Research Methods Flashcards
Scientific method
A five-step process for empirical investigation of a hypothesis under conditions designed to control biases and subjective judgements.
How do psychologists develop new knowledge?
Psychologists, like researchers in all other sciences, use the scientific method to test their ideas empirically.
Empirical investigation
An approach to research that relies on sensory experience and observation as research data.
Theory
A testable explanation for a set of facts or observations. In science, a theory is not just a speculation or a guess.
Hypothesis
A statement predicting the outcome of a scientific study; a statement describing the relationship among variables in a study.
Operational definitions
Specific descriptions of concepts involving the conditions of a specific study. Operational definitions are stated in terms of how the concepts are to be measured or what operations are being employed to produce them.
Independent variable (IV)
A stimulus condition so named because the experimenter changes it independently of all the other carefully controlled experimental conditions.
Random presentation
A process by which chance alone determines the order in which the stimulus is presented.
Data
Pieces of information, especially information gathered by a researcher to be used in testing a hypothesis. (Singular: datum)
Dependent variable (DV)
The measured outcome of a study; the responses of the subjects in a study.
Replicate
In research, this refers to doing a study over to see whether the same results are obtained. As a control for bias, replication is often done by someone other than the researcher who performed the original study.
Step ① of scientific method
Developing a hypothesis
Step ② of scientific method
Performing a controlled test
Step ③ of scientific method
Gathering objective data
Step ④ of scientific method
Analyzing the results
Step ⑤ of scientific method
Publishing, criticizing, and replicating the results
Experiment
A kind of research in which the researcher controls all the conditions and directly manipulates the conditions, including the independent variable.
Confounding or extraneous variables
Variables that have an unwanted influence on the outcome of an experiment.
Controls
Constraints that the experimenter places on the experiment to ensure that each subject has the exact same conditions.
Random assignment
Each subject of the sample has an equal likelihood of being chosen for the experimental group of an experiment.
Ex post facto
Research in which we choose subjects based on a pre-existing condition
Correlational study
A type of research that is mainly statistical in nature. Correlational studies determine the relationship (or correlation) between two variables.
Survey
A quasi-experimental method in which questions are asked to subjects. When designing a survey, the researcher has to be careful that the questions are not skewed or biased towards a particular answer.
Naturalistic observation
A research method in which subjects are observed in their natural environment.
Longitudinal study
A type of study in which one group of subjects is followed and observed (or examined, surveyed, etc.) for an extended period of time (years).
Cross-sectional study
A study in which a representative cross section of the population is tested or surveyed at one specific time.
Cohort-sequential study
A research method in which a cross section of the population is chosen and then each cohort is followed for a short period of time.
Personal bias
The researcher allowing personal beliefs to affect the outcome of a study.
Expectancy bias
The researcher allowing his or her expectations to affect the outcome of a study.
Double-blind study
An experimental procedure in which both researchers and participants are uninformed about the nature of the independent variable being administered.
Institutional Review Board (IRB)
A committee at each institution where research is conducted to review every experiment for ethics and methodology.
Institutional Animal Care and Use Committee (IACUC)
A committee at each institution where research is conducted to review every experiment involving animals for ethics and methodology.
What are the APA’s guidelines on deception?
Under most circumstances, participation in research should be voluntary and informed.
What are the exceptions to the APA’s deception guidelines?
If deception is necessary for the purpose of the experiment, no substantial risks can be likely. The participants must be informed as soon as possible of the deception and must be debriefed to avoid any ill effects.
What are the APA’s guidelines on animal research?
Researchers must provide decent living conditions for animal subjects and weigh any discomfort caused them against the value of the information sought.
ABCs of laboratory animal research
Appropriate, beneficial, caring
How do we make sense of the data?
Researchers use statistics for two major purposes: (1) descriptively to characterize measurements made on groups or individuals and (2) inferentially to judge whether those measurements are the result of chance.
Frequency distribution
A summary chart, showing how frequently each of the various scores in a set of data occurs
Histogram
A bar graph depicting a frequency distribution. The height of the bars indicates the frequency of a group of scores.
Descriptive statistics
Statistical procedures used to describe characteristics and responses of groups of subjects.
Mean
The measure of central tendency most often used to describe a set of data- calculated by adding all the scores and dividing by the number of scores
Median
A measure of central tendency for a distribution, represented by the score that separates the upper half of the scores in a distribution from the lower half.
Mode
A measure of central tendency for a distribution, represented by the score that occurs more often than any other.
Range
The simplest measure of variability, represented by the difference between the highest and the lowest values in a frequency distribution
Standard deviation (SD)
A measure of variability that indicates the average difference between the scores and their mean.
Normal distribution
A bell-shaped curve, describing the spread of a characteristic throughout a population
Correlation
A relationship between variables, in which changes in one variable are reflected in changes in the other variable- as in the correlation between a child’s age and height
Correlation coefficient
A number between -1 and +1 expressing the degree of relationship between two variables
Inferential statistics
Statistical techniques (based on probability theory) used to assess whether the results of a study are reliable or whether they might simply be the result of chance. Inferential statistics are often used to determine whether two or more groups are essentially the same or different
Random sample
A sample group of subjects selected by chance (without biased selection techniques)
Representative sample
A sample obtained in such a way that it reflects the distribution of of important variables in the larger population in which the researchers are interested - variables such as age, income level, ethnicity, and geographic distribution
Significant difference
Psychologists accept a difference between the groups as “real”, or significant, when the probability that it might be due to an atypical sample drawn by chance is less than 5 in 100 (indicated by the notation p<.05)
Method which establishes cause and effect
Experiment
Why would someone do a case study instead of another method?
Reproducing the situation would be unethical
Strengths of experiments
Manipulation of variables to control outside influences; best method for identifying causal relationships
Weaknesses of experiments
Artificial; limited generalizability; manipulation of some variables is unethical, impractical
Strengths of questionnaires
Effective means of measuring actions, attitudes, opinions, preferences, and intentions of large numbers of people
Weaknesses of questionnaires
Lack of explanatory power; validity determined by sample; reliability difficult to determine; self-report may be inaccurate, biased
Strengths of interviews
Allows a wide range of responses; follow-up questions possible
Weaknesses of interviews
Does not enable researchers to draw conclusions about causal relationships; time-consuming
Strengths of naturalistic observation
Behavior is unaffected by manipulations
Weaknesses of naturalistic observation
Little opportunity to control variables; time-consuming
Strengths of case studies
Extensive evidence is gathered on single person
Weaknesses of case studies
Lack of generalizability; time-consuming
Archival research
Examines records to confirm correlational hypothesis
Repeated measures
Using same subjects in each condition of experiment
Strengths of repeated measures design
- Subject variables kept constant
- better statistical tests can be used
- fewer subjects required
Weaknesses of repeated measures design
Order effects
Demand characteristics
Different tests needed
Independent measures
Using different subjects in each condition of the experiment
Strengths of independent measures design
- Order effects do not influence second condition
- demand characteristics less of a problem
- same test can be used
Weaknesses of independent measures design
- subject variables differ
- worse statistical tests can be used
- more subjects required
Matched pairs
Using different but similar subjects in each condition of an experiment. And effort is made to match the subjects in each condition in any important characteristics that might affect performance
Strengths of matched pairs design
- subject variables kept more constant
- better statistical tests can be used
- order effects do not occur
- demand characteristics are less of a problem
- same test can be used
Weaknesses of matched pairs design
- subject variables can never be perfectly matched in every respect
- time consuming, difficult
- more subjects required
Sampling
Process of selecting subjects to study from the target population
- should be as representative as possible
- should be of a sufficient size to represent variety, but not uneconomically large
Strengths of random sampling
Provides the best chance of an unbiased representative sample
Weaknesses of random sampling
Difficult
Stratified sampling
Dividing target population into subcategories and selecting members of these categories in target proportions
Strengths of stratified sampling
Deliberate effort is made to identify the most important characteristics of a sample
Weaknesses of stratified sampling
Time-consuming
Opportunity sampling
Selecting available subjects
Strengths of opportunity sampling
Quick, convenient, economical
Weaknesses of opportunity sampling
Unrepresentative, researcher bias
Self-selecting sampling
Individuals who have consciously or unconsciously determined own involvement in study
Strengths of self-selecting sampling
Convenient, ethical
Weaknesses of self-selecting sampling
Unrepresentative, subject bias
What are the extraneous variables related to experimental subjects?
Individual differences
How do you control for individual differences?
- large, random sample
- random assignment
What are problems related to experimental method?
Artificiality
How do you control for artificiality?
- field study instead of laboratory
- increase number of definitions (broaden) operationalized variable
What are problems related to experimental design?
Order effects, demand characteristics, experimenter expectancy
How do you control for order effects?
- use independent measures design
- counterbalance (half perform A before B, half perform B before A)
How do you control for demand characteristics?
- use independent measures design
- use deception to hide research aim
- use single-blind method (they don’t know which condition they’re in)
How do you control for experimenter expectancy?
-double-blind method (neither subject nor researcher knows hypothesis/condition)
-inter-observer reliability measures
(Another observer simultaneously but separately rates same piece of behavior)
What are problems with experimental procedures?
Distraction and confusion
How do you control for distraction and confusion?
- clear, simple, standardized instructions
- subject should be asked for questions
General process of correlation all research vs experimental research
Correlational: researcher observes a previously existing situation; makes no changes
Experimental: researcher manipulates a situation in order to observe the outcome
Intended result of correlational research vs. experimental research
Correlational: identifies associations between factors
Experimental: learns how changes in one variable cause changes in another variable
What are the 6 key ethical issues?
- informed consent/debriefing
- right to withdraw
- deception
- protection from harm
- confidentiality
- privacy
How do you address informed consent and debriefing?
- participants formally agree to take part after being given comprehensive information about the nature and purpose of study & their role
- afterwards, the true nature is revealed & participant is reminded of rights
How do you address the right to withdraw?
Remind before, during, and after the study.
How do address deception ethically?
-justify the deception with an ethics review board
How do you address protection from harm?
-studies should be designed so that participants come to no more harm than they would in their day to day lives
How do you address confidentiality?
-researchers should use fake names or numbers instead of participant names
How do you address privacy?
-potential subjects’ privacy should be respected
When are informed consent/debriefing unnecessary?
During covert observation
Hindsight bias
Tendency upon hearing something to think one knew it all along
When is research valid?
When it measures what the researcher set out to measure; accurate
When is research reliable?
Can be replicated; consistent
Response/ subject bias
Tendency for subjects to behave in certain ways (picking left instead of right, etc)
Social desirability
Response bias; tendency to try to give answers that reflect well upon them
Hawthorne effect
Selecting a group of people on whom to experiment affects the performance of that group
Positively skewed distribution
Extreme score that is very high; more low than high scores; mean>median
Negatively skewed distribution
Extreme score that is very low; more high than low scores; mean<median
Z scores
Measure the distance of a score from the mean in units of standard deviation
What percent of scores in a normal distribution fall within one standard deviation of the mean?
68%
What percent of scores in a normal distribution fall within two standard deviations of the mean?
95%
What percent of scores in a normal distribution fall within three standard deviations of the mean?
99%
Percentile
The distance of a score from 0
-someone who scores in the 90th percentile has scored better than 90% of people
Sampling error
Extent to which a sample differs from the population
