UCSB Psych 10A Midterm 2

Between Subjects

Focuses on the differences between individuals on a given variable/process → participants are assigned to one treatment condition each

Within-Subjects

Focuses on differences between multiple measurements of a variable within a person → every person gets all of the conditions as the other participants and the measurements are repeated (sometimes called repeated measures design)

Mixed

• In a multifactorial design when 1 factor is between and 1 is a within subjects factor

Factors

variables that affect your DV or outcome variable

Independent variables

Quasi variables

Moderators

-Can be quasi variables or not 

Mediators

-Can be quasi variables or not

Predictor variables

Single Factor

Write out the words “single factor design”

Multifactorial

• Each factor is a number with a x to indicate the word “by”

• The number itself represents the number of levels or conditions on that particular factor

Moderator

• Sometimes experimenters think that the characteristics/ attitudes/predispositions that people bring into the lab may affect how they will react to the experimental manipulation

• Under what conditions is this IV to DV or predictor to outcome variable relationship true? 

• Moderators can be thought of as qualifiers for an effect 

Mediator

• Mediators is a way to see what variables explain the relationship between a factor and a DV or a predictor and a outcome variable

• They are the mechanism or in other words they explain how a factor like an IV effects/changes the DV

• How are variables are related?

Quasi-experimental

• Equivalent to experimental designs but you cannot assign participants to a variable that is of importance 

Within-subjects (repeated measures)

• Focuses on differences between multiple measurements of a variable within the person; every person gets all of the same measurements as the other participants

• Requires fewer participants because participants serve as their ow control

• Can see how participants change over time in response to various conditions

Used often in health studies to examine effects of different treatments or exposures to treatment on person’s functioning

Within-subjects design issues

• Carryover effects—response to one task influences next

• Order effect: what is presented 1^st can have influence on subsequent ratings

• Practice effects: Participant’s experience in one task makes it easier to perform a later task (even when the task is different)

Interference effects: performing one task disrupts performance on a 2^nd task

Counter balancing

varying the order in which different tasks are completed

External Validity

• Degree to which there can be reasonable confidence that results of a study would be obtained for other people and in other situations

Mundane Realism

• The extent to which an experiment physically resembles real life 

Psychological Realism

• The extent to which the psychological processes triggered in an experiment are similar to those that occur in everyday life

Criterion Validity

• Measure is correlated with a behavioral outcome

  • Known groups paradigm

    • Can be used to validate self report measures

Convergent Validity

Measure is correlated with similar constructs

Discriminant Validity

Measure is NOT correlated with dissimilar constructs

Reliability

Extent to which measures or observations that are made are consistently found, can be replicated

Internal Reliability

The extent that all the items in a multi-item measure behave in the same way

Need to establish reliability in 

Surveys 

Observations

Temporal Consistency

Does the item/scale correlate (positively) with itself over time?

Test-Retest

Estimate of the degree of fluctuation of the instrument from one administration to next

Inter rater/Inter observer consistency

Do your raters/observers scores match each others fairly well?

Estimate of the degree of fluctuation of the scores from one rater/observer to the other rater/observer

Replication

Ability to dependably demonstrate and repeat results (robust effects)

Convenience Sampling

Easy but greatly reduces external validity

Self selection

Easy but can be problematic because there are other variables (possibly other variables of interest) that systematically covary with the variables you are interested in

Random Sampling

Every member of the population has an equal chance of being selected for the sample

Cluster Sampling

Arbitrary groups are used to sample

Stratified Random Sampling

• Multistage technique where researchers select a of demographic categories (strata) and then the researcher randomly samples from those strata

Snowball Sampling

Used with rare cases and then have the sample recommend similar sample participants

Quota Sampling

• Target amount of each category

  • Sample non randomly until each category has the same amount

Trait Level Measures

capture a thing that remain relatively stable over time

State Dependent Measures

ideal for picking up changes that are faster and in relationship to the environment

Threats to Validity

-People are Different

-People Change

-Process of Studying People Changes People

-Experimental Choices Matter

Confounds

Another factor or variable accounts for your findings

Artifacts

Overlooked variables that can influence your study

Significance

expresses the likelihood that the observed effect would occur by chance alone

• Minimum level is p < .05

Effect Size

indicates strength/magnitude of the effect

Correlational

(r) strength of association between two variables

Experimental

(Cohen’s d) difference between means of experimental & control groups [e.g. degree of change in the dependent variable (DV) attributable to the independent variable (IV)]

Power

• Probability of rejecting the null hypothesis when it needs to be rejected (when it is false)

  • Power is determined by effect size and sample size

  • We try to have power be 0.8 (or above)

Power Analysis

• At outset of study researchers can determine sample size needed to potentially detect effect  by assuming a particular effect size and estimating the sample means and SD

Consent

• Contract between investigator and participant, usually written and signed

  • Participants are informed of what they are getting themselves into

Assent

Assent is obtained when person is not considered to be legally competent to give informed consent

Direct Replication

the original study is repeated as closely as possible to determine whether the original effect is found in the new data

Conceptual Replication

explore the same research question but use different procedures. The conceptual variables are the same but the variables are operationalized differently

Replication plus Extension

the original study is repeated as closely as possible but researchers add some variables to test additional questions

Meta Analyses

• take into account many studies and try to find the patterns in the results