Task 7 Flashcards
What are the two major activities of scientific studies?
—Exploratory data collection and analysis
— Hypothesis testing
What do we know as the activity of “Exploratory data collection and analysis”
—Is aimed at classifying behaviour within a given area of research
—Identifying potentially important variables
—Identifying relationships between those variables and the behaviors
When is exploration typical?
In the early stages of research in an area
What is hypothesis testing?
Evaluating potential explanations for the observed relationships
Hypothesis testing: What do testable explanations allow you to predict?
What relationships should and shouldn’t be observed if the explanation is correct
When does hypothesis testing usually start?
After you have collected enough info about the Behaviour to begin developing supportable explanations
What are the two categories of relato ships you can find in Exploratiry data collection and analysis and Hypithesis testing?
—Causal relationship
—Correlational relationship
What is a causal relationship?
—When one variable directly or indirectly influences another
—when changes in the value of one variable directly or indirectly changes in the value of a second
What two types of causal relationships are there?
Unidirectional
Bidirectional
What is an unidirectional causal relationship?
When variable A influences variable B,but not the other way around.
What is a bidirectional causal relationship?
When each variable influences the other
What is a correlational relationship?
The changes in one variable accompany changes in another, but proper tests have not been conducted to show that either variable actually influences another.
What is the o my knowledge given by a correlational relationship?
That a relationship between variables exists
What is covariation?
Changes in one variables tend to be accompanied by specific changes in another(does not mean that either variable exerts influence on the other)
How does our ability to distinguish between causal and corellation varies?
With the degree of control you have over the variables under study
What are two broad types of research design?
Correlational and experimental
What is correlational research?
No -experimental research used to identify and characterize relationships
What is the purpose of correlational research?
To determine whether two(or more) variables covary, and if so, to establish the directions, magnitudes and forms of the observed relationships.
What are the steps of correlational research?
—1 developing measures of the variables of interest
—2 collect data
TO REMEMBER FROM CORRELATUONAL RESEARCH
No manipulations are made over the variables you simply observe them
How can you use correlational research?
To predict from the value of one variable, the probable value of the other variable.
What are the two variables in correlational research?
Predictor/explanatory variable
Criterion/response variable
What is a predictor explanatory variable?
Variable used to predict
What is the criterion/response variable?
Variable whose value is being appreciated
What are the two obstacles from drawing clear causal inferences in correlational research?
Third variable problem
Directionality problem
What is the third - variable problem?
The possibility that correlational relationships may result from the action of an unobserved “third variable”
How do we resolve third-variable problem?
Examine the effects of each potential third variable to determine whether it does , in fact , account for the observed relationship
What is the directionality problem?
Even when a direct causal relationship exists , the direction of causality is difficult to determine
What are three situations where correlational research makes sense?
—Gathering Data (early stages of research
—Inability ti manipulate variables
—Relating naturally occurring variables
What is experimental research?
Research that incorporates a high degree of control over the variables of the study.
What does the control we have over the variables of a study in experimental research permits us?
Establishing causality
What are two defining characteristics of experimental research?
—Manipulation of Independent variables
—Control over extraneous variables
What is an independent variable?
Variable whose values are chosen and set by the experimenter
What are treatments(levels)?
Specific conditions associated with each level of the independent variable
How do you manipulate your I.v?
Exposing your participants to at least two levels of the variable, hoping that changes in the level of the independent variable cause changes in the Behaviour being recorded(dependent variable)
What is a dependent variable?
Variable whose value you observe and measure in experimental designs
What is an experimental group?
The group receiving the treatment
What is control group?
The group not receiving the treatment
What does a control group provides to the experiment?
Provides baseline of Behaviour against which the Behaviour if the participants I. The experimental group is compared
What are extraneous variables?
Variables that may affect the Behaviour that you wish to investigate but are not of interest for the present experiment
What can uncontrolled variability may lead to?
—> Make it difficult/impossible to detect effects of the I.v
—> may produce differences in Behaviour across the levels of the independent variable
What are two ways to control extraneous variables?
—Hold extraneous variables constant
—Randomize their effects across treatments
How do you hold extraneous variables constant?
—When variables don’t vary over the course of experimental, they cannot cause uncontrolled variation in dependent variable
How do you
Randomize extraneous variables effects across treatments?
- Dealing with effects of extraneous variables that cannot be held constant or should not be held constant
- Distributing effects of these differences across treatments in such a way that they tend to even out and thus cannot be mistaken for effects of the independent variable
- use random assignment of subject to treatments (using table of random treatments)
- using inferential statistics to evaluate the probability with thigh chance alone could have produced observe difference
What is the strength of the experimental approach?
—Ita ability to identify and describe causal relationships
What are the limitations of an experimental approach?
— cannot use experimental method if you cannot manipulate hypothesized causal variables
—Tight control over extraneous variables in order to clearly reveal the effects of the independent variable( reduces external validity)
What is a demonstration?
Research design that resembles an experiment but lacks one of the crucial features of a true experiment.(I.v)
so it just exposes a group of subjects to the same only treatment condition
What is a confounding variable?
A variable that varies along with your I.v.
Why is a confounding. Variable bad for your experiment?
— it damages internal validity of the experiment
—diminishes ability to establish a causal relationship
What are some sources of confounding?
—> Failing ti randomly assign participants to experimental or control group
—>The experimenter bias (treat it with blind or double blind technique)
—> Treatment conditions are not carefully conceived and therefore unintended variables are introduced
What is a quasi-independent variable?
A correlational variable that resembles an independent variable in an experiment
How do you create a quasi independent variabke?
By assigning subjects to groups according to some characteristic they possess (age gender iq) rather than using random assignment
What are the advantages of including a quasi independent variable
- It allows you to test the generality if your findings across the levels of the quasi independent variable
- Reduce error variance by segregating data into into groups of participants who responded in a similar fashion to the manipulation (eff for of I.v is more clear)
The variance you cannot explain with your independent variable can be explained by quasi
What is error variance?
Variance in a set of scores that is due to extraneous variables
What are some disadvantages of using a quasi independent variable?
- Results are frequently misinterpreted
- Researchers often establish relationships between causal and dependent variables
- An extra effort is required to obtain subjects differing in the required characteristics
What are developmental designs?
Evaluating changes in Behaviour that relate to changes in a Persons chronological age ( a type of quasi experimental design wherein a characteristic of the participant (age) serves as a quasi-independent variable).
What are the two types of developmental designs?
- Cross-sectional designs
- Longitudinal designs
What is a cross sectional design?
Developmental design where you select several participants from a number of groups
This design is better when people are closer in age
Advantages of cross sectional?
Advantage: Permits you to obtain useful developmental data in a relatively short period of time
Limitations of cross-sectional design?
—Generation effects: Influence of generational differences in experience which become confounded its effects of age
E.g people who’s older isn’t bad at using phones because they’re old and lost facilities but because their generation. Lacks that experience
What is a longitudinal design?
Developmental design where a single group of participants is followed over some time period
Advantages of longitudinal design ?
Prevents generation effects
Allows you to witness the developmental changes clearly
What are disadvantages of longitudinal design?
-Cross-generational effects; conclusion drawn form longitudinal study of a particular generation may not apply to another generation
What are some disadvantages of using a quasi independent variable?
- Results are frequently misinterpreted
- Researchers often establish relationships between causal and dependent variables
- An extra effort is required to obtain subjects differing in the required characteristics
What are developmental designs?
Evaluating changes in Behaviour that relate to changes in a Persons chronological age ( a type of quasi experimental design wherein a characteristic of the participant (age) serves as a quasi-independent variable).
What are the two types of developmental designs?
- Cross-sectional designs
- Longitudinal designs
What is a cross sectional design?
Developmental design where you select several participants from a number of groups
This design is better when people are closer in age
Advantages of cross sectional?
Advantage: Permits you to obtain useful developmental data in a relatively short period of time
Limitations of cross-sectional design?
—Generation effects: Influence of generational differences in experience which become confounded its effects of age
E.g people who’s older isn’t bad at using phones because they’re old and lost facilities but because their generation. Lacks that experience
What is a longitudinal design?
Developmental design where a single group of participants is followed over some time period
Advantages of longitudinal design ?
Prevents generation effects
Allows you to witness the developmental changes clearly
What are disadvantages of longitudinal design?
-Cross-generational effects; conclusion drawn form longitudinal study of a particular generation may not apply to another generation
What is subject mortality?
Loss of subjects from the research diminishes external validity
What are multiple observation effects?
Making multiple observations of the same participant over time which poses a threat to internal validity
What are the two main effects of multiple observation effects?
Carryover effect: Improved performance on tests over time may be related participants increasing experience with taking the tests
History effect: ?
What is a solution for the carryover effect?
Using multiple forms of the test to evaluate Behaviour at different times or use different tests that measure Behaviour at fmdifferent times
