Quiz 9 Flashcards
Non-experimental Research Designs
Research designs in which an experimenter simply either describes a group or examines relationships between existing groups. Describes the problem through observing changes to variables that occur without incorporating any manipulation on the part of the researcher. The focus is to describe what develops naturally.
Does not manipulate variables
-Does not seek to identify causal relationships
-Seeks to discover relationships
Typically involves one group
Sampling Methods
-Numerous – both probability and non-probability
Characteristics of non-experimental designs
- Typically involves one sample group
- Uses probability and non-probability sampling methods (DOES NOT use purposive and theoretical sampling methods)
- Do not manipulate variables.
Why choose a non-experimental research design
Non-experimental research design is often used:
-When it may be unethical or not feasible to conduct an experimental design.
- When the researcher is looking to study a rare outcome.
- When the research involves only one sample.
- When the researcher is looking to explore a topic before deciding whether or not to examine it further with an experimental design.
- When the research is looking to establish past relationships or associations between variables.
Developmental Designs
Study characteristics or variables as they develop or change over time
-Cross-sectional and Longitudinal
Developmental Designs : Cross sectional
Takes a snapshot of stages of development from different groups at the same time.
Researcher collects data one time from different groups to simulate development over time.
Allows for quick, inexpensive data collection.
Low internal validity due to possibility of confounding variables
-1 data collection point for respondent
-development is shown through the differences that exist between groups
-does NOT utilize a control or comparison group
ex: . For example if the researcher wants to look at maturation across a span of 4 years in high school the researcher will collect data from groups of freshman, sophomores, juniors, and seniors and analyze it together to see change over time
- confounding variables could be an issue
Developmental Designs : Cross sectional Example
Objective:To assess the impact of breast feeding on the risk of obesity and risk of being overweight in children at the time of entry to school.
Methods:Routine data were collected on the height and weight of 134,577 children participating in the obligatory health examination at the time of school entry. Mothers were surveyed on breast feeding practices.
Main outcome measures:Being overweight was defined as having a body mass index above the 90th percentile and obesity was defined as body mass index above the 97th percentile of all enrolled children. Exclusive breast feeding was defined as the child being fed no food other than breast milk.
Results:The prevalence of obesity in children who had never been breast fed was 4.5% as compared with 2.8% in breastfed children.
Conclusions:In industrialized countries promoting prolonged breast feeding may help decrease the prevalence of obesity in childhood.
Developmental Designs: Longtidunal Studies
Follows a group (cohort) over a period of time to study development.
Allows for the researcher to set up multiple data collection points over the life of the study and look at multiple variables.
Often expensive and requires a team of researchers.
High rate of attrition (loss to follow up.
ex:In a longitudinal study the researcher would follow a group of incoming freshman for 4 years, and collect data once a year to look at the maturation of one group.
Observational Research Design
Records naturally occurring behavior to better understand what behavior is occurring
Quan Observational Research
Quantitative observational design differs from using observation to collect data in a qualitative study
-Operational Definition:
*provides strict guidelines as to what should be observed, counted, and evaluated during the study
Data Collection
-Prespecified focus to observations, underlying theoretical framework
-Operational define what is being observed in order to count or evaluate observation
-Collecting of data is done in small segments of time
-Codes are predetermined backed on theory
-Rating scale is used to evaluate the observation
-More than one independent raters
-Involves in-depth training of team and raters to ensure consistency
Observational Design: Code in Qualitative research
Codes are determined after the data collection occurs. Here the word code is defined as the interpretation of a meaning unit and is associated with the data analysis process
Observational Design: Code in QUAN research
Codes are how the researcher quanitfies the observation (collects data). The individuals who collect data, often called raters, are made aware of what type of data they will be collecting before the study even begins. The raters collect data using rating scale that is made up of these predetermined codes
Cohort Research Design
Used to determine if an exposure is linked to the development of a disease or outcome when the relationship between the two has not yet been determined
Cohort Research Design: Prospective
Looks forward to see if an outcome develops from already known exposure Can follow a Single cohort – exposure Two cohorts – exposure/no exposure Can take long to complete
Study begins with the identification of a population and exposure status (exposed/not exposed groups)
Population is followed over a period of time for the development of disease
Cohort Research Design: Retrospective
Looks back into existing data via medical records or subject recall to identify if exposures could be linked to an outcome or disease
Outcome could or could not be present at the start of the study
Quick and inexpensive
Previously collected data is reviewed to identify the population and the exposure status (exposed/not exposed groups)
Determines at present the (development) status of disease
What is the difference between prospective cohort and developmental (longitudinal) studies?
Developmental (longtidunal):
Follows a group over time to study developmental issues (e.g. quality of life).
Prospective (Cohort)
Follows a cohort to determine whether exposure to a risk factor leads to the development of an outcome.
*While cohort studies are longitudinal, not all longitudinal studies would be classified as cohort.
Example of Cohort Study
A cohort study was designed to assess the impact of sun exposure on skin damage on beach volleyball players. At the end of a weekend tournament, players who self identified as wearing waterproof, SPF 35 sunscreen were compared with players who indicated that they did not wear any sunscreen. Players’ skin from both groups was analyzed for texture, sun damage, and burns. Comparisons of skin damage were then made based on the use of sunscreen. The analysis showed a significant difference between the cohorts in terms of the skin damage.
*Framingham Heart Study 1948
Cohort study Advantages
Subjects in cohorts can be matched, which limits the influence of confounding variables
Standardization of criteria/outcome is possible
Cohort Study disadvantages
Cohorts can be difficult to identify due to confounding variables
No randomization, which means that imbalances in subject characteristics could exist
Blinding/masking is difficult
Attrition (loss to follow up)
recall bias
unrelated data
confounding and extraneous variables
Case-Control Research Design
Begins after the development of the outcome and looks back in time to identify exposure (risk factor)
- researcher knows the outcome (disease) and looks to identify the exposure (risk factor)
- The researcher looks to identify wan exposure (risk factor) that explains why this group (case) has the particular disease or condition compared to a similar group without the disease or condition (control)
Case control studies are observational because no intervention is attempted and no attempt is made to alter the course of the outcome
retrospective
Case-Control Studies Advantages
Good for studying rare conditions or diseases
Less time needed to conduct the study because the condition or disease has already occurred
Researcher can simultaneously look at multiple risk factors
Useful as initial studies to establish an association
Case-control studies disadvantages
Retrospective studies have more problems with data quality because they often rely on memory and people with a condition will be more motivated to recall risk factors (also called recall bias).
Case Control Example
A case-control study was conducted to investigate if exposure to zinc oxide is a more effective skin cancer prevention measure. The study involved comparing a group of former lifeguards that had developed cancer on their cheeks and noses (cases) to a group of lifeguards without this type of cancer (controls) and assess their prior exposure to zinc oxide or absorbent sunscreen lotions.
This study would be retrospective in that the former lifeguards would be asked to recall which type of sunscreen they used on their face and approximately how often. This could be either a matched or unmatched study, but efforts would need to be made to ensure that the former lifeguards are of the same average age and lifeguarded for a similar number of seasons and amount of time per season.
Cohort vs Case Control
Cohort studies
Begin with a group of people (a cohort) free of disease. The people in the cohort are grouped by whether or not they are exposed to a potential cause of disease. The whole cohort is followed over time to see if the development of new cases of the disease (or other outcome) differs between the groups with and without exposure.
Case-control studies
Begin with the selection of cases (people with a disease/outcome) and controls (people without the disease/outcome). The controls should represent people who would have been study cases if they had developed the disease (population at risk). The exposure status to a potential cause of disease is determined for both cases and controls. Then the occurrence of the possible cause of the disease could be calculated for both the cases and controls.
Cohort and Case-control data analysis
Relative Risk
The probability of an outcome of interest developing as a result of the exposure being followed.
Used when analyzing data in a cohort study.
Odds Ratio
“Represents the odds that an outcome will occur given a particular exposure, compared to the odds of an outcome occurring in the absence of the exposure” (Szumilas, 2010, p. 227).
Used when analyzing data in a case-control study.
Correlational Research Design
Attempts to determine if the characteristics of one or more variables are associated with the characteristics of another variable
- Can determine the strength and degree of association between variables.
- Allows the researcher to predict with some level of accuracy that if one variable increase the other will either increase or decrease.
- Used when experimental design is not ethical or feasible.
- Cannot determine a cause and effect relationship.
- Allows the researcher to study multiple variables at the same time.
Correlational
Examines the extent (strength and direction, degree of association) of relationship between characteristics or variables within a group or between two or more groups
Correlation exists if:
- One or more variables increase or decrease in relation (strength and direction)
- The values of those variables are distributed in a consistent manner
- Age is related to Reading level: typical as age increases so does reading level
- Discrete combination of variables combined can predict the phenomena
- Residential status, SAT scores, and Greek membership predict XX outcome
Correlational Design Example
The purpose was to describe the relationship between emotional intelligence, psychological empowerment, resilience, spiritual well-being, and academic success in undergraduate and graduate nursing students.
Sampling: The study was set in a private Catholic university, there were 124 participants (59% undergraduate and 41% graduate students).
Data collection methods: Spreitzer Psychological Empowerment Scale, the Wagnild and Young Resilience Scale, and the Spiritual Well-Being Scale and the Mayer–Salovey–Caruso Emotional Intelligence Test
Results:
Academic success was correlated with overall spiritual well-being, empowerment and resilience.
Academic success was not correlated with overall emotional intelligence but when undergraduate and graduate students were considered separately
Graduate students had a significant relationship between total emotional intelligence
Data Analysis in Correlational Research
Pearson r (linear or correlational coefficient )
Correlation coefficients can range from -1.00 to +1.00
Value of -1.00 represents a perfect negative correlation
Value of +1.00 represents a perfect positive correlation
Value of 0.00 represents a lack of correlation
Caution about correlational research
Interpret results with caution
For example:
Strong and positive correlation (r = .90) between ice cream sales and gun violence
Can I determine that ice cream sales is correlated with gun violence?
Can I determine that ice cream causes gun violence?
Strong and negative correlation between (r = -.90) between ice cream sales and number of children playing in the park
Another variable responsible for relationship
Strong and positive correlation (r = .90) between elephant population in Thailand and size of the Florida orange crop
Any two things that increase yearly are correlated but only faulty logic sees a relationship between two unrelated events
When interpreting results remember that a correlation is strong if it is close to 1 or -1 – and weak if it is close to zero.
But a strong correlation can have no meaning if there is no relationship between the variables.
Correlational vs. experimental
Correlational:
Correlational research usually does not influence any variables
Measure and look for relations (correlations) between some set of variables
Data analysis looks at the strength and direction of the relationship
Cannot prove causality
Experimental:
Experimental research manipulates variables
Measure the effects of this manipulation on other variables
Data analysis also calculates “correlations” between variables, specifically, those manipulated and those affected by the manipulation
Has the power to prove causality
Do not get confused by data analysis techniques and research design
Methods used in non-experimental deisgn
Sampling: Probability and nonprobability
Data collection
Observation
*Pre-determined
*pre-specified
Survey
*Self-reported data
Archival records
*Inexpensive
*May not address what researcher is looking to
find out
Threats to validity in non-experimental research
External(results are generalizable to other groups or a larger population):
Real life setting
Doesn’t allow the researcher to control for confounding variables
Representative sample
Should be as close to population as possible
Replicability
May be hard due to the use of a natural setting
Internal (results are true because the study worked and not due to a confounding variable or bias):
Self-selection
The shared commonality of group
Bias
Assignment – non-random groups
Response – attempt to have more favorable responses
Recall – more accurately remember certain events
Researcher – personal beliefs
History and maturation