Nursing Research Research designs quantitative studies ch. 9
Quiz yourself by thinking what should be in
each of the black spaces below before clicking
on it to display the answer.
Help!
|
|
||||
|---|---|---|---|---|---|
| Research Design | overall plan for answering research questions or testing a hypothesis while maintaining control over extraneous variables in a study
🗑
|
||||
| Purpose of a Research Design | provides a blueprint for strategies to follow during a study; provides structure for analyzing and evaluating the data obtained
🗑
|
||||
| Where is the Research Design most commonly found in a report? | The Method Section
🗑
|
||||
| 3 methods of collecting studies | 1. self report
2. observational
3. physical measurement
🗑
|
||||
| Types of Quantitative Designs | 1. experimental
2. quasi-experimental
3. non-experimental
🗑
|
||||
| Characteristics of an Experimental Design (part 1) | -manipulation of independent variables
-random selection of subjects
-random assignment of subjects to a control group and a treatment group
-researcher is an active agent
-RCT (randomized controlled design)
🗑
|
||||
| Characteristics of an Experimental Design (part 2) | -cause must precede the effect
-you do something to one group but not to another (manipulating the independent var)
-IT IS THE MOST POWERFUL DESIGN B/C OF THE RANDOMNESS
-all procedures must go through experimental design 1st
🗑
|
||||
| goals of an experimental design study | to examine cause and effect of 1 treatment vs. another or no treatment in a setting where randomization is feasible
🗑
|
||||
| Which is the most powerful design for establishing a cause and effect? | Experimental Design
🗑
|
||||
| Manipulation | doing something to some of the subj. in a study (treatment grp) & withholding it from other subj in a study (control grp) or doing something to a group via a placebo
-acting on the IV then observing the effects on the DV
🗑
|
||||
| Independent Variable (IV) | the variable believed to be a cause of or to have an influence on the DV; manipulated or treatment variable in an experimental research
🗑
|
||||
| Dependent Variable (DV) | the variable believed to be an effect of the independent variable; outcome variable in experimental research
🗑
|
||||
| Control Group | group of subj. in a study who receive no treatment (IV) yet have their performance on the DV evaluated
🗑
|
||||
| Treatment group | group of subj. in a study who receive a treatment or have a condition manipulated (IV) and then have their performance on the DV evaluated for effectiveness of the treatment or manipulation
🗑
|
||||
| Random Selection | selection of subj. for a sample to be used in a study on a random basis
-each person has an equal chance or probability of being selected
-systematic bias regarding attributes not introduced;any differences noted inferred to be a result of the treatme
🗑
|
||||
| Random Assignment | assignment of subj to either a control group or a treatment group on a random basis
**Random assignment is involved in design**
🗑
|
||||
| which is the most trustworthy and accepted method of equalizing in an experiment? | Random Assignment; but there is no guarantee
🗑
|
||||
| Determining Randomization | -drawing from a hat
-flipping a coin
-using a computerized lottery
-using a table of random numbers
🗑
|
||||
| Types of Experimental Designs: Posttest design | observe DV only after treatment; between-subjects design
🗑
|
||||
| Types of Experimental Designs: Pretest-posttest design | observe DV before and after treatment; between subj design
🗑
|
||||
| Types of Experimental Designs: Factorial Design | observe main effects and interaction effects of IV factors on DV; between subj design
**uses more than one factor**
🗑
|
||||
| Types of Experimental Designs: Cross-over design | AKA repeated measures design
-observe DV after more then one treatment; within subjects design
🗑
|
||||
| Between-subjects design | a design in which separate groups are being compared (smokers & nonsmokers)
🗑
|
||||
| within-subjects design | a design in which one group is compared under diff. circumstances or points in time (before surgery/after surgery)
🗑
|
||||
| Limitations of Experimental Designs | -some variables not amenable to manipulation d/t nature of variables or for ethical reasons
-Hawthorne effect: being in a study may cause Ss to change their behavior, obscuring effect of variables
🗑
|
||||
| Limitations of Experimental Designs | **Ss and researcher could alter behavior, thus may need to conduct a double blind study (both Ss and researcher unaware of who is in treatment and control groups)
🗑
|
||||
| Characteristics of Quasi-experimental Design | -manipulation of IV
-no random selection of Ss
-no random assignment of Ss to a control or treatment group
-less powerful design for establishing cause and effect
-researcher is an active agent
🗑
|
||||
| Goals of a quasi-experimental design | to examine cause and effect relationships or to evaluate effectiveness of a treatment in a setting where randomization is not feasible
🗑
|
||||
| Types of Quasi-experimental designs: nonequivalent control group design | observe DV before and after treatment; between subjects design using treatment group and comparison group; no randomization
🗑
|
||||
| types of quasi-experimental design: time-series design | observe DV over an extended period of time during which treatment is administered; within subjects design; no control group or randomization
🗑
|
||||
| Characteristics of Non Experimental Design | -no manipulation of IV
-no random selection of Ss
-no random assignment of Ss to control or treatment group
-researcher is passive agent (observer)
🗑
|
||||
| Which is the least powerful design? | Non-experimental design
-it does not involve cause and effect, but rather identification of relationships or differences
🗑
|
||||
| What is the most common design in nursing studies? | Non-experimental design
🗑
|
||||
| Goals of a non-experimental design | to describe events, beliefs, attitudes, behaviors, processes, or characteristics or to examine relationships between 2 or more variables
🗑
|
||||
| Types of non-experimental designs: descriptive design | describe characteristics of ppl. or situations or prevalence and distribution of specific attitudes, beliefs, behaviors, and knowledge
🗑
|
||||
| Types of non-experimental designs: correlational design | explore relationship among two or more variables w/o treatment; examine changes or differences over time - may be a retrospective design, a prospective design, a cross-sectional design or a longitudinal design
🗑
|
||||
| Correlational Design | -does not establish cause and effect (smoking and lung cancer)
-establishes magnitude of correlation
-close to 1.00 (+ or -) = strong correlation
-close to 0.00 (+ or -) = weak correlation
+ = same direction
- = opposite direction
🗑
|
||||
| The following correlations were obtained in several studies. Which has the strongest correlation? a. +.85 b. -.26 c. +.34 d. -.97 | D, A, C, B
🗑
|
||||
| Retrospective Design | study begins with DV (effect) and looks backward for cause
-examine present state resulting from influence of past event (effect to cause)
-ex: neonatal sepsis based on mothers poor hygiene
🗑
|
||||
| Prospective Design | study beings with IV (cause) and looks forward for effect (DV)
-examine present event resulting in influencing future state (cause to effect) (ex: use of a high fat diet in Heart study resulting in heart disease)
🗑
|
||||
| Cross-sectional design | study involves collecting data at one point in time with multiple Ss
-examine differences across groups (ex: facial cleansing patterns in teenagers in high school)
**weaker than longitudinal
**almost always retrospective
🗑
|
||||
| Longitudinal Design | study involves collecting data from one group of subjects at multiple points in time
-examine changes over time
**pimarily prospective
🗑
|
||||
| Extraneous Variables | factors that may influence or confound study results
-external factors: related to research situation or environment
-intrinsic factors: related to research subjects
**need to control by holding conditions constant and uniform to limit effect
🗑
|
||||
| Control of External Factors | constancy of conditions: minimize potential contaminants during the collection of data; make environment or situation similar for Ss
-setting
-timing
-data collection
-instructions
-communication patterns (researchers may convey expectations to Ss
🗑
|
||||
| Control of Intrinsic Factors | -randomization (most effective)
-homogenity-- endure Ss are similar (ex: all men, all teenagers)
-matching: form comparison groups using Ss characteristics
-statistical control (ex: analysis of covariance, repeated measures)
🗑
|
||||
| research validity | evaluation of the merits of a study to promote correct inferences
🗑
|
||||
| research validity: internal validity | extent to which evidence supports treatment (IV) is causing or influencing effect (DV), rather than extraneous variables
🗑
|
||||
| research validity: external validity | extent to which findings are generalizable to other ppl & conditions (adequate sampling, replication of studies w/ diff Ss in diverse settings)
🗑
|
||||
| threats to internal validity part 1 | history: occurrence of events concurrent with IV that can affect DV
selection: biases from preexisting diff. btwn groups
maturation: developmental, biological, or psychosocial processes occurring as a result of time, not the IV
🗑
|
||||
| threats to internal validity part 2 | mortality: loss of SS during the study (attrition)
ex: impeachment, earthquake, race riot, CEU program, ad, bombing
🗑
|
Review the information in the table. When you are ready to quiz yourself you can hide individual columns or the entire table. Then you can click on the empty cells to reveal the answer. Try to recall what will be displayed before clicking the empty cell.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Created by:
lissy11
Popular Nursing sets