 69

researcher used his or her own judgment in selecting sample members (e.g. handpicking community leaders or experts for expertise on target population)

Front 70

Quota sampling

Back 70

relative proportion of the total population is assigned for the target population’s characteristics, grouped into strata, and then sampled

Front 71

Snowball sampling

Back 71

process of accumulation as each located subject suggests other participants

Front 72

Sampling frame

Back 72

list or quasi-list of members of a population (e.g. student roster, telephone directory)

Front 73

Simple random sampling

Back 73

each element in sampling frame is assigned a number and a table of random numbers is used to select elements for the sample

Front 74

Systematic Sampling

Back 74

selection of every kth element or member of the sampling frame

Front 75

Stratified sampling

Back 75

grouping members of a population into homogeneous strata before sampling (e.g. ethnic group or gender); improve the representativeness of a sample by reducing the degree of sampling error

Front 76

criteria for establishing causality

Back 76

(1) The IV must precede the DV chronologically; (2) There must be a relationship or correlation between the IV and DV; (3) The co-variation between the two variables cannot be explained by a third variable

Front 77

establish causation

Back 77

The goal of experimental designs is to _____________.

Front 78

threats to internal validity

Back 78

history, maturation, testing, instrumentation, statistical regression, selection bias, ambiguity about the direction of causal influence [SHAMITS]

Front 79

History

Back 79

external events; changes occur outside the person

Front 80

Maturation

Back 80

passage of time; changes occur within a person

Front 81

Testing

Back 81

process of testing itself enhances performance on a test; also: social desirability, in which participants choose what they think researchers want

Front 82

Instrumentation

Back 82

change in instrumentation over time (e.g. switching from one measure to another between pre- and post-test); instrument decay (e.g. physical decay in a measurement apparatus)

Front 83

Statistical regression

Back 83

extreme scores will regress to the mean

Front 84

Selection bias

Back 84

differences between two groups prior to intervention

Front 85

Ambiguity about the direction of causal influence

Back 85

related to time order of IV and DV; DV could actually cause IV

Front 86

Experimental

Back 86

only design that can claim causality; requires random assignment to experimental and control group and comparison of results between the two

Front 87

random assignment

Back 87

r indicates:

Front 88

measurement

Back 88

o indicates

Front 89

intervention

Back 89

x indicates:

Front 90

Pre-experimental

Back 90

no randomization; cannot claim causality; commonly used in pilot studies; use of comparison group as opposed to control group

Front 91

Quasi-experimental

Back 91

similar to experimental design, except that participants cannot be randomly assigned (e.g. smokers vs. non-smokers; would be unethical to cause someone to become addicted to nicotine)

Front 92

Advantages to secondary analysis

Back 92

data is already there, less costly and time consuming

Front 93

Disadvantages to secondary analysis

Back 93

no control over sampling; must trust that data is reliable

Front 94

Continuous variable

Back 94

can theoretically have an infinite number of values between adjacent units on a scale

Front 95

Discrete variable

Back 95

one in which there are no possible values between adjacent units on a scale

Front 96

Mean

Back 96

average; add up the values to find the sum and then divide by the number of values

Front 97

Median

Back 97

the middle; remove the highest and lowest value until you arrive at the middle; if there are an odd number of values, average the two in the middle to find the median

Front 98

Mode

Back 98

most frequent value; the value that appears more often than any other value; there can be more than one

Front 99

Standard deviation

Back 99

typical distance from the mean; do not need to know how to calculate; 0 = no variation among values

Front 100

p-value

Back 100

the probability of an observed relationship being caused by chance; this value is compared to the “significance level” or “alpha (α) level” (customary “significance level” is 0.05)