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;
176 Cards in this Set
- Front
- Back
Designs used to study the behavior change that an individual or group exhibits as a result of some intervention or treatment.
|
single-subject experimental designs
|
|
Multiple measures of pre-test performance conducted in single-subject research designs to control for threats to validity.
|
baseline measures
|
|
Designs in which the treatment is removed following baseline assessment.
|
withdrawal designs
|
|
Single subject additive design in which baseline phase is followed by treatment phase and ends in no treatment (some ethical objections to this design)
|
A-B-A design
|
|
single subject design that strengthens the research conclusions by demonstrating the effects of the treatment twice.
|
A-B-A-B design
|
|
Single subject design used when returning to baseline is difficult. Collects baseline data across-behaviors, across-subjects, or across-settings. Behaviors must be independent of one another.
|
multiple-baseline design
|
|
single subject design used with no baseline, no withdrawal, but potential problem with multiple-treatment interference.
|
alternating treatments design
|
|
Replication by the same investigator with the same or different subjects in a specific setting
|
direct replication
|
|
Replication that involves a number of subjects with the same problem, at the same location, at the same time
|
simultaneous replication
|
|
Replication that involves different investigators, behaviors, or settings.
|
systematic replication
|
|
The development and application of a treatment package, composed of two or more interventions that have been found to be effective individualy, designed for persons with complex behavior disorders.
|
clinical replication
|
|
Symbol meaning summation
|
Greek Sigma
|
|
The number of times each value of a variable occurs
|
frequency
|
|
Indices that represent a typical score among a group of scores
|
measures of central tendency
|
|
measure of central tendency to use for interval or ratio data
|
mean
|
|
measure of central tendency to use for ordinal data
|
median
|
|
measure of central tendency for nominal data
|
mode
|
|
The best index of typical performance when a group of test scores contains one or more extreme scores
|
median
|
|
Indices of how spread out a group of scores is
|
measures of variability
|
|
non-treatment phase of a single-subject experimental design is designated by this letter
|
A
|
|
treatment phase of a single-subject experimental design is designated by this letter
|
B
|
|
limitation of single-subject design
|
external validity or generalizability
|
|
repeating a research study is called this
|
replication
|
|
Measures of variability
|
range
quartile deviation standard deviation variance |
|
a limitation of using the mean
|
it is highly influenced by extreme scores
|
|
highest value - lowest value
|
range
|
|
half of the difference between the 75th percentile and the 25th percentile
|
quartile deviation
|
|
The measure that gives the average variation from the mean
|
variance
|
|
Most frequently used measure of data variability. It is the square root of the variance.
|
standard deviation
|
|
The square of the standard deviation
|
variance
|
|
Measure of variability appropriate for ordinal data
|
quartile deviation = (upper quartile-lower quartile)/2
|
|
Measure of variability appropriate for nominal data
|
range
|
|
Measure of variability appropriate for interval or ratio data.
|
standard deviation
|
|
relationship between the measures of central tendency for a normal distribution
|
mean=median=mode
|
|
Percentage of scores within one standard deviation of the mean
|
+ or - 34.13% or 68% of scores
|
|
Percentage of scores within two standard deviations of the mean
|
+ or - 47.75% or 95% of scores
|
|
Percentage of scores within three standard deviations of the mean
|
+ or - 49.86% or 99+% of scores
|
|
Distribution with more extreme scores at the lower end
|
negatively skewed distribution
|
|
Relationship between measures of central tendency in a negatively skewed distribution
|
mean<median<mode
|
|
Relationship between measures of central tendency in a positively skewed distribution
|
mean>median>mode
|
|
Three measures of relative position
|
Percentile Rank - percent of scores that fall at or below a score
z score - how far from the mean in s.d. units T score - modification of z score with mean 50 and s.d.= 10 |
|
expected, chance variation in variables that occurs when a sample is selected from a population (not the researcher's fault)
|
sampling error
|
|
the standard deviation of the sample means; indicates by how much one sample mean can be expected to differ from the means of other samples from the same population
|
standard error of the mean
|
|
The formal process of decision making in which researchers evaluate the results of a study against their original expectations.
|
hypothesis testing
|
|
The decision made when the differences found are not likely due to sampling error. The research hypothesis is suppported (not proven)
|
reject the null hypothesis
|
|
The decision made when the differences found are likely due to sampling error. The research hypothesis is not supported.
|
fail to reject the null hypothesis
|
|
statistical test to see if we can reject the null hypothesis
|
tests of significance
|
|
tests of significance are used to determine whether or not there is a significant difference between or among two or more what?
|
means
|
|
Greek letter used for the level of significance. This is the probability of a Type I error.
|
alpha, usually = .05
|
|
error made when you incorrectly reject the null hypothesis
|
Type I error.
|
|
error made when you incorrectly fail to reject a null hypothesis (you should have rejected, but did not)
|
Type II error
|
|
The Normal Curve
|
Mean=median=mode is in the center. Shows distribution of values plus and minus 3 to 4 standard deviations
|
|
more extreme scores occur at the lower end of the distribution.
|
negatively skewed
|
|
more extreme scores are the upper end of the distribution
|
positively skewed
|
|
the percentage of scores that fall at or below a given score
|
percentile rank
|
|
expresses directly how far a score is from the mean in terms of standard deviaion units. allows scores from different tests to be compared across individuals
|
z score
|
|
a standard score derived from a z score by multiplying the z score by ten and adding 50. This distribution has mean = 50 and s.d. 10
|
T score
|
|
Scores with a mean of zero and a s.d. of 1.
|
z score
|
|
Distribution of standard scores if the raw scores are normally distributed
|
normal distribution
|
|
measure of relationship for interval or ratio data. assumes a linear relationship
|
pearson r
|
|
measure of relationship for ranked or ordinal data where both variables are ranked.
|
Spearman Rho
|
|
scatter plot of the frequency distribution connected by lines
|
frequency polygon
|
|
picture showing the percentage of each category
|
pie chart
|
|
graphic display of data with parallel bars for each data group that show relative frequencies
|
bar graph/bar chart
|
|
significance test usually used. differences could occur in either a positive or negative direction
|
two-tailed tests
|
|
the number of observations that can vary around a parameter
|
degrees of freedom
|
|
type of test to use when the variables are normally distributed, the data is interval or ratio, participant selection is independent, and the variances of comparison groups are equal
|
parametric tests: t-test for independent or dependent samples, ANOVA (F-ratio), Pearson r
|
|
statistical test for ordinal or nominal data or for skewed distributions; needs a larger sample size.
|
non-parametric tests:
chi-square (nominal data); Spearmen rho (ordinal data) |
|
statistic to determine whether the means of TWO groups are significantly different at a given probability level
|
t-test
|
|
Smaller significance level increases the needed value, larger sample size (so larger d.f.) decreases the needed value
|
t-value
|
|
a parametric test of significance used to determine whether, at a selected probability level, the means of two independent samples are significantly different. One independent variable with 2 groups and One dependent variable.
|
t-test for independent samples
|
|
a parametric test of significance used to determine whether, at a selected probability level, the means of two matched samples are significantly different
|
t-test for non-independent samples
|
|
significance test for whether the means for one sample at two different times are significantly different
|
t-test for non-independent samples
|
|
parametric test of significance to determine if scores are significantly different at a probability level for multiple group comparisons. (no sub-groups). One independent variable with 3 or more levels and One dependent variable.
|
simple or one-way ANOVA
|
|
variance between groups/variance within groups
|
F-ratio
|
|
ANOVA statistic computed to determine whether variances among sample means are significantly different.
|
F-ratio
|
|
the reason for using multiple significance tests on the same data
|
to increase the likelihood of finding a significant difference
|
|
the use of multiple comparison increases the probability of this type of error
|
Type I error (incorrectly reject).
|
|
Factorial design for 2 or more independent variables with two or more levels each and 1 dependent variable
|
multi-factor ANOVA
|
|
test that adjusts post-test scores for initial differences on a variable. used for causal-comparative studies, or in experimental studies with random assignment to treatment groups
|
ANCOVA
|
|
the ability of a significance test to identify a true research finding, allowing the researcher to reject a null hypothesis that is false
|
Power
|
|
Increasing the power of a statistical test reduces this type of error
|
Type II error (incorrectly fail to reject)
|
|
a conservative multiple-comparison technique appropriate for making any and all pairwise comparisons involving a set of means
|
Scheffe' test
|
|
combines variables that are known to individually predict the criterion into a single prediction equation
|
multiple regression
|
|
a non-parametric test of significance for data in the form of frequency counts. good for nominal variables
|
Chi-Square
|
|
a category in which person or objects naturally falls (such as male or female)
|
true category
|
|
a category that is operationally defined by a researher (such as tall or short).
|
artificial category
|
|
analytical tool to identify and predict patterns in datasets collected from thousands of subjects and hundreds of variables
|
data mining
|
|
A statistical procedure used to identify relations among variables in a correlation matrix. this determines how variables group together based on what they may have in common
|
factor analysis
|
|
One independent variable with 2 or more levels, One dependent variable, One or more covariates
|
One-way ANCOVA
|
|
Two or more independent variables with 2 or more levels each, One dependent variable, One or more covariates
|
Factorial ANCOVA
|
|
One independent variable with 2 or more levels, Two or more dependent variables
|
One-way MANOVA
|
|
One independent variable with 2 or more levels, Two or more dependent variables, One or more covariates
|
One-way MANCOVA
|
|
Two or more independent variables with 2 or more levels, Two or more dependent variables.
|
Factorial MANOVA
|
|
Two or more independent variables with 2 more more levels, Two or more dependent variables, One or more covariates
|
Factorial MANCOVA
|
|
analyses that are used when you have more than one dependent variable
|
One-way MANOVA
One-way MANCOVA Factorial MANOVA Factorial MANCOVA |
|
analyses that are used when you have more than one independent variable
|
Factorial ANOVA
Factorial ANCOVA Factorial MANOVA Factorial MANCOVA |
|
analyses that are used when you have covariates
|
One-way ANCOVA
Factorial ANCOVA One-Way MANCOVA Factorial MANCOVA |
|
analyses that are used when you have one independent variable and one dependent variable
|
t-test (only 2 groups)
One-way ANOVA (2 or more groups) One-way ANCOVA (covariates) |
|
general term for data collection in qualitative research
|
fieldwork
|
|
the major data collection techniques for qualitative data collection. the reseracher participates in the situation while observing and collecting data
|
participant observation
|
|
the researcher observes and records behaviors but does not interact or participate in the life of the setting under study.
|
non-participant observation
|
|
qualitative research materials gathered, recorded, and compiled during the course of a study.
|
field notes
|
|
purposeful interaction in which one person obtains information from another
|
interview
|
|
questions prompted by the flow of conversation. used to find out where the participants are coming from and what they have experienced.
|
unstructured interview
|
|
when a researcher uses a specific set of questions to elicit the same information from all respondents. Includes both open-ended and closed questions.
|
structured interview
|
|
a written collection of self-report questions to be answered by a selected group of research participants.
|
questionnaire
|
|
method of qualitative data collection from many data sources that naturally occur in educational settings and require only that the researcher locate them
|
examining records
|
|
student records, standardized test scores, retention rates, minutes of meetings, newspaper clippings, etc.
|
archival documents
|
|
daily record for research participants to record their perceptions of what occurs in the setting
|
journals
|
|
diagrams of classes and schools that provide contextual insight and can be used to record traffic flow
|
maps
|
|
pictoral record in qualitative data collection that is time consuming to watch
|
videotape
|
|
recording in qualitative data collection that takes a large time committment to listen to
|
audiotape
|
|
various written or visual sources of data in qualitative data collection that contribute to our understanding of what is happening
|
artifacts
|
|
a presentation of work that captures a student's work samples over time
|
portfolio
|
|
an essential feature for describing the validity and reliability of qualitative research
|
trustworthiness
|
|
the use of multiple methods, data collection strategies, and data sources to get a more complete picture of what is being studied and to see if the data agrees
|
triangulation
|
|
the degree to which qualitative research data consistently measures whatever it measures
|
reliability
|
|
research study of how different humans experience the world around them in a written account
|
narrative research
|
|
data derived from multiple data sources for narrative research
|
empirical data
|
|
qualitative research materials gathered, recorded, and compiled during the course of a study. contain descriptive and reflective information. should be as extensive, clear and detailed as possible.
|
field notes
|
|
the process in which the researcher analyzes key elements in narrative research and then rewrites them in chronological sequence.
|
restorying
|
|
a participant creates a timeline divided into segments of significant events or memories in narrative research
|
oral history
|
|
prompts to elicit details about the phenomenon under investigation in narrative research
|
photographs, memory boxes, other artifacts
|
|
stories about experiences that provide insights into the subject and explanations of their actions in narrative research
|
storytelling
|
|
a written dialogue that serves as a working chronicle of the participant's thoughts on issues related to the research phenomenon in narrative research
|
letter writing
|
|
a life history that has the potential to broaden understandings of past events and experiences in narrative research
|
autobiograhical writing
|
|
writing the narrative together between participant and researcher
|
collaboration
|
|
the major problem with qualitative research
|
the time involved to collect data and the volumes of notes and data to be restoried
|
|
study of the cultural patterns and perspectives of participants in their natural setting
|
ethnographic research
|
|
a study of the shared patterns of a marginalized group with the aim of advocacy for that group
|
critical ethnography
|
|
an objective, scientifically written ethnography that uses common categories for cultural descriptions
|
realist ethnography
|
|
an analysis of one person, event, activity, or process set within a cultural perspective
|
ethnographic case study
|
|
How you know when to quit collecting data when doing ethnographic research
|
when you begin collecting redundant data
|
|
a study on a bounded system that can take an extensive period of time. research study in which the participants are chosen because the researcher chooses to study them.
|
case study research
|
|
good data that is enlightening
|
rich
|
|
case study research that includes many variables with a depth of information and an analysis of their interactions.
|
thick description
|
|
qualitative research undertaken about the same phenomenon at several sites. done to improve external validity (generalizability)
|
multiple case studies
|
|
data management tool used to assemble master charts with descriptive data from each site on one large "monster dog"
|
unordered meta-matrix
|
|
includes descriptive data for each site but orders the sites on the variable of interest to show the differences between high, med., and low sites.
|
site-ordered descriptive matrix
|
|
multiple case study cross-site analysis techniques
|
unordered meta-matrix
site-ordered meta-matrix |
|
Steps in analyzing qualitative research data
|
memo
describe classify |
|
type of research in which data collection and analysis continually interact
|
qualitative research
|
|
writing notes in the field note margins and underlining sections or issues that seem important during the initial reading of them
|
memoing
|
|
start to list major ideas that emerge in your literature review and in the data collection in qualitative research
|
identifying themes
|
|
categorically marking or referencing units of text with special labels
|
coding qualitative data
|
|
visual display of the major influences that affected qualitative research study to allow for the identification of consistencies and inconsistencies between groups
|
concept map
|
|
Can be an important item to assist with data analysis in qualitative research
|
computer software
|
|
questions to be answered when interpreting qualitative data
|
1-what is important in the data
2-why it is important 3-what can be learned from it 4-so what? |
|
research designs that combine quantitative and qualitative approaches in a single study
|
mixed methods research designs
|
|
exploratory mixed methods design that collects primarily qualitative data. the qualitative analysis identifies quantitative variables which are tested with quantitative techniques
|
QUAL-Quan model
|
|
explanatory mixed methods design that collects quantitative data first then collects qualitative data to help elaborate on the quantitative results
|
QUAN-Qual model
|
|
triangulation mixed methods design where the quantitative and qualitative data are equally weighted and are collected concurrently throughout the same study.
|
QUAN-QUAL model
|
|
parametric test to use if comparing attitudes through a Likert scale
|
t-test
|
|
symbol in research designs to indicate randomization
|
R
|
|
symbol in research designs to indicate that a treatment has already happened to a group before the study begins
|
( )
|
|
symbols to use for different treatments in research designs
|
X1, X2, X3, etc.
|
|
symbol used in research designs to indicate that a pre-test or post-test was given to participants
|
O
|
|
Five characteristics of action research
|
1-persuasive
2-relevant 3-accessible 4-a challenge to the intractability of reform 5-not a fad |
|
characteristic of action research - identifies data sources that provide insights and develop solutions to the researcher's own problems
|
persuasive and authoritative
|
|
A characteristic of action research; the reason it increases the predictability of what happens in the researcher's classrooms
|
relevent
|
|
action research characteristic - it is meaningful to the researcher because you have identified the area of focus
|
accessible
|
|
action research that is a challenge to the education system unwillingness to change
|
intractability of reform
|
|
action research characteristic that good teachers are always systematically looking at the effects of their teaching on student learning
|
not a fad
|
|
Levels of Action Research
|
1-single school or dept.
2- schoolwide - usually focused on one discipline 3- individual teacher |
|
action research process
|
1-identify area of focus
2-collect data 3-data analyis and interpretation 4-action planning |
|
a proposal for what steps to take to improve practice to resolve the problem the research was studying
|
action planning
|
|
When to use abbreviations
|
No contractions, and only very standard abbreviations, such as SAT, or abbreviations that the researcher has defined.
|
|
When to spell out a number
|
When less than ten or at the start of a sentence
|
|
research report page number location
|
top right-hand corner
|
|
research report treatment of first level headings
|
centered, mixed case, not underlined
|
|
research report body of text formatting
|
all double spaced
|
|
research report margins
|
all uniform, minimum one inch
|
|
research report formatting for all statistical values
|
all italicized
|
|
type of analysis in which every participant does not have the same potential to gain; less reliable than analysis of post-test scores alone
|
analysis of gain or difference scores
|
|
in case study research, the type of sample from which the researcher can learn a great deal about the research problem
|
information rich
|