Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
256 Cards in this Set
- Front
- Back
|
3 ways social workers know things
|
agreement reality
experiential reality science |
|
|
3 principles of scientific method
|
knowledge is ALWAYS subject to change
empirical evidence is based on specified and systematic observation everything is open to question |
|
|
3 principles of good research
|
based on large and diverse sample
specified well enough so that it can be accurately replicated honest about potential biases and minimizes their effect |
|
|
tradition
|
shared meaning and understanding that is often considered obvious
|
|
|
authority
|
knowledge accepted based on the status or power of the messenger
|
|
|
common sense
|
reasoning or commonly held beliefs
|
|
|
popular media
|
tv, internet, newspapers and other popular sources
|
|
|
5 flaws in unscientific sources
|
inaccurate observation
overgeneralization selective observation ex post facto hypothesizing ego involvement |
|
|
inaccurate observations result from?
|
human error
failure to observe things right in front of us |
|
|
overgeneralization
|
the assumption that a few similar events are evidence of a general pattern
|
|
|
selective observation
|
tendency to pay attention to future events and situations that correspond to or confirm a pattern perceived to be true
|
|
|
ex post facto
|
proposing a new argument to explain findings AFTER research has been conducted
|
|
|
ego involvement
|
personal involvement in a particular result or finding clouds objectivity
common when a developer tests her own intervention |
|
|
ad hominem attack
|
discrediting the person rather than the argument
illogical reasoning |
|
|
newness
|
touting something because it is novel
illogical reasoning |
|
|
bandwagon
|
everyone else is doing it argument
illogical reasoning |
|
|
straw person argument
|
distorting an argument in order to attack it
illogical reasoning |
|
|
evidence-based practice
|
practice model based primarily on the scientific method and scientific evidence
|
|
|
what does evidence-based practice do?
|
encourages integration of scientific evidence, practice expertise, and client circumstances
evaluates outcomes is applicable for intervention, assessment, policy and community practice |
|
|
evidence-based medicine
|
1980s
process of using the best available evidence to make clinical decisions for individual medical care integration of best research evidence with clinical expertise and patient values |
|
|
nature of evidence-based practice
|
client-centered
requires critical thinking and understanding research design and methods |
|
|
6 steps in evidence-based practice
|
formulate a question to answer practice needs
search for evidence critically appraise relevant studies determine which EBP is most appropriate for the CLIENT apply EBP evaluation and feedback |
|
|
CIAO
|
how to formulate a question if one or more interventions are specified in advance
Client characteristics Intervention being considered Alternative intervention Outcome |
|
|
main question to ask when critically appraising relevant studies
|
was treatment outcome measured in reliable, valid, unbiased manner?
causality? |
|
|
most problematic controversy of EBP
|
real world obstacles prevent implementation
superiors don't understand EBP time constraints insufficient and limited resources |
|
|
ideology
|
closed system of beliefs and values
assumptions are fixed and not open to questioning shapes understanding and behavior |
|
|
paradigm
|
organizes our observations and makes sense of them
more open to question and modification than ideologies evolve over time |
|
|
contemporary positivism
|
paradigm that emphasizes objectivity, precision, and generalizability in research
|
|
|
interpretivism
|
paradigm that emphasizes in depth subjective understanding of people's lives
|
|
|
critical social science
|
paradigm that focuses on oppression and uses research methods to empower oppressed groups
|
|
|
differentiating between paradigm and theory
|
paradigms are general frameworks for understanding aspects of life
theory is a systematic set of interrelated statements to explain aspects of life or how people conduct and find meaning in their life |
|
|
theory and social work
|
theories deal with what is, not what should be
helps us make sense of patterns helps direct inquiry into areas that are likely to show useful patterns helps develop useful implications from findings for practice, policy, research |
|
|
5 components of theory
|
hypothesis
variable independent variable dependent variable attributes |
|
|
hypothesis
|
statement that predicts relationship between variables
|
|
|
variable
|
concept that symbolizes an idea, object, event or person
|
|
|
IV
|
explains or causes something
|
|
|
DV
|
being explained or caused
|
|
|
attributes
|
characteristics or qualities that describe something or somebody
make up variables or concepts ex. male and female are attributes of variable gender |
|
|
what do credible theories depend on?
|
empirical support of observations
systematic and logical components |
|
|
deductive method
|
begins with theory and derives one or more hypotheses to test in research
top down |
|
|
inductive method
|
begins with observed data and develops hypotheses to explain observations
bottom up |
|
|
probabilistic model of causation
|
most explanatory research uses this
if A occurs, B is more likely to occur don't speak in terms of certainty |
|
|
ideographic model
|
causal model of explanation
seeks to understand everything about a particular individual or case by using many factors ex. why has a particular young man become delinquent? |
|
|
nomothetic model
|
causal model of explanation
seeks a partial understanding of a general phenomenon using few factors ex. what factors are most important for explaining delinquency among young people? typically quantitative |
|
|
quantitative method
|
attempt to produce precise and generalizable findings
more appropriate for nomothetic |
|
|
qualitative methods
|
emphasizes deeper meanings of human experience
intended to generate theoretically rich observations not easily reduced to numbers |
|
|
inductive method
|
begins with observed data and develops hypotheses to explain observations
bottom up |
|
|
ways to prevent biases from influencing observation
|
employ blind observers
self-report scales outside of researcher's presence existing info (school records) |
|
|
probabilistic model of causation
|
most explanatory research uses this
if A occurs, B is more likely to occur don't speak in terms of certainty |
|
|
cross-sectional study
|
examines and analyzes phenomenon by taking a cross section of it AT ONE TIME
|
|
|
ideographic model
|
causal model of explanation
seeks to understand everything about a particular individual or case by using many factors ex. why has a particular young man become delinquent? |
|
|
inductive method
|
begins with observed data and develops hypotheses to explain observations
bottom up |
|
|
nomothetic model
|
causal model of explanation
seeks a partial understanding of a general phenomenon using few factors ex. what factors are most important for explaining delinquency among young people? typically quantitative |
|
|
longitudinal study
|
observations over an EXTENDED PERIOD of time
|
|
|
quantitative method
|
attempt to produce precise and generalizable findings
more appropriate for nomothetic |
|
|
probabilistic model of causation
|
most explanatory research uses this
if A occurs, B is more likely to occur don't speak in terms of certainty |
|
|
trend studies
|
longitudinal
study general population over time (US census) |
|
|
qualitative methods
|
emphasizes deeper meanings of human experience
intended to generate theoretically rich observations not easily reduced to numbers |
|
|
ideographic model
|
causal model of explanation
seeks to understand everything about a particular individual or case by using many factors ex. why has a particular young man become delinquent? |
|
|
nomothetic model
|
causal model of explanation
seeks a partial understanding of a general phenomenon using few factors ex. what factors are most important for explaining delinquency among young people? typically quantitative |
|
|
ways to prevent biases from influencing observation
|
employ blind observers
self-report scales outside of researcher's presence existing info (school records) |
|
|
quantitative method
|
attempt to produce precise and generalizable findings
more appropriate for nomothetic |
|
|
cross-sectional study
|
examines and analyzes phenomenon by taking a cross section of it AT ONE TIME
|
|
|
qualitative methods
|
emphasizes deeper meanings of human experience
intended to generate theoretically rich observations not easily reduced to numbers |
|
|
longitudinal study
|
observations over an EXTENDED PERIOD of time
|
|
|
ways to prevent biases from influencing observation
|
employ blind observers
self-report scales outside of researcher's presence existing info (school records) |
|
|
trend studies
|
longitudinal
study general population over time (US census) |
|
|
cross-sectional study
|
examines and analyzes phenomenon by taking a cross section of it AT ONE TIME
|
|
|
longitudinal study
|
observations over an EXTENDED PERIOD of time
|
|
|
trend studies
|
longitudinal
study general population over time (US census) |
|
|
cohort studies
|
longitudinal
study a specific subpopulation as they change over time |
|
|
panel studies
|
longitudinal
study the same people over time |
|
|
4 types of research
|
exploration
description explanation evaluation |
|
|
exploration
|
explores a topic to provide a beginning familiarity
breaking new ground |
|
|
description
|
describes situations and event
ex. US Census |
|
|
explanation
|
tries to answer "why" questions
|
|
|
evaluation
|
evaluates social policies, programs, interventions
encompasses exploration, description and explanation |
|
|
7 phases of research process
|
formulate problem
design study collect data process data analyze data interpret findings write report |
|
|
institutional review board
|
panel of professionals that give approval to researchers when their studies involve human subjects
became widespread during 1970s as a result of federal legislation and public concern with ethics of biomedical and behavioral research |
|
|
ethical issues in social work research
|
voluntary participation and informed consent (can conflict with generalizability)
no harm to participants (study benefits must outweigh risks of harm) protection of participant identities (anonymous and confidential) deception of participants negative findings must be reported |
|
|
NASW Code of Ethics
|
critically examine and keep current with emerging knowledge
routinely review professional literature base practice on recognized knowledge, including empirically based knowledge, relevant social work and social work ethics |
|
|
politics of social work
|
ethics deal with methods employed
political issues concerned with practical costs and use of research |
|
|
topic selection should be guided by (3 things)
|
decisions that enhance social services at agencies
practical problems in social welfare information needs related to policy, planning and practice |
|
|
5 attributes of a good research question
|
narrow and specific
more than one possible answer posed in a way that can be answered by observable evidence addresses the decision-making needs of agencies of practical problems in social welfare has clear significance for guiding social welfare policy or practice |
|
|
feasibility
|
extent to which a stud may be done practically and successfully
scope, time, fiscal cost, ethical issues, cooperation with research partners, study participants |
|
|
ecological fallacy
|
occurs when a researcher erroneously draws conclusions about individuals based on the examination of groups
ex. findings that suicide rates are higher in Protestant countries cannot lead us to assume that Protestants have higher rates of suicide than Catholics |
|
|
5 ways literature review helps
|
problem selection
understanding if question has been answered identifying conceptual and practical obstacles learning how to address obstacles building on existing research |
|
|
reductionism
|
overly strict limitation on the kinds of concepts and variables to be considered relevant to the phenomenon under study
ex. economic or psychological |
|
|
concept
|
mental image that symbolizes an idea, object, event, behavior, person
|
|
|
extraneous variables
|
represent alternative explanations for relationships that are observed between the IV and DV
may be examined to see if observed relationship is misleading |
|
|
mediating variable
|
mechanism by which IV affects DV
|
|
|
moderating variable
|
can affect strength or direction of relationship between IV and DV
|
|
|
types of relationships between variables
|
positive, negative, curvilinear
|
|
|
positive relationship
|
as IV increases, DV increases or as IV decreases, DV decreases
|
|
|
negative relationship
|
as IV increases, DV decreases or as IV decreases, DV increases
|
|
|
curvilinear relationship
|
ex. skepticism decreases as students take more research courses up to a point, but after that skepticism increases as more research courses are taken
|
|
|
levels of measurement
|
nominal
ordinal interval ratio |
|
|
nominal level of measurement
|
equivalence - different or same
ex. race |
|
|
ordinal level of measurement
|
rank-order - more, less, same
ex. motivation - very low, low, high, very high |
|
|
interval level of measurement
|
equal intervals between adjacent units without an absolute zero point (non-existence of certain attribute)
ex. temperature, IQ |
|
|
ratio level of measurement
|
absolute zero point
ex. length, weight, age |
|
|
conceptualization
|
process through which we specify precisely what we will mean when we use particular terms
|
|
|
range of variation
|
extent we combine attributes in fairly gross categories
|
|
|
problems of operationally defining variables
|
may not know in advance what most salient variables are
limited understanding of variables may keep us from anticipating best way to operationally define those variables even the best operational definitions are superficial |
|
|
measurement error
|
data do not accurately portray the concept we attempt to measure
|
|
|
systematic error
|
when the information we collect consistently reflects a false picture
biases are most common systematic error |
|
|
random error
|
no consistent pattern of effects
ex. complex or boring measurement procedures, measure uses professional jargon which respondents are not familiar with |
|
|
errors in written self reports
|
item wording
words vs. deeds |
|
|
errors in direct behavioral observation
|
social desirability bias
observers might be biased |
|
|
errors in interviews
|
different interviewers
social desirability bias |
|
|
errors in examining available records
|
practitioner might exaggerate their records
improper documenting |
|
|
ways to avoid measurement error
|
use unbiased wording
carefully train interviewers use unobtrusive observations to minimize social desirability bias understand how existing records are kept triangulation |
|
|
triangulation
|
using several different research methods to collect the same information
|
|
|
reliability
|
particular measurement technique, when applied repeatedly to the same object, would yield the same result each time
more reliable, less random error |
|
|
interobserver and interrater reliability
|
the degree of agreement or consistency between/among observers
|
|
|
test-retest reliability
acceptable reliability? |
assessing a measure's stability overtime
acceptable reliability = above .7 or .8 (higher the better) |
|
|
internal consistency reliability
|
assess whether the items of a measure are internally consistent
use split-halves method or parallel forms reliability to assess this |
|
|
face validity
|
measure appears to measure what it is supposed to
determined by subjective assessment made by the researcher or other experts |
|
|
content validity
|
degree to which a measure covers the range of meanings included within the concept
established based on judgment |
|
|
criterion-related validity
|
based on some external criterion
subtypes - predictive, concurrent validity |
|
|
predictive validity
|
measure can predict a criterion that will occur in the future
|
|
|
concurrent validity
|
measure corresponds to a criterion that is known concurrently
|
|
|
construct validity
|
assess whether a measure fits theoretical expectations
|
|
|
factorial validity
|
scale may measure more than one dimension
refers to whether the number of constructs and the items that make up those constructs measure what the researcher intends |
|
|
close-ended questions must be...
|
exhaustive and mutually exclusive
|
|
|
close-ended questions must be...
|
exhaustive and mutually exclusive
|
|
|
guidelines for asking questions
|
clear items
avoid double-barreled questions respondents must be competent and willing to answer questions should be relevant short items are best avoid words like no or not avoid biased items be culturally sensitive |
|
|
guidelines for asking questions
|
clear items
avoid double-barreled questions respondents must be competent and willing to answer questions should be relevant short items are best avoid words like no or not avoid biased items be culturally sensitive |
|
|
questionnaire construction
|
spread out and uncluttered
use genuine boxes contingency questions - respondents only answer questions that are relevant |
|
|
questionnaire construction
|
spread out and uncluttered
use genuine boxes contingency questions - respondents only answer questions that are relevant |
|
|
item selection for scales
|
proper face validity
adequate variance reliability and validity |
|
|
item selection for scales
|
proper face validity
adequate variance reliability and validity |
|
|
Likert scaling
|
question format that is frequently used in survey questionnaires
respondents indicate their choice from unambiguously ordered response categories strongly agree, agree, disagree, strongly disagree |
|
|
Likert scaling
|
question format that is frequently used in survey questionnaires
respondents indicate their choice from unambiguously ordered response categories strongly agree, agree, disagree, strongly disagree |
|
|
semantic differential
|
choosing between two opposite directions
ex. simple to complex and you choose very much, somewhat, neither, somewhat, very much |
|
|
semantic differential
|
choosing between two opposite directions
ex. simple to complex and you choose very much, somewhat, neither, somewhat, very much |
|
|
survey research
|
one of the oldest methods of research and the most frequently used mode of observation
|
|
|
survey research
|
one of the oldest methods of research and the most frequently used mode of observation
|
|
|
survey research is best for
|
exploratory and explanatory research
best for describing a population that is too large to observe directly |
|
|
survey research is best for
|
exploratory and explanatory research
best for describing a population that is too large to observe directly |
|
|
mail survey questionnaires
|
include cover letter, monitor returns, follow up mailings
higher response rate, less significant response bias (50% is acceptable, 70% is very good) |
|
|
mail survey questionnaires
|
include cover letter, monitor returns, follow up mailings
higher response rate, less significant response bias (50% is acceptable, 70% is very good) |
|
|
ways to improve mail surveys
|
follow-up
offering remuneration attractive format sponsorship or endorsements personalization shortened format good timing |
|
|
ways to improve mail surveys
|
follow-up
offering remuneration attractive format sponsorship or endorsements personalization shortened format good timing |
|
|
date of first follow up
|
15 days after initial mail out
|
|
|
second follow up
|
day 22
|
|
|
interview surveys
|
higher response rate than mail
minimizes don't know or no answers |
|
|
general guidelines for survey interviewing
|
appearance and demeanor
familiarity with questionnaire follow question wording exactly record responses exactly probes for responses must be completely neutral |
|
|
advantages of phone surveys
|
money and time
more honest answers interviewers have more support personal safety |
|
|
disadvantages of telephone surveys
|
bogus surveys
survey discontinuation answering machines cell phones |
|
|
advantages of online surveys
|
quick and inexpensive
ideal for some populations |
|
|
disadvantages of online surveys
|
representativeness
technological problems |
|
|
how long should an online survey be?
|
15 minutes or less
|
|
|
7 strengths of survey research
|
describes characteristics of large population
makes large sample feasible makes findings more generalizable enables analysis of multiple variables flexible analysis uniform measurement strong reliability |
|
|
5 weaknesses of survey research
|
fitting of round pegs into square holes
lack of context inflexibility of design artificiality weak in validity |
|
|
element
|
the unit about or from which information is collected for a sample
|
|
|
population
|
the theoretically specified aggregation of elements
|
|
|
sampling unit
|
the element or set of elements (cluster) considered for selection in some stage of sampling
|
|
|
sampling frame
|
the actual list of sampling units
|
|
|
sample
|
subset of elements selected from a population that is observed for purposes of making inferences about the nature of the total population
|
|
|
nonprobability sampling
|
used when probability or random sampling is not possible (ex. homeless)
less reliable, but easier and cheaper |
|
|
4 types of nonprobability sampling
|
availability or convenience sampling
purposive or judgmental sampling quota sampling snowball sampling |
|
|
availability or convenience sampling
|
sampling from subjects who are available
ex. how much an agency's services help a particular client or group of clients |
|
|
purposive or judgmental sampling
|
when researcher uses her own judgment in selecting sample members
ex. handpick community leaders or experts known for their expertise on target population |
|
|
quota sampling
|
relative proportion of the total population is assigned for the target population's characteristics (ex. gender), grouped into strata or cells, and the required number of participants from each stratum or cell is then selected
|
|
|
snowball sampling
|
process of accumulation as each located subject suggests other participants
|
|
|
chief criterion of the quality of a sample
|
degree to which a sample is representative - extent to which the characteristics of the sample resemble those of the population for which it was selected
|
|
|
basic principle of probability sampling
|
all members of population will have an equal chance of being selected in the sample, know as equal probability of selection method
|
|
|
element of probability sampling
|
unit about which information is collected and that provides basis for analysis
|
|
|
ultimate purpose of probability sampling
|
to select a set of elements from a population in such a way that descriptions of those elements accurately portray the total population from which items are selected
|
|
|
random selection
|
each element has an equal chance of selection independent of any other event in the selection process
|
|
|
probability sampling sampling frame
|
list or quasi-list of members of a population (school roster, telephone directory)
|
|
|
nonresponse bias
|
occurs when a substantial number of people in a randomly selected sample choose not to participate
|
|
|
cultural bias
|
unwarranted generalization of research findings to the population as a whole when once culture or ethnic group is not adequately represented in the sample
|
|
|
gender bias
|
unwarranted generalization of research findings to the population as a whole when one gender is not adequately represented in the sample
|
|
|
simple random sampling
|
each element in sampling frame is assigned a number
a table of random numbers is then used to select elements for the sample |
|
|
systematic sampling
|
selection of every kth element or member of the sampling frame
first element selected at random to avoid bias elements chosen based on sampling interval |
|
|
stratified sampling
|
involves the process of grouping members of a population into homogeneous strata before sampling
improves the representativeness of a sample by reducing the degree of sampling error |
|
|
3 probability sampling designs
|
simple random
systematic stratified |
|
|
multistage cluster sampling
|
more complex technique frequently used in cases in which a list of all members of a population does not exist
initial sample of group members is selected and then listed the listed members are subsampled, which provides final sample of members |
|
|
advantages to using existing data
|
expedience
unobtrusiveness ability to study the past cheap, fast, large sample |
|
|
secondary analysis
|
a form of research in which the data collected and processed in one study are reanalyzed in a subsequent study
|
|
|
purposes of secondary analysis
|
reanalyze data to resolve doubts
answer a new research question use unanalyzed data |
|
|
sources of existing statistics
|
administrative and public records
ex. Statistical Abstract of the US Federal agencies, demographic yearbook |
|
|
disadvantages of using existing data
|
old data
no control over questions asked missing data validity and reliability problems |
|
|
content analysis
|
a method of transforming qualitative material into quantitative data
|
|
|
purposes of content analysis
|
coding and tabulating the occurrences of certain forms of content that are being communicated
particularly useful to answer who says what to whom, why, how, and with what effect? |
|
|
sampling (content analysis)
|
determine what to observe, for how long, and how often
can occur at many levels (books, words) focuses on depth vs. specificity |
|
|
manifest content
|
visible, surface content
|
|
|
latent content
|
underlying meaning
|
|
|
strengths of content analysis
|
low costs in time and money
ease of correcting errors long periods of time unobtrusiveness |
|
|
weaknesses of content analysis
|
limited to recorded communication
validity and reliability |
|
|
historical and comparative analysis
|
method designed to trace the development of social forms over time and compare these developmental processes across cultures often based on historical record
|
|
|
purposes of historical and comparative analysis
|
biographies of social work pioneers
case studies of policies and programs identifying recurring patterns to inform the present |
|
|
raw data
|
primary sources
diaries sermons lectures government reports |
|
|
hermeneutics
|
art, science, or skill of interpretation
|
|
|
inference
|
conclusion that can be drawn logically given the research design and findings
|
|
|
causal inference
|
implies that the IV has a causal impact on the DV
|
|
|
research design
|
refers to decisions made in planning and conducting research
often used in connection with whether logical arrangements permit causal inferences |
|
|
3 criteria for inferring causality
|
cause must precede the effect in time
the 2 variables are empirically correlated with one another the observed empirical correlation between the 2 variables cannot be due to the influence of a 3rd variable that causes the 2 under consideration |
|
|
internal validity
|
depends on extent to which 3 criteria for causality are met
refers to whether or not causal inferences can be drawn from results |
|
|
7 threats to internal validity
|
history
maturation testing instrumental changes statistical regression selection bias ambiguity regarding the direction of causal inference |
|
|
pre-experimental design
|
limited degree of internal validity
exploratory or descriptive purposes |
|
|
3 common pre-experimental designs
|
one-shot case study
one-group pretest-posttest design posttest-only design with nonequivalent groups |
|
|
one-shot case study
|
administers experimental stimulus to a single group and measures DV in that group.
fails to control for any threats to internal validity |
|
|
one-group pretest-posttest design
|
measure DV in a single group, administer experimental stimulus, and then remeasure DV
establishes correlation and time order but does not account for factors other than IV that might cause change in DV |
|
|
posttest only design with nonequivalent groups
|
administer experimental stimulus to one group, then measure DV in both experimental group and control group
cannot infer that any differences between the 2 groups was caused by the intervention |
|
|
true-experimental designs
|
strongest designs allowing social work researchers and EBP to have increased confidence in making causal references based on study findings
|
|
|
what do true-experimental designs assume?
|
the process of random assignment removes any significant initial differences between experimental and control groups
|
|
|
what do true-experimental designs control for?
|
history, maturation, testing, instrumentation change, statistical regression, selection bias
|
|
|
pretest-posttest control group design
|
true-experimental
does control for possible impact of testing and retesting |
|
|
posttest only control group design
|
pre-testing not possible in some experiments
|
|
|
solomon 4 group design
|
assesses amount of pretest-posttest change while checking for testing effects
|
|
|
randomization or random assignment
|
improves likelihood that the control group represents what the experimental group would look like had it not been exposed to the experimental stimulus
|
|
|
matching
|
procedure whereby pairs of subjects are matched on the basis of their similarities on one or more variables, and one member of the pair is randomly assigned to the experimental group and the other to the control group
|
|
|
quasi-experimental designs
|
nonequivalent comparison groups design
time series design most used by social work |
|
|
3 additional threats to validity of experimental and quasi-experimental findings
|
measurement bias
research reactivity attrition (experimental mortality) |
|
|
way to avoid measurement bias
|
blind raters who are unaware of the hypotheses and whether or not a participant has received experimental intervention
|
|
|
research reactivity
|
refers to changes in outcome data that are caused by researchers or research procedures rather than the IV
|
|
|
attrition
|
occurs when participant drops out of an experiment before it is completed
|
|
|
strategies to minimize attrition
|
reimbursement
avoid intervention or research procedures that disappoint participants utilize tracking methods |
|
|
external validity
|
extent to which research results are generalizable to wider population
|
|
|
major factor that influences external validity
|
representativeness of the study sample, setting, and procedures
|
|
|
3 assumptions in qualitative research
|
focus is the unit under study and not a reduces sub-part
meanings matter important information can be found in the details people reveal about themselves when they tell their stories, and these stories are not incidental |
|
|
3 qualitative methods
|
interviewing
observation secondary documents, artifacts, etc. |
|
|
5 features of qualitative research
|
natural setting is the direct source of data and the researcher is the key instrument
it is descriptive - the words, pictures or behaviors are the data concerned with process, not just outcomes and products data are analyzed inductively meaning is essential |
|
|
limitations of qualitative research
|
labor intensive - uses more energy, time and resources
sample size tends to be small, limiting generalizability researcher is required to become such an expert, so immersed in data, that delegation to an assistant becomes difficult researcher selectivity concern over safety of researchers |
|
|
statistics
|
a tool to measure the extent to which theory and research correspond to each other
|
|
|
statistic
|
numerical characteristic of a sample
|
|
|
continuous variable
|
one that theoretically can have an infinite number of values between adjacent units on a scale
|
|
|
discrete variable
|
one in which there are no possible values between adjacent units on a scale
|
|
|
frequencies procedure
|
univariate analysis
must examine frequency distributions of variables of interest before any statistical analysis SPSS - analyze, descriptive statistics, frequencies |
|
|
central tendency measures
|
statistic that best represents a sample as a center
mean, median, mode |
|
|
mean
|
average
at least ordinal |
|
|
median
|
at least ordinal
|
|
|
mode
|
most frequent value
nominal |
|
|
measures of dispersion
|
the extent of difference in a sample
standard deviation |
|
|
standard deviation
|
typical distance from mean for at least ordinal variable
0 standard deviation = no variation among subject |
|
|
statistical significance
|
bivariate analysis
use p value |
|
|
p-value
|
the value of probability of an observed relationship being not worth interpreting because it was observed by chance or out of bad luck
|
|
|
cutoff value of p
|
Sig in SPSS
custom to use .05 aka significance level |
|
|
one tailed test
|
directional hypothesis
|
|
|
two tailed test
|
non-directional hypothesis
SPSS calculates for 2 tailed p value |
|
|
p value <.05
|
statistically significant
|
|
|
p value >.05
|
not statistically significant
|
|
|
difference of means test
aka T Test |
IV - nominal with 2 categories
DV - at least ordinal, but interval or ratio (education) |
|
|
SPSS for T Test
|
analyze
compare means Independent samples t test |
|
|
what do results of t test allow you to determine?
|
statistical significance of group diferences
significant if p value is <.05 |
|
|
One-way Analysis of Variance
aka ANOVA |
IV - nominal with 3 or more categories
DV - at least ordinal, but interval or ratio |
|
|
SPSS for ANOVA
|
analyze
compare means one way ANOVA |
|
|
what do results of ANOVA allow you to determine?
|
tells you which Mean Difference is significant
p value <.05, then not all categories are the same but you cannot tell which group differs from which |
|
|
bivariate correlations
aka correlations coefficient |
IV - at least ordinal
DV - at least ordinal Pearson correlation coefficient |
|
|
SPSS for correlations coefficient
|
analyze
correlate bivariate |
|
|
Chi square test of independence or cross tabulation analysis
|
IV - nominal
DV - nominal |
|
|
SPSS for chi square
|
analyze
descriptive statistics crosstabs IV = row DV = column |
|
|
what do results of chi square allow you to determine?
|
cannot directly test direction or strength of relationship
can only determine existence of relationship p value <.05 then a certain relationship exists between 2 variables |
