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;
63 Cards in this Set
- Front
- Back
Developing a qualitative study design involves decisions in regard to what aspects of the study?
|
Intervention versus no intervention
Nature of any comparisons Methods of controlling extraneous variables Timing of data collection Research sites and settings Communication with subjects |
|
What are the Dimensions of Quantitative Research Design?
|
~Control over independent variable
~Type of group comparisons ~Timeframes ~Observance of independent and dependent variables ~Setting |
|
What are the 4 designs associated with Control over independent variable?
|
experimental
quasi-experimental preexperimental nonexperimental |
|
What are the 2 designs associated with the type of group comparisons?
|
between- subjects vs. within-subjects designs
|
|
What are the 2 designs associated with Timeframes?
|
Cross-sectional vs.
longitudinal designs |
|
What are the 2 designs associated with Observance of independent and dependent variables?
|
retrospective and prospective
|
|
What are the 2 designs associated with Setting?
|
Naturalistic setting, laboratory
|
|
What are the 3 Characteristics of a True Experiment?
|
Manipulation
Control Randomization (also called random assignment)— |
|
What is manipulation property?
|
Manipulation—researcher does something to some subjects (introduces an intervention or treatment. experimenters vary the indepenant variable and then observe the dependant variable.
|
|
What is control property?
|
Control—researcher introduces controls, including a control group
|
|
What is the Randomization (also called random assignment) property?
|
Researcher assigns subjects to groups at random.
Typical assignment is to an experimental group or a control group. May be done by computer or through a table of random numbers. |
|
What is a experimental group?
|
This is the group receiving the treatment of interest.
|
|
What is a control group?
|
This refers ti a group of participants whose performance on a dependant variable is used to evaluate the performance of the experimental group.
|
|
What is a table of random numbers?
|
A table displaying hundreds of digits arranged in a random order.
|
|
Experimental Designs include:
|
~After-only (posttest-only) design
~Before-after (pretest posttest) design ~Factorial design ~Crossover (repeated measures) design |
|
Counterfactual is?
|
the cotrol group condition that is used as a basis of comparison.
|
|
What are the possibilities for the Control Condition or Counterfactual?
|
~No intervention
~An alternative intervention ~A placebo or pseudo-intervention ~Standard methods of care ~Different doses or intensities of treatment ~Delayed treatment |
|
What type of experiments lack either randomization or control group, but introduce other controls?
|
Quasi-Experiments
|
|
Types of quasi-experimental designs:
|
~Nonequivalent control group pretest-posttest design
~Time series designs |
|
Nonequivalent control group pretest-posttest design
|
Involves 2 or more groups of subjects observed before and afterthe implementation of an intervention.
|
|
How is the quasi-experimental designs different from the experimental research designs?
|
Subject are not randomly assignedto groups.
|
|
Time series designs
|
This design does not have a control group nor uses randominization. test.Involves collecting data over an extended eriod of time and introducing the treatment during that period.
|
|
What is a preexperimental design?
|
~Lack control group and/or randomization
~Lack controls of quasi-experiments |
|
Examples of preexperimental designs (2):
|
Nonequivalent control group, after-only design
One group before-after design |
|
Evaluation of quasi-experimental and pre-experimental designs (what are advantages and disadvantages)
|
May be easier, more practical than true experiments but it more difficult to infer causality
and usually there are several alternative rival explanations for results |
|
What is Nonexperimental research?
|
Take 2 groups and as the naturally occur and sopare their psychological and physical well being. This type of research involves observations rather than interventions.
|
|
What are the types of Nonexperimental research?
|
Correlational (ex post facto) research
Descriptive research |
|
Correlational (ex post facto) research
|
Research is conducted after variation in the independant variable has occured. Basic purpose is to study relationship amoung variables.
|
|
What are Correlational (ex post facto) research with
prospective designs? |
Starts with a presumed cause and then goes forward to the presumed effect.More costly but stronger.
|
|
What are Correlational (ex post facto) research with retrospective designs?
|
A phenomenaa is observed an in the present and is linked to phenomena occuring in the past.
|
|
_________ is often used to strengthen a retorspective design.
|
Case-control designs
|
|
What does a Case-control design involve?
|
comparing cases with a certian condition with controls who are selected to be familer to the cases with regard to key background factors that could be linked to the condition.
|
|
What is Descriptive research?
|
the purpose is to observe, describe, and document aspects of a situation. often referred to as Descriptive correlational study.
|
|
What does Descriptive correlational study mean?
|
that researchers were intrested in describing relationships among variables, without seeking to establish casual connections.
|
|
What are the 2 designs associated with Time deminsion?
|
Cross-sectional
Longitudinal |
|
What does Cross-sectional design mean?
|
Cross-sectional design—Data are collected at a single point in time
|
|
What does Longitudinal design mean?
|
Longitudinal design—Data are collected two or more times over an extended period
|
|
Retrospective studies are almost always _______.
|
cross sectional designs
|
|
what is the main advantage of a cross sectional design?
|
they are economical and easy to manage.
|
|
What are the 3 types of longitudinal studies?
|
Trend studies
Panel studies Follow-up studies |
|
Trend studies
|
Investigations in which samples from a population are studied over time with respect to some ohenomena, Different samples are selected from the same population at repeated intervals.
|
|
Panel studies
|
same people provide data at two or more points in time. Typically yeild more info. These are difficult and expensive.
|
|
What is sttrition?
|
loss of participants over time.
|
|
Follow-up studies
|
Are undertaken to determine the subsequent status of subjects with specified condition or those who recieve a specified intervention.
|
|
What are the basic two types of extrinsic varibles that need to be controlled?
|
external factors and intrinsic factors.
|
|
How are external factors controlled?
|
Control over environment(most likly achieved in lab), setting, time
|
|
How are intrinsic factors controlled?
|
Through Randomization to secure comparable groups.
Theugh homogeneity which is a restricting sample Through matching which involves using information about a subject characteristic to form comparison group. Through statistical control. |
|
What is analysis of covariance?
|
a detailed description of powerful statistical control mechinisms.
|
|
What are the Characteristics of Good Research Design in Quantitative Studies?
|
Internal validity
Statistical conclusion validity External validity Construct validity |
|
What is Statistical conclusion validity?
|
the ability to detect true relationships statistically
|
|
What is Internal validity?
|
the extent to which it can be inferred that the independent variable caused or influenced the dependent variable
|
|
What is External validity?
|
The generalizability of the findings to other samples or settings
|
|
What is Construct validity?
|
adequacy of measuring key constructs
|
|
What are the Threats to Statistical Conclusion Validity?
|
~Low statistical power
~Weak construction of independent variable and counterfactual ~Large differences between groups needed ~Unreliable implementation of a treatment ~Inadequate participation in treatment conditions |
|
What is statistical power?
|
Associated with Statistical Conclusion Validity. it is the ability of the design to detect true relationships among variables.
|
|
What are the Threats to Internal Validity?
|
~History threat
~Selection threat ~Maturation threat ~Mortality threat ~Often a result of differential attrition from groups |
|
What is the History threat?
|
Associated with Internal Validity. it is the occurance of events concurrent with the independant variable that can affect the dependat variable. Most likely effects one-group before- after designs and time series design.
|
|
What is the Selection threat?
|
Associated with Internal Validity. it encompasses biases resulting from preexisting differences between groups. when people are not assigned randomly the possibility always exist that groups being compared are not equivalent.
|
|
What is the Maturation threat?
|
Associated with Internal Validity. it arises from processes occuring as a aresult of time. One group before-after designs are espically vulnerable to this threat?
|
|
What is the Mortality threat?
|
Associated with Internal Validity. it stems from differential attrition of groups. Which means that subjets are lost during the study.
|
|
What are the Threats to External Validity?
|
Inadequate sampling
Novelty effect Expectancy effect (Hawthorne effect) Placebo effect Artificiality of research environment |
|
What is Inadequate sampling?
|
Associated with External Validity. the characteristics of the smple are not representative of the population.
|
|
What is the Novelty effect?
|
Associated with External Validity. This is when a treatment is new and subjects and researchers alter their behavior. they may be ethusiastic or skeptical about new methods of doing things.
|