Flashcards
4. Experiments Versus Observational / Correlational Studies
Cards in this deck (17)
- 1Revise: Name and describe two types of observational research methods- Direct: Intervention vs. no intervention
Even direct observation usually involves much more than just “watching carefully” (and writing a report about it). Researchers usually create behavioral categories for observation (i.e. operationally defined behaviors of interest).
For agreement and objectivity purposes, multiple observers may be used.
1. Time sampling techniques
2. Event sampling techniques
- Indirect: Physical traces, archival records - 2Explain the purpose of an experimentAn experiment, however, investigates the effect of independent variable(s) on dependent variable(s).
- The IV is usually manipulated by the experimenter.
- The DV is assumed to be directly affected by changes in the IV.
- All other conditions remain constant, i.e. there is control of confounding (extraneous) variables
- Experimental research can be conducted either in the laboratory or in the field. - 3Compare and contrast experiments and observations
- 4What is a confounding variable and its consequences?A confounding variable is an “extra” variable that you didn’t account for. They can ruin an experiment and give you useless results, for example by suggesting that there is correlation when in fact there isn’t.
- 5Describe two types of confounding variablesThere are two types of possible confounding variables:
- Person-specific: e.g. age, education, socio-economic status, motivation, memory, intelligence
- Situation-specific: e.g. the experimenter, time point of testing, testing environment, apparatus, stimulus intensity, duration - 6Advantages of experimental research (as opposed to observational / correlational research)Isolates cause and effect
Control of extraneous variables high internal validity
Elimination of alternative explanations
Easy to replicate - 7Disadvantages of experimental research (as opposed to observational / correlational research)Participant bias low external validity
Artificial conditions and measures low ecological validity
Participants contribution completely prescribed
Kind of studied phenomena is limited - 8The purpose of a between-subjects design (experimental)Experiments with a between-subjects design compare at least two conditions A and B. In other words, there are at least two levels of the independent variable (IV).
- 9When to use a between-subjects design- Subjects who participate are placed into conditions A or B ideally at random, to control for extraneous variables like age, gender, income, educational background etc.
• If the subjects receive either level A or B but not both (different conditions = different groups of subjects), then it is a between-subjects design (independent measures).
- Sometimes a between-subjects design must be used, if the independent variable is:
• A quasi-experimental subject-variable (e.g. anxiety, gender)
• Manipulated in a certain way that precludes within-subject measures (participating in one condition makes it impossible or unreasonable for the same person to be in a second condition, e.g. problem-solving with and without a crucial piece of information) - 10When to use a within-subjects design- If each subject receives both levels of IV (A, B), i.e. both levels exist within the same subject, then it is a within-subjects design (repeated measures).
- 11Example of a between-subjects design study- Sigall and Ostrove (1975) conducted a between-subjects design experiment on the influence of physical attractiveness of a defendant on the recommended sentence.
Subjects were given a written description of a crime and asked to recommend a jail sentence.
IV1 = type of crime (2 levels, burglary in which a woman stole 2,200 pounds vs. a swindle in which a woman induced a man to invest 2,200 pounds
IV2 = Attractiveness of the woman (3 levels: very attractive vs. unattractive vs. no photo) - 12Results of the example study
- 13Advantages of a between-subjects design- The advantage of a between-subjects design is that each subject enters the study fresh and naïve with respect to the procedure / purpose of the study.
- 14Disadvantages of a between-subjects design- The disadvantages, however, are that there is a large number of individuals needed and that the differences between conditions might be due to accidental differences between subject groups.
- 15How to deal with the disadvantages of a between-subjects design- A countermeasure to this would be to create equivalent groups using randomization / random assignment, which is a method used for placing randomly selected subjects into the different groups.
• This means that there is equal probability for each subject to be assigned to a specific condition, which should spread possible individual difference factors evenly across conditions.
- However, with a small number of participants it could happen that random assignment places all A-subjects into one group, creating non-equivalent groups. In this case, there should be equal probability of assignment plus explicit control for relevant individual differences. This is referred to as ‘matching’ and requires pre-testing of participants. - 16Using a quasi-experiment to deal with the disadvantages of a between-subjects design- Comparisons may also be made between groups of people who differ from each other in ways not manipulated by the experimenter.
• Comparisons between non-manipulated (subject-) variables are referred to as a quasi-experimental design.
This refers to already existing characteristics of the participants in the study (e.g. gender, intelligence, age, anxiety). - 17—
Information
- Description
- Psychology 2A (Research Planning and Design) Flashcards on 4. Experiments Versus Observational / Correlational Studies, created by Nina Olsson on 24/07/2018.
- Created by
- Nina Olsson
- Views
- 0
- Rating