click below
click below
Normal Size Small Size show me how
201 RMIP
Chapter 7
Term | Definition |
---|---|
Control | Any means used to rule out threats to the validity of research. Provides a standard of comparison and reduces variability. |
Control group | Subjects in a between-subjects design experiment who are like the experimental group in every aspect except that they do not receive treatment. Control groups are not necessary in every research. |
Experimental groups | Subjects in an experiment who receive treatment. |
Control condition | A condition in a within-subjects design experiment that does not contain the experimental manipulation |
Within-subjects experiment | research design in which each subject experiences every condition of the experiment. |
Between-subjects experiment | research design in which each subject experiences only one of the conditions in the experiment. |
Why is it important to reduce variability? | Limiting the things that change to those mandated by the experimental design (such as the independent variable) reduces the chances of confounding variables or measurement error and increases our confidence in the experimental results. |
When do you know that you have achieved experimental control? | When you have so limited the source of variability in an experiment that the behaviour becomes highly predictable. |
control experiment | allows one to conclude that a dependent ariable is assoicated with an independent variable and not with any other variable. |
experimental control | comes to the same conclusion as contorl experiment, except it so limits the number of variables operating in the situation and their range of values that the conclusion is clearer. |
What are 3 general strategies for achieving control in psychological research? | 1. using a laboratory setting 2.considering the research setting as a preparation 3. instrumenting the response |
What is the benefit of using a laboratory as a setting? | A scientific laboratory is a place set up to allow the most appropriate control over variables of interest in the aprticular research. Laboratory studies are more ideal if possible, otherwise a field study offers left control of variables. |
Explain the necessity of research setting as a preparation. | A preparation is a environment that is selected or constructed for a particular purpose. Everyhting that is part of the research setting is a part of the preparation, which is really a context for data collection. Crucial. |
Name 4 factors of preparation in relation to research setting as a preparation. | 1. experimental equipment 2. method of testing 3. location of testing 4. the subject used in the study |
Reaction time | The time it takes to respond to a certain stimulus used to study widely differing topics such as mental rotation, memory, and schizophrenia. Useful because of simplicity and reliability of the data it yields. |
Explain instrumentation of the response as control. | The precision with which you measure the dependent variable can influence your results. Extremely helpful to use measurement devices as instruments for reducing behavior to forms convenient for data analysis, such as numbers. |
Name 5 specific strategies for achieving control in psychological research. | 1. subjects as own control (within-subjects control) 2. random assignment (between-subject control) 3. matching (between-subjects control) 4. nuilding nuisance variables into the experiment 5. statistical control |
Explain subjects as own control (within-subjects control) (strategy for achieving control in psychological research). | Have each participant experience every condition of the experiment. This way, variation caused by differences between people is greatly reduced. |
Name 2 ways in which within-subjects control does not work. | 1.The participant has learned something by one method, it is impossible to re-learn it entirely with a new method. 2. Experiencing one condition may carry over and influence the response to another condition |
What 3 conditions should you consider before using within-subjects control? | 1. using subjects as their own controls is logically possible 2. participating in all conditions of the experiment will not destroy the naivety of the subject 3. serious contrast effects between conditions will not be present |
Random assignment | Unbiased assignment process that gives each subject an equal and independent chance of being placed in every condition |
Matching | control procedure to ensure that experimental and control groups are equated on one or more variables before the experiment. |
What are the 6 steps in conducting matched-groups experiment? | 1. administer pretest 2. rank subjects on pretest 3. form pairs on the basis of ranking 4. randomly assign members of pairs to groups 5. administer experimental treatments 6. examine differences between members of pairs |
What are the 3 requirements necessary to justify matching for an experiment? | 1. Strong suspicion there is an important variable on which the subjects differ that can be controlled 2. must believe a subtsantial correlation will be present between matching variable and dependent variable 3. it must be feasible to do a pretest. |
Nuisance variable | A condition in an experiment that cannot easily be removed and so is made an independent variable as a means of control |
What is th difference between nuisance variables and confouded variables? | Confounded variable varies with the independent variable. Nuisance variable is treated as a second independent variable that is varied seperately from the first one. |
Statistical control | Mathematical means of comparing subjects on paper when they cannot be equated as they exist in fact |
replication | repeating an experiment to see if the results will be the same |
systematic replication | Rsearcher B will do an experiment similar to Researcher A's but with different types of subjects, with different values of the stimulus, or with different ways of measuring theoretical concepts |
The elegant experiment | The simplest experiment that will make a clear and convincing test of a hypothesis |
Experiment in which different groups of subjects experience different conditions. | Between-subjects design |
Experiment in which subject experiences every condition | Within-subjects deisgn |
The group in a between-subjects experiment that receives the treatment | experimental group |
The group in a between-subjects experiment that does not receive the treatment | control group |
In within-subjects experiment, the condition that does not contain the experimental manipulation | control condition |
It is not necessary to have a control group or a control condition in an experiment as long as... | There is some group or condition that can serve as a comparison for a particular experimental manipulation |
Problems with the way that an experiment was carried out could result in... | The failure to confirm a hypothesis, but it does not necessarily mean that the hypothesis is incorrect. |
Except for the manipulation of the independent variable, all variables in the experiment should be... | Held constant across groups or conditions |
Experimental control | The ability to restrain or guide sources of variability in research |
What are the 3 main strategies for achieving control in research? | 1. using a laboratory setting 2. considering the research setting as a preparation 3. instrumenting the response |
Laboratory research is defined by... | The ability to control the important sources of variability in the research setting. |
The concept of a preparation enphasizes what? | Choosing the best possible research situation in which to test a hypothesis |
Instrumentation of the response refers to what? | The means of measuring the dependant variables. |
What are the 4 specific control strategies? | 2. Using subjects as their own controls 2. randomizing 3. matching 4. building nuisance variables into the experiment, 5. using statistical control |
Subjects can be used as their own controls in an experiment as long as ... (3) | 1. doing so is logically possible 2. when serving in all conditions will not destroy their naivete 3. when there will not be serious contrast effects between conditions |
When each subject has an equal chance of being assigned to every condition... | The allocation of subjects to conditions is RANDOM. |
When can matching be used (2)? | 1. When an important variable on which subjects differ is correlated with the dependent variable 2. Where it is feasible to present a pretest to the subjects |
What happens when the nuisance variables cannot easily be removed from the experiment? | They can be controlled by making them independent variables in the experiment. |
Statistical control | Statistical control involves equating subjects on paper by means of the analysis of covariance. |
Direct replication | Repeateing essentially the same experiment. |
Systematic replication | Doing a different experiment in which certain results should be found if the original experiments were valid. |
What is the most important means of control? | Replication |
What are the 3 factors that dictate the choice of method? | 2. The exact hypothesis to be tested 2. the methhods that are standard in the particular field 3. practical considerations |
How do you choose the number of subjects in your experiment (2)? | 1. The number of subjects to be used depends on the size of the effect and 2. the anticipated variability of the data. |
The power of the experiment ____ with the square root of the number of subjects | increases proportionately |
What are 3 threats to internal validity in a between-subjects design? | 1. mortality 2. selection 3. experimenter bias |
What is the main threat to construct validity? | Loose connection between theory and method, usually stem from poor operational definitions |
What are 3 general strategies for achieving control in experimental research? | 1. internal validity vs external/construct validity(field vs lab) 2. research setting as preparation 3. instrumentation of the response as control |
What is the issue from instrumentation of the response as control, and how can it be solved? | Issue of reliability of measure apparatus. If possible, automate measurement. If limited to human observers: provide extensive training, two orr more independent observers, score blind. |
Is internal, external, and construct validity good or questionnable in field research? | Good external and construct valifity. Questionnable internal validity |
Is internal, external, and construct validity good or questionnable in laboratory settings? | Questionnable external and construct validity. Good internal validity. |