Chapter 6
A study examining the relationship between humor and memory compares memory performance scores for -One group presented with humorous sentences -And a second group presented with non-humorous sentences. The participants in one group are primarily 8-year-old students Those in the second group are primarily 10-year-old students Age is potentially a ____
Confounding variable
Variable that provides an alternative explanation for the observed relationship E.g., When the observed relationship between the two variables has been artificially produced by the extraneous variable
Confounding variable E.g., If the pleasant and calming music room is painted green, the no-music room yellow, and the unpleasant and aggressive music room red, then the color of the room is a confounding variable
____ and ____ have exactly the same goal Both designed to demonstrate that a relationship exists between two variables , but both do not try to explain the relationship Reach the same conclusions Have the same limitations What's the difference?
Correlation Non-experimental Data used to accomplish the goal Correlational strategy 1 group of participants and measures 2 variables Non experimental 2 or more groups and measures 1 variable
If a correlational study produces numerical scores, data are usually evaluated by computing a _____ non-numerical scores, data are usually evaluated by computing a _____
Correlation (e.g., Pearson correlation) Chi-square test
The four remaining research strategies are intended to identify and describe relationships between variables What are they?
Correlational Experimental Quasi-experimental Non-experimental
Potential cues or features of a study that Suggest the purpose and hypothesis Influence participants to respond/ behave in a certain way
Demand characteristics
The correlational strategy online attempts to ____ the relationship, not ____ it
Describe Explain it E.g., Even though there may be a relationship between Facebook time and GPA, this does not mean that limiting students' time on Facebook would cause them to get better grades
Purpose: Produce a description of individual variables as they exist within a specific group. Data: A list of scores obtained by measuring each individual in the group being studied. Example: On average, students at the local college spend 12.5 hours studying outside of class each week and get 7.2 hours of sleep each night.
Descriptive
_____ studies are intended to summarize SINGLE variables for a SINGLE group of individuals
Descriptive
Which research strategies tend to have high EXTERNAL validity?
Descriptive Correlation Non-experimental
A general approach to research that involves measuring a variable or set of variables as they exist naturally to produce a description of individual variables as they exist within a specific group, but does not attempt to describe or explain relationships between variables
Descriptive research strategy
A good researcher is aware of these threats while planning a research study and incorporates elements into a research design that _____ or _____ threats to validity before research is conducted
Eliminate or minimize
In Ch 3, validity was introduced as it applies to measurement E.g., Whether the procedure actually measures the variable it claims to measure Here's validity is introduced as it applied to an _____
Entire research study Usually defined via external and internal validity
Confounding variables can be classified in 3 general categories that make it somewhat easier to monitor them and keep them out of a research study
Environmental variables E.g., size of room, time of day, gender of experimenter Participant variables E.g., height, weight, gender, age, IQ Time-related variables -Participant (E.g., mood, physical state) -Outside event (E.g., weather) -Accumulations (E.g., fatigue, practice)
Do not say you're doing an experiment unless you're using a ____ research design that controls for confounding variables
Experimental
Purpose: Produce a cause-and-effect explanation for the relationship between two variables. Data: Create two treatment conditions by changing the level of one variable. Then measure a second variable for the participants in each condition Example: Increasing the amount of exercise causes a decrease in cholesterol levels.
Experimental
When comparing two or more GROUPS of scores, what research strategies are used? One of the variables differentiates the groups The second variable measured obtains a score for each individual
Experimental Quasi-experimental Non-experimental High-income families vs. low-income families Examine students' grade average (construct: academic performance)
A research strategy that attempts to establish the existence of a cause-and-effect relationship between 2 variables by manipulating 1 variable while measuring the 2nd variable and controlling all other variables
Experimental research strategy E.g., Are increases in exercise responsible for causing decreases in cholesterol level? Two treatment conditions Low exercise High exercise Cholesterol is measured for each group Compare scores between low- and high-exercise groups
A journal article reports that a new teaching strategy is very effective for first-grade students A teacher wonders if the same strategy would be effective for a class of third-grade students What is the teacher questioning?
External validity of the report
Additional variables that exist in a research study but are not directly investigated are called ____, and every research study has thousands of them
Extraneous variables
Threats to external validity fit into 3 general categories
Generalizing across participants or subjects Generalizing across features of a study Generalizing across features of the measure
Experimental research studies tend to have very ____ internal validity, but often have relatively ____ external validity
High Low
With the correlational research strategy, data is usually presented ...
In a scatter plot Each individual is represented by a point Axes correspond to 2 variables E.g., Facebook time GPA
A researcher measures mood for a group of participants who have listened to happy music for 20 minutes and for a second group who have listened to sad music for 20 minutes If different mood scores are obtained for the two groups, the researcher would like to conclude that music influences mood However, the happy music group was tested in a room painted yellow and the sad music group was tested in a room painted dark brown and the researcher is concerned that the room color and not the music may influence mood scores What kind of validity is being questioned?
Internal
When both variables are measured using numbers or ranks, a variety of terms can be used to classify the relationships ____: A pattern in which the data points tend to cluster around a straight line ____: A pattern in which the data points tend to cluster around a curved line ____: Increases in 1 variable tend to be accompanied by increases in the other ____: Increases in 1 variable are accompanied by decreases in another
Linear relationship Curvilinear relationship Positive relationship Negative relationship
If a descriptive study produces Numerical data, ____ is computed Non-numerical data, ____ is computed
Mean/average score Proportion/percentage score
Generalizing across features of a study "to what extent can the results of the study be generalized to other procedures for conducting the study?" *if any of these occur, it leads to serious concerns regarding threats to EXTERNAL validity _____: Occurs when individuals participating in a research study (a novel situation) perceive and respond differently than they would in the normal real world _____: Fatigue, practice _____: Results of a study can be specific to an experimenter with a certain set of characteristics
Novelty effect Multiple treatment interference Experimenter characteristics
Participants may modify their natural behavior because they are participating in research Particularly a problem in a laboratory setting
Reactivity
How to implement the strategy General framework for conducting a study
Research design
Fine, detailed stage Exact, step-by-step description of a specific research study Includes precise determination of: -Exactly how the variables will be manipulated, regulated, and measured -Exactly how many individuals will be involved -Exactly how the individual participants or subjects will proceed through the course of the study
Research procedures
General approach to a research study, intended to answer a specific question What you hope to accomplish
Research strategy
Your statistical strategy should align with the ____ you're using
Research strategy
Generalizing across participants or subjects "to what extent can research results be generalized to individuals who differ from those who actually participated in the study?" *if any of these occur, it leads to serious concerns regarding threats to EXTERNAL validity _____: Sampling procedure favors the selection of some individuals over others ____: Volunteers are not perfectly representative of the general population ____: The results of a study may only be specific to participants with a certain set of characteristics (e.g., gender, age, race, ethnic identity, SES) ____: When research is conducted with nonhumans and presumed to be readily applicable to humans
Selection bias Volunteer bias Participant characteristic bias Cross-species generalization bias
Generalizing across features of the measures "to what extend can the results of the study be generalized to other ways of measuring the study?" *if any of these occur, it leads to serious concerns regarding threats to EXTERNAL validity _____: Occurs when the assessment procedure (pre-test) alters participants so that they react differently to treatment than they would in the real world when the treatment is used without assessment _____: Many variables can be defined and measured in different ways. The results of a study may be limited to that specific measurement _____: Effect of the treatment may decrease or increase with time
Sensitization Generality across response measures Time of measurement
____ evaluate mean differences between groups ____ compare differences in proportions between groups
T-tests and ANOVAs Chi-square tests
How can sensitization threaten external validity of the study?
The results may be limited to individuals who have experienced a pre-test
Any factor that limits the ability to generalized the results from a research study is a _____
Threat to external validity E.g., Results from a group of 50 year-old males does not necessarily generalize to other genders or to other age groups
A well-designed study produces results that accurately represent the ____ being examined and justify a conclusion that accurately answers the original ____
Variables Question
Research design requires decisions about 3 basic aspects
1) group vs. individual 2) same vs. different individuals 3) the number of variables to be included
What is a general plan for implementing a research strategy?
A research design
Any factor that allows an alternative explanation for the results
A threat to internal validity E.g., 3 weeks of therapy is followed by a decline in depression Suppose the weather was cold and miserable when the study began and changed to bright and sunny when the study ended 3 weeks later Weather provides an alternative explanation for the results
An external factor may distort measurements
Artifact
____ are a threat to BOTH internal and external validity
Artifacts
THIS WILL BE ON THE FINAL EXAM What are the 3 criteria for inferring causation?
Association (i.e., correlation) Temporal precedence (i.e., cause comes before effect) Control for alternative explanations
Correlation does not imply
Causation
Purpose: Produce a description of the relationship between two variables but do not attempt to explain the relationship. Data: Measure two variables (two scores) for each individual in the group being studied Example: There is a relationship between Facebook time and GPA for college students, but we don't know why.
Correlational
____ studies do not involve comparing groups of scores Instead, measures 2 variables for each individual in a SINGLE group Looks for patterns
Correlational
_____ research strategy: Observe 2 variables as they exist naturally for a set of individuals
Correlational
Cues given to participants about how they are expected to behave
Demand characteristics
Researchers often exaggerate the ____ between treatment conditions to increase chance of a significant result
Differences E.g., wouldn't compare 70 vs 72 degrees, would compare 70 vs 90 degrees
Which research strategy tends to have high INTERNAL validity?
Experimental
What are examples of artifacts?
Experimenter bias Demand characteristics Reactivity
What is the purpose of the experimental research strategy?
Explain the relationship by determining the underlying cause
Results from a research study suggest that a stop-smoking program is very successful However, the participants who volunteered for the study were all highly motivated to quite smoking and the researcher is concerned that the same results may not be obtained for smokers who are not as motivated What kind of validity is being questioned/
External
The value or quality of any research study is determined by the extent to which the study satisfies the criteria of _____ and _____
External and internal validity
Concerns the extent to which the results obtained in a research study hold true outside that specific study Can the results be generalized to other populations? Settings? Measurements?
External validity
The degree to which you research results generalize beyond the specific characteristics of your study
External validity
A variable that exists in a study but is not being directly examined?
Extraneous variable
What 3 kinds of generalization are there?
Generalization from a sample to the general population Generalization from one research study to another -Will another researcher get the same results? Generalization from a research study to real-world situation
In general there's a tradeoff between ____ and ____
In general there's a trade-off between internal and external validity Research that is very strong with respect to 1 kind of validity often tends to be weak with respect to the second type
The descriptive research strategy is not concerned with relationships between variables, but rather with the description of _____
Individual variables E.g., For students at a specific college, What is the typical number of text messages received each day? What is the average number of hours of sleep each day?
What aspect of a study is threatened if the participants are tested in one treatment condition at one time and then tested in a second treatment condition at a different time?
Internal validity
The extent to which a research study produces a single, unambiguous explanation for the relationship between two variables
Internal validity E.g., Changes in 1 variable are followed by changes in the other variable, and no other variable provides an alternative explanation for the results
A study must be tightly controlled so that no extraneous variables can influence the results However, a controlling study may create a research environment that is so artificial and unnatural that results obtained may not occur in real world Attempts to increase ____ can reduce ____
Internal validity External validity
A research study attempts to describe the relationship between self-esteem and birth order position by measuring self-esteem for each individual in a group of first-born boys, and then comparing the results with self-esteem scores for a group of later-born boys Which research strategy is being used?
Non-experimental
Purpose: Produce a description of the relationship between two variables but do not attempt to explain the relationship. Data: Measure scores for two different groups of participants or for one group at two different times Example: There is a relationship between gender and verbal ability. Girls tend to have higher verbal skills than boys, but we don't know why.
Non-experimental
Intended to demonstrate a relationship between variables, but it does not attempt to explain the relationship
Non-experimental research strategy
The ____ does NOT produce cause-and-effect explanations
Non-experimental research strategy E.g., Is there a relationship between verbal skills and gender? A study may demonstrate that girls have higher verbal skills than boys, but it does not explain why
Purpose: Attempt to produce a cause-and-effect explanation but fall short. Data: Measure before/after scores for one group that receives a treatment and for a different group that does not receive the treatment Example: The treatment may cause a reduction in smoking behavior, but the reduced smoking may be caused by something else.
Quasi-experimental
Which research strategy tends to lie somewhere in the middle in terms of EXTERNAL and INTERNAL validity?
Quasi-experimental
Uses some of the rigor and control that exist in experiments; however, ____ studies always contain a flaw that prevents the research from obtaining an absolute cause-and-effect answer ALMOST (but not quite) experiments
Quasi-experimental research strategy E.g., Using pre-existing groups rather than controlling the assignment of individuals to groups No way to know whether people in both groups are similar (e.g., age, income, motivation, etc.)
A general approach to research
Research strategy
What can minimize experimenter bias?
Single- or double-blind experiments
Experimental, quasi-experimental, and non-experimental studies all involve comparing GROUPS of scores E.g., mean differences, differences in proportions Thus, the use similar
Statistical techniques
Step ____: Select a research strategy
Step five
Selection of a research strategy is usually determined by
The kind of question that the research study hopes to answer
Any factor that generates doubt about the accuracy of the results or raises question about the interpretation
Threat to validity
How well the research study actually answers the Q it intended to answer
Validity