1. Both variables must be quantative

2.Correlation coefficient cannot be affected by the units of measurement

3. only measure linear relationship between variables

4. Correlation does not imply causeation

5.The correlation is strongly affected by a few outlying observations.

1. Question being considered

2. Resources - Skills +Training,lab space, money, time, participants

3. Ethical considerations

4. Converging Operation approach is likely to be best (best to use more than one method)

An active attempt to undo any changes that might have occured. Often impossible to do entirely.

ex: crying baby in locked car.

Should not be excessive

Should not be used to coerce participant in risky/uncomfortable procedure

for students, alternative to research participation be equally palatable

belmont report

Conceptual variables: the ideas that form the basis of a research hypothesis

Measured variables: Consist of numbers that represent conceptional variables

Ex:

Refers to a precise statement of how a conceptual variable is turned into a measured variable

Ex: Socio-economic status is the average of standardized scores on: parental income, education of mother, and education of father.

The use of different operations of the same conceptual variable allowing the research to triangulate on conceptual variable of interest

ex: measuring job performance w/ self-reating , supervisor

Data classified into categories

ex:gender, ethnicty, fav. color, sexual orientation

uses numbers to indicate the extect to which a preson possesses a characteristic

ex:How many cups of coffee?

How much anxiety do you feel?

Income?

Equal distance between scores on a measure are known to correspond to equal changes in the conceptual variable

Most measures of psychological contructs are not this

ex: fehrenheit temperature scale

Interval scales that also have a true zero point, this allows us to multiply and divide scale values.

ex: calvin temperature scale

Numbers indicate whether there is more or less of the conceptual variable, but do not indicate the exact interval between the individuals on the conspetual variable

very common with conceptual constructs

individuals are asked to respond to questions posed by an interviewer or questionaire

very common and problematic

a measure of personality

ex: roshach ink blots

1. protecting participants from physical and psychological harm

2. Providing freedom of choice about participating in the research

3. Maintaining awareness of the power differentials

4. Honestly describing the nature and use of the research

1. Provides her or his demographic information

2. Is given informed consent form explaining

• the procedure of the research
• who is conducting it
• how the results will be used
• what is going to happen during the research

3.Is informed of his or her rights, including the freedom to leave the project at any moment

4.Is geven the oppertunity to ask questions

5. Signs the form indicating that he or she has read and understood the information

Occurs whenever research participants are not completly and fully  informed about he nature of the research project before participating

contaminates participants against future studies

Only use when absolutly neccasary

occurs immediatly after research

designed to explain the purposes and procedures of research

indentify and resolve any unanticipated negative consequences

after which participants have the right to withdraw

Scoring: Nomothetic approach: stories are matched to existing data

Idiographic apprpoach: amkes sense of the sotry w/ respect to the subjects life

Subjects are asked to respond to a series of words

useful for studying prejudice

The topic being evaluated is stated once at the top of the page

items consist of pairs of adjectives located at the two endpoints of a standard response format

Tends to evaluate topic on:

Evaluation(good vs bad)

Potency(strong vs weak)

Activity(active vs passive)

involves the creation of differences in the items themselves

items are arranged in the cumlative order

changes in responding that occur when individuals know they are being measured

common types include:

Social Desirability

Self-Promotion

The natural tendency for research participants to present themselves in a positive or socially acceptable way to the researcher

ex: research in bars

Occurs when research participants respond in ways that they think will make them look good

because self report measures are prone to various distortions we like to rely on  behavioral measures

Behavioral Variables include:

• Frequency
• Intensity
• Speed
• Duration
• Latancy

also known as non-obtrusive studies

frequently used to assess attitudes unlikely to be directly expressed on self-report measures

Assess the physiological functioning of the bodys nervous and endocrine system

• Blood pressure
• ECG Data
• Pulse
• Skin Temp
• Pupil dialation
• Facial electromyography

Random error

Chance fluctuations in measured variables

Ex: Misreading or misunderstanding

Measurement of indiviuals on different places

Misprints

Mark answers incorrectly

occurs when the mearsure variable is influenced ny other conceptual variables that are not part of the conceptual variables of interest

ex:self-esteem,social desirability, mood, intelligence

• Test-retest reliablity
• Equivilent-forms reliability
• Internal constistincy
• Interrater reliability

Extent to which scores on similar but not the same indentical measures, administered @ two different times, correlate with each other

ex:SAT

Extent to which the scores on the items of a scale correlate with each other

if the scores do not correlate in a strong and positive way with each other than we say that a scale produces internally inconsistant scores

Split-half reliability: internal consitancy calculated by calculated by correlating a persons score on one hald of the items w/her or his score on the other half of the items

Cronbach's coefficient Alpha(a)

the most common and the best index of internal consistency

an estimate of the average correlation amount all the items on the scale

a=N*r

1+(N-1)*r

Statistic used as the measure of agreement among judges

only applicable when judges make categorial judgements

1. Summerize the ratings of the two judges in a contigency table
2. calculate how often the two judges agreed in their ratings
3. calculate how often the two judges would have agreed in their ratings if they had made their ratings completly randomly

K=Σfo-Σfe

    N-Σfe