Home
Subjects
Create
Search
Log in
Sign up
Upgrade to remove ads
Only $2.99/month
Social Science
Psychology
Psychometrics
Research methods Test 2
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (103)
simple random sample
Every member of the population is given equal chance of being included in a sample
Research Randomizer, Star Trek, Random Integer Generator includes
Tools that allow researcher to generate a random numbers table based on needs
Random number tables are
Tables of numbers that are unrelated to each other
Before computerized tools for random samples researchers used
Published books with random number tables
The students are assigned numbers and the computer associates with
The number that goes with the student
Random samples are subject to
Error
sampling error
Error created by random sample
Researchers can evaluate the effects of sampling error by
Inferential statistics
Errors due to bias is not reduced by
Increasing sample size
Systematic sampling
nth individual is selected therefore the researcher can choose number 2 and select every two people on the list, bad if the population has been organized in a particular order
Systematic sampling should not be referred to
Random sampling
The technical term for discussing the magnitude of sampling error is
Precision
Ways to reduce sampling error
Increase sample size
Use stratification in conjunction with random sampling
Strata means
layers
stratify
Create layers in the random or systematic selection of the sample
Stratified samples first create
Homogeneous groups from the population then make a proportional but random selection
Stratified random sample steps
Divide population
Select from both groups
Stratification only works if
The segments of the population for a characteristic along with people are expected to differ in items described
Stratification goals is to
Not make comparisons
simple random sampling, systematic sampling, stratified random sampling, cluster sampling are methods of
probability sampling methods
Cluster sampling is another form of
probability sampling
Cluster sampling involves
researchers draw groups or clusters of participants instead of selecting individuals
Cluster sampling is used when
getting a list of all individuals that constitute a population is very difficult or impossible, but getting a complete list of a higher unit of analysis is not
Cluster samplings drawback
each cluster tends to be more homogeneous in a variety of ways than the population as a whole.
How could you increase precision with cluster sampling
researcher could stratify on geography and draw a random sample of clusters from each stratum
nonprobability sampling do not guarantee
that each person or element in the population has an equal chance of being selected
Purposive sampling
non probability method where researchers use their knowledge of the population to select individuals who they believe will be good sources of information
Purposive sampling is used more in
qualitative research
Strategies for for purposive sampling
maximum variation sampling
extreme or deviant case sampling
Purposive sampling is also called
judgmental sampling
maximum variation sampling involves
selecting a sample in which the widest range of variation on the dimensions of interest is represented
extreme or deviant case sampling looks at
how cases are deviant can help define the category boundaries and shed light on the conventional case within a group
Homogenous sampling is a form of
purposive sampling that takes the opposite approach to maximum variation. Sample people who are similar
theoretical sampling is based on
the judgement of the researchers and selects additional participants based on information needed to corroborate, extend, or revise the emerging theory
theoretical sampling is a ______ process
iterative
iterative process means
that the researcher s alternative between theory development and collection of more data
saturation means
researchers have have explored the categories many times and have ceased to find any new properties that fit into those categories
Snowball sampling
non probability sample that is used to locate another participants who are difficult to find. FInd one person and ask them to direct you to others.
Snowball sampling is used by both
qualitative and quantitative researchers
Snowball sampling is presumed to be
bias
Demographic information compared to Qualitative and Quantitative research with snowball sampling
Qualitative researchers should plan to collect this information that allows them to accurately write about the participants of the study
Quantitative use a thin description
sample of convenience
used when thin descriptions are encountered means that people were selected based on availability and willingness. Regarded as a flaw in sampling
Demographics represent
Age gender income race
Demographic information is how
Researchers analyze and discuss outcomes of the study
Participants drop out during midcourse is known as
Mortality
pilot studies
Studies designed to obtain preliminary information on how new treatments and measures work
Pilot studies sample sizes are
Small
Sample size is determined by
Identifying the minimum number of people need to represent that population well and produce useful results
Validity is
a concept that is used in relation to measures
Valid means
to the extent that it measures what it is designed to measure and accurately performs and functions what it is intended to
True or false there is no test that is perfectly valid
True
Why is perfect validity elusive
test only tap a small sample
some studies are difficult to measure
Quantitative researchers seek to reduce
elusive contructs to numerical scores
judgemental validity
consist of assessments based on professional knowledge.
Two forms of judgmental validity
content validity
face validity
content validity is
an assessment of a measure based on the appropriateness of its contents. Ex.Achievement test
Content validity can also be applied to evaluating type of measures such as
self concept
Face validity measures
whether a measure appears to be valid on the face of it. upon superficial inspection does it measure what it claims to measure
Low face validity is desirable when
researchers want to disguise the true purpose of the research from respondents by making it less sensitive
True or False: It is possible for a test to have high face validity and low content validity ?
True
Empirical Validity is also known as
Predictive validity or criterion-related validity
Empirical Validity is when
Researchers make planned comparisons to see if a measure yields scores that relate to the chosen criterion
validity coefficient is a
Correlation coefficient used to express validity
concurrent validity
Administer the test and collect data about the same time
The type of validity that relies on subjective judgments and empirical data is
Construct validity
Construct stands for
A collection of related behaviors that are associated in a meaningful way
Any one indicator can be associated with
Many constructs
Construct validity method offers only
Indirect evidence
Direct evidence on the validity is obtained by
Criterion related validity
Because construct validity studies are indirect researcher should be cautious about
Declaring a measure to be valid from one study
Historically construct validity has been most closely associated with
Personality scales
Reliability means
consistent results
A test with high reliability may have low
validity
When evaluating measures validity is more important than
RELIABILITY
How can researchers determine reliability
measure twice and than compare to see consistency
reliability coefficients range
0.00-1.00
Using correlation coefficients to describe reliability is know as
reliability coefficients
Interobserver or interrater reliability coefficents is known as
reliability coefficients used to describe the agreement between those rating the measurement.
interrater realiability
obtaining two measurements at the same time
test-retest reliability researchers measure
at two different points in time
test-retest reliability seeks to know
more about the reliability test, not the observers
practice effect
influence on performance as a result of practicing a task
parallel forms reliability
consistency between/among alternate versions of the same instrument
When the sets of scores are correlated the results indicate
parallel-forms reliability
Achievement test measures
knowledge and skills individuals have acquired
aptitude test is designed to
predict some specific type of achievement
Aptitude test that are developed by commercial test publishers validity coefficients are about
.20 to .60
Published aptitude test have a reliability around
.8 or higher
Intelligence test is designed to predict
intellectual ability in general
Intelligence test measure skills that have been
acquired in some specific cultural milieu
when researchers measure deep-seated personality traits such as attitudes, interests and dispositions they want participants
typical levels of performance
Reducing the influence of social desirability increases
validity of personal measures
Three basic approaches to reducing social desirability
personality is measured anonymously, unobtrusively (without awareness), projective techniques
projective techniques ask respondents to
interpret pictures, complete sentences, or provide word associations
projective techniques are rarely used in personality research because
time consuming, not exactly numerical results, validity is suspect
Instead of projective techniques what methods are used in personality research
objective type personality measures such as true and false, agree/disagree
Scales that have strongly agree to strongly disagree is known as
likert- type scales
Reverse scoring
The numerical scoring scale runs in the opposite direction; 5 points each are awarded for positively agreeing and negatively agreeing to likewise statements
Data traingulation is
the use of multiple sources or multiple methods for obtaining data on the research topic
methods triangulation
two qualitative methods were employed to collect data from one group of participants
Data triangulation includes
two or more types of participants in the data collection but uses the same type of method
methods triangulation uses
multiple methods to collect data from participants
researcher triangulation reduces
the possibility that the results of qualitative research represents only the views of one researcher. (Usually a team)
You might also like...
Research and Evaluation Terms
31 terms
Chapter 5 Measures & Sampling
57 terms
RESEARCH METHODS EXAM QUESTIONS, ANSWERS & MARKS
68 terms
RESEARCH METHODS EXAM QUESTIONS, ANSWERS & MARKS
68 terms
Other sets by this creator
Pediatrics Stuff
100 terms
Gero Exam 22
10 terms
Care 2 Exam 4
234 terms
Psychiatric Nursing Ch 22 - Schizophrenia
49 terms
Other Quizlet sets
Quiz review for exam 2
12 terms
9.3 Plant Growth
23 terms
Middle Age Adult
46 terms
ISA 235 Final Exam Ch2 & CE17
60 terms