Psych 225 Exam 2 Guide

(C4) Voluntary Participation

'In the initial dialogue between the scientist and the prospective participant, the scientist must ask the participant to be a part of the experiment.

(C7) Threats to internal validity

(e.g. history)

4. Behaviors

(e.g., condom use during last episode) and behavioral intentions)

(C14) Survey Administration Methods

(e.g., face-to-face, telephone...)

(C8) Control Techniques

(e.g., matching, counterbalancing)

7. Power

1-B therefore the chance of not making a type 2 error which is just as important as making a good conclusion! Strong power means it is unlikely you will accept a false null hypothesis.

(C8) True Experiment

1. Participants randomly assigned 2. At least two levels of independent variables 3. Controls for major threats for internal validity

(C3) Wallas' four stages of the scientific process

1. Preparation: becomes interested, researches, and looks at problem in various perspectives. Find alternative reasoning to problems. 2. Incubation: Closed meditating on a topic but not thinking about it. New Ideas are thought to come spontaneously. 3. Illumination: The idea/solution begins to take form in consciousness. A new answer/view. 4. Verification: Test hypothesis to see if it resembles the real world.

(C3) Hypothesis

A statement or expectation developed in relation to an explicit or implicit theory concerning potential outcomes of an experiment (that is, the relationship between the independent and dependent variable)

3. Effect size, Cohen's d

effect size was larger for meta-analysis than narrative review Cohen's d is an effect size used to indicate the standardized difference between two means. It can be used, for example, to accompany reporting of t-test and ANOVA results. It is also widely used in meta-analysis. Cohen's d is an appropriate effect size for the comparison between two means. In this study people who saw meta analysis saw cohen's d estimates and therefore demonstrated a standardized difference in contrast to the narrative review group in terms of ability to correctly estimate the magnitude.

7. Initial attitudes

initial attitude and the incentive for commitment were manipulated variables. If they ate a saltiene with hot sauce they were offered $20 to immediately partake in the without water for 24 hours study. Medium group ate saltine with peanut butter, low just a saltine. paid $5.

6. Salience (Bray & Sugarman only)

Completely separate article from Schmidt et al. (1986) but extremely similar design. Salience dictionary definition: The quality of being particularly noticeable or important. Salience in reference to Bray and Sugarman: the performance of interacting groups will be altered by highly evaluative audience to show high salience towards the observer by the group.

(C3) Construct, operational definition

Construct: A generalized concept, such as anxiety or gravity, that is constructed in a theoretical manner Operational Definition: The crucial terms in the hypothesis are defined clearly in reference to concrete operations

3. Self-efficacy, self-efficacy subscales

we examined the psychometric properties (internal consistency, convergent and discriminant validity, and social desirability bias) of a 22-item self-efficacy instrument that assessed three domains of protective sexual behaviors: refusing intercourse, questioning potential sexual partners, and using condoms

3. Crucial experiment

Green et al was a crucial experiment due to its nature of experimenting on the validity of the two theories that clearly disagree over the effect of the extremity of initial attitude on attitude change that occurs following discrepant behavior in the 'forced-compliance' situation. Dissonance/self-perception controversy.

1. Meta-analysis, narrative review

Half the pp were Meta-analysis trained and half were narrative review trained. Those who experienced meta-analytical training were better able to match the correct magnitude of the study with their estimate. Both groups however were influenced by salience manipulations.

1. Festinger: Cognitive dissonance

His analysis asserted that the subject in a dissonance-type experiment is simply an observer of his own behavior. Thus, the subject in such a situation should infer his attitudes and beliefs from his behavior whenever that behavior appears to be free from control of external reinforcement contingencies that would indicate extrinsic motives, for example, monetary rewards.

5. Social desirability, self-esteem, mastery, social anxiety, computer attitudes, conservatism

Social desirability refers to the tendency to respond to survey items in a fashion that makes one look good or present a favorable impression. This response bias is an important methodological concern for self-report studies."' in general, and especially for sexual behavior studies that use self-report Because so much attention has been directed toward AIDS and other STDs, study participants may want to answer the survey items in a way that portrays them as sexually responsible persons. Examination of the correlation between scores on the self-efficacy instrument with scores on the instrument assessing social desirability responses will determine whether or not this response bias exists.

(Lab) Quasi-experimental

Quasi-experiments are subject to concerns regarding internal validity, because the treatment and control groups may not be comparable at baseline. With random assignment, study participants have the same chance of being assigned to the intervention group or the comparison group.

(C8) Random sampling, random assignment

Random sampling: pick Y% of participants from X participant population Random Assignment: Assigning X participants to Y treatments

(C8) Type 1 and Type 2 errors

Refer to CH 7

(C3) Reliability and Validity

Reliability: The extent to which we are confident that scores would reoccur Data reflects the scores, not error As reliability increases, power increases Validity: The accuracy of our ideas and our research; the degree to which these are true and capable of support.

1. Replication

Replication is the most important and universally accepted criterion of genuine scientific knowledge. This article argues that social psychologists are scared of making type one errors (failing to accept the correct null hypothesis that there is no statistical difference between groups.) and therefore do not perform conceptual replications which can extend the generality of the tested relationship.

(C14) Response sets

Response sets is the human tendency to answer questions in ways that are the most complimentary, or flattering, to the respondent rather than telling the absolute truth.

(C14) Problems with, advice concerning, self-report items

Self-report items can allow participants to stretch the truth. Not having any proctor allows them to do this much better.

6. Criterion of significance

Social Psychologists need to have their p values below .05 in order to make conclusions, which blinds them to the fact that they should do a meta analysis instead of repeated studies.

1. Social facilitation & social impairment

Social facilitation: is the mere presence of another person that increases drive and thus influences behavior. - are produced by some form of evaluation apprehension and not simply by the mere presence of another person. Social impairment: is the mere presence of another person that decreases drive and this influences behavior explicitly negative.

3. Strong inference, crucial experiment

Strong inference: Believed that social facilitation is a thing despite actual research (Zajonc) Crucial experiment: Schmidt et al and other experiments were considered 'crucial' as they answered a theory that was based on a strong inference and not scientific experimentation.

8. Construct validity

Strongly supported the hypothesis derived from dissonance theory.

4. Subjective arousal

Subjective arousal was assessed via self report using an 11-point rating scale(0—un aroused,10—extremely sexually aroused). We designed this scale solely for the purpose of this study ;however ,this scale is similar to those used in other studies of sexual arousal

5. Cover story

Subjects were told that they would perform a short perceptual judgement task and that several time throughout the experiment they would be asked to indicate on various scales of how thirsty they felt. During a specified break, all of the experimental subjects were asked to volunteer for a future experiment which was 'examining the psychological consequences of being deprived of water for 24 hours.' Following the 'experiment' the "present" experiment was completed. The dependent measures were changes in subjective thirst ratings on two self-report scales and the actual amount of water consumption that occurred.

(C4) Box titled "informed consent may be hazardous to your health"

Summary: Informed consent is known as necessary, but it is actually more necessary for the protection of the researchers -- not the participants. Participants should know what will be happening to their body/minds but evidence suggests humans are so highly suggestible that outcomes can change their behavior. Leads to spectrum of behavioral changes -- even with placebo patients. Need to know that costs outweighs risks of informed consent.

(C14) Content Analysis

Survey that returns data in a quantitative form. The information must be coded to ensure reliability across subjects -- there must be a system to code open ended questions. Must be a systematic way to group data for future analysis.

(C7) Systematic & chance variation

Systematically, the factors varied (independent influenced dependent) The factors varied due to chance.

(C14) Reliability & validity (See also course pack, p. 60-62)

Text Book: Reliability is the extent to which an instrument produces the same results each time it is employed to measure a particular construct. Validity refers to how well a measure accurately reflects a concept or measure. Course Packet:

4. Zajonc: Innate drive, mere presence

Zajonc (1965) provided the most widely accepted explanation of these divergent effects with his claim that the 'mere presence' of others increases a person's generalized 'innate drive' and thus facilitates the tendency to emit his or her dominant response for that task.

(C14) Restricted range

a range of values that has been condensed, or shortened. For example, the entire range of G.P.A. scores is 0 to 4.0. A restricted range could be 3.0 to 4.0, or 2.0 to 3.0.

2. Bem: Self-perception

article that suggested an alternative to Festinger's Cognitive dissonance by doing an experiment on the salience of pre-manipulation attitudes, Bern and McConnell(1970) interpreted their data as supporting self-perception theory. They acknowledged, however, that their results were not inconsistent with a dissonance theory interpretation and concluded that it seems unlikely that a "crucial" experiment for discriminating between dissonance and self-perception theory will ever be executed since the two theories appear to make identical empirical predictions.

(Lab) Moderating Variables

commonly denoted as just M, is a third variable that affects the strength of the relationship between a dependent and independent variable In correlation, a moderator is a third variable that affects the correlation of two variables.

(Lab) Correlational design

correlational research design is a type of non-experimental study in which relationships are assessed without manipulating independent variables or randomly assigning participants to different conditions.

(C4) Informed Consent

Assuming the participant is freely able to participate in research, the scientist in the initial dialogue should inform the prospective participant about what will be required of him or her during the study.

(C3) Contrast, reciprocity, innate drive, learned drive

Contrast: Reciprocity: Innate drive: Zajonc: presence of members of the same species leads to an innate reflexive alertness of high arousal and generalized drive and leads to increased tendency to enact the dominant response If the task is simple, well learned, the dominant response is also correct (social facilitation) If the task is complex, novel, dominant response is often incorrect (social impairment) The mere presence of others is enough to facilitate this Learned drive: Cottrell: Specific to humans People learn that their actions have social consequences Presence of others leads to questions as to whether they can evaluate -No they can not evaluate leads to no change in arousal and same performance as when alone -Yes others can evaluate leads to social facilitation on well learned tasks

2. Convergent & discriminant (divergent) validity

Convergent: Convergent validity refers to the intercorrelation between constructs that are either related or are consistent with a specified In our present study, we assessed convergent validity by examining the intercorrelations among the subscales and by correlating self-efficacy subscale scores with scores on measures of sexual behavior (number of partners, condom use behavior, and pregnancy and STD history) and with psychological constructs related to a healthy lifestyle. Divergent/Discriminant: Discriminant validity refers to the ability of an instrument to distinguish between different constructs. 3s That is, scores on one instrument should be unrelated to scores obtained by measures of different or unrelated constructs. We determined discriminant validity by correlating scores on the self-efficacy instrument with scores on measures of liberalism-conservatism and attitudes toward computers, both of which are expected to be unrelated to self-efficacy for protective sexual behaviors.

(C4) deception and debriefing

Deception: Psychologists can not deceive the participants unless the deceptive technique is justified by the value of the study. Can not deceive if can cause mental/physical harm. If deceive, must tell before the conclusions are out. Debriefing: Psychologists provide a prompt opportunity for participants to obtain appropriate information about the nature, results, and conclusions -- so that there are no misconceptions. If no debriefing and it is justified, needs to have reduced harm.

Green (1974). Dissonance and self-perception analyses of "forced compliance": When two theories make competing predictions (1-9)

Dissonance theory and self-perception theory offer radically different explanations of the observed phenomena in the "forced-compliance" situation. The present study was designed to test the relative predictive merits of these two theories. Using a typical dissonance paradigm, the extremity of the initial attitude and justification for commitment to a discrepant act were manipulated. Results strongly supported the dissonance explanation that increasing the extremity of the initial attitude would enhance subsequent attitude change. Other dissonance predictions were supported as well, while the self-perception predictions received little support. The conclusion was reached that the dissonance analysis is more appropriate for explaining the effects of incentive and attitude-discrepancy manipulations in the forced-compliance paradigm. Also, another study was proposed to further test the relative merits of the competing predictions offered by the two theories.

Schmitt, Gilovich, Goore, and Joseph (1986). Mere presence and social facilitation: One more time and Bray and Sugarman (1980). Social facilitation among interacting groups: Evidence for evaluation apprehension hypothesis (1-7)

Does the presence of others help or hinder our performance? The answer, as almost 90 years of research has demonstrated, is that it depends on the nature of the task being performed. The presence of others appears to facilitate the performance of easy or well-learned tasks, but to hinder the performance of difficult or novel tasks. Zajonc (1965) provided the most widely accepted explanation of these divergent effects with his claim that the presence of others increases a person's generalized drive and thus facilitates the tendency to emit his or her dominant response for that task. For simple or well-learned tasks the dominant response is likely to be the correct response and performance is therefore facilitated; for difficult or novel tasks the dominant response is not likely to be correct and performance is therefore hampered.

2. Kinsey sexual attraction scale

Each participant provided his sexual identity (bisexual, homosexual, or heterosexual) and two ratings of his relative sexual attraction to women versus men (fantasy in the last year and since age 18)using the Kinsey scale (Kinsey et al.,1948) with responses ranging from 0(completely heterosexual)to 6 (completely homosexual).

(C4) Institutional review board

Ethical review board scientists can ask questions to about their study.

(C7) F, t, p values

F: effect size (large helps you reject the null) t: Significance p: Probability of X

5. Type I (α) & II (β) errors

Fisher believed the concepts of type 2 error and power were inappropriate for scientific inference because of his focus on assessing the confidence that his particular hypothesis was true. Therefore, he is too fixated on on proving his hypothesis true and fails to see how accepting his false null is worse than rejecting his correct hypothesis.

3. Physiological arousal, plethysmograph

Genital arousal data were continuously recorded using an MP100 data acquisition unit (BIOPAC Systems Inc. ,Goleta ,California) and AcKnowledge software,Version3.7.3(BIOPACSystemsInc., Goleta, California). Genital arousal was assessed with circumferential penile plethysmography using an indium/gallium strain gauge that measured changes in penile circumference, with increases in circumference indicating increased physiological arousal. The gauge was calibrated to a range of 30mm, and raw data were filtered to reduce noise in the signal.

4. Salience

Importance of article titles -- people remembered higher salience titles (did not help the narrative review people make estimates)

1. Reliability, Cronbach's α

In the present study, the internal consistency of each of the three behavioral subscales' was assessed using Cronbach's alpha, which can range in value from 0 to 1. A value of .70 or greater indicates that the subscale has adequate internal consistency. Internal consistency provides an estimate of reliability on the basis of the average correlation among scale items."

(C3) Induction and Deduction

Induction: Observations lead to an idea or theory about relationships that exist in the world (I take IN my surroundings and create a theory based on relationships I take IN and perceive) Deduction: A well-established theory predicts observations. Predictions can be made from the theory and tested through experimentation (I DEDUCE based on this theory that X will happen in my surroundings due to Y)

Berkowitz (1992). Some thoughts about conservative evaluations of replications (1-7)

It is suggested that an unduly conservative research tradition operates in social psychology to heighten the perception of inconsistency in research replications. In the large part, this tradition, producing a bias in favor of the null hypothesis stems from a belief in "the law of small numbers" and a failure to appreciate the probabilistic nature of research results so that each replication or dependent measure is expected to be a significant at better than the .05 level by its self. R.A. Fisher emphasized on avoiding type 1 errors and neglect the possibility of type 2 errors is also considered. It is also noted that social psychological tests of hypothesized relationships are typically low in power. The argument in favor of combining probabilities over the series of replications is supported. It may also be, however that a good many social psychologists are also greatly risk averse, so that the possibility of a negative outcome (making a mistake) is given very much more weight than positive information (Favoring the hypothesis being tested by research).

5. Cottrell: Learned drive, evaluation apprehension

Learned drive: underlies social facilitation -- basically innate drive expanded. Evaluation apprehension: (Produces social facilitation effects) The cognitive anticipation of positive or negative outcomes -- which is pronounced by social facilitation. - Confusing article -- Evaluation apprehension exists on its own (i.e. you are scared right now how you will do on this exam) but social facilitation's effects of increasing your drive due to the mere presence of others is a dependent theory. Furthermore, once social facilitation is established, it can further cognitive thought of evaluation apprehension and therefore create a positive feedback loop hormonally.

3. Effect size

Magnitude of phenomenon measured. Small effect size when there is a small population.

Rieger, Chivers, & Bailey (2005). Sexual arousal patterns of bisexual men and Rosenthal, Sylva, Safron, & Bailey (2011). Sexual arousal patterns of bisexual men revisited (1-6)

Men who identify themselves as bisexual report feeling sexually aroused by both men and women. However, past research has not demonstrated that such men exhibit substantial genital arousal to both male and female erotic stimuli, suggesting that they identify as bisexual for reasons other than their genital arousal pattern. The purpose of the present study was to examine arousal patterns among bisexual men who were recruited using stringent criteria involving sexual and romantic experience with both men and women in order to increase the likelihood of finding a bisexual arousal pattern. Bisexual men in the present study demonstrated bisexual patterns of both subjective and genital arousal. It remains unclear which pattern is most typical of contemporary bisexual men: the present results supporting a bisexual arousal pattern, or previous results not finding one. I neither case, understanding men with bisexual arousal patterns could help illuminate the etiology and development of male sexual orientation.

2. Availability heuristic

Mental short cut to think of immediate examples when given a topic. Those who were given meta-analytic training had better examples to base off of and gave closer magnitudes than narrative review pp

4. Meta-analysis

Meta-analytic procedures are favorable in summarizing and integrating research findings, which is why this study used a different type of meta-analytic procedure by only reviewing a few other studies as support to why social psychologists now customary approach to repeated studies (which basically is like considering one investigation at a time independently of the predecessors or successors is too cautious. Do a meta analysis instead.

(Lab) Methodology of MA lit and MA 1&2

Methodology and correct format?

(C8) Control

Non testing group that is used to examine in contrast to testing groups to look for influence of one variable on another with certainty.

(C7) Reality−decision table (α, β, etc.). See also course pack, p.72

Not due to chance Chance Fail to reject Null . Correct TYPE 2 Reject Null TYPE 1 Correct α (Alpha level): Probability of making a type 1 error (hope it low p < .01) β (Beta level): Probability of not making a type 2 error Important as (1-B) is POWER which is the probability the researcher correctly rejects the null hypothesis when it is false.

6. Incentive, justification

Offered money, justification was that it would be unpleasant during water deprivation study

(C14) Participants, respondents

Participant: Experimental, questionnaire Respondent: Correlational, survey

Bushman and Wells (2001). Narrative impressions of literature: The availability bias and the corrective properties of meta-analytic approaches (1-5)

Participants (N= 280) reviewed 20 fictional research summaries of studies examining the relation between similarity and attraction. Although there were some inconsistencies across the fictional studies, there was a positive relation overall (d= 0.2).The authors manipulated the salience of the titles and the serial order in which the studies were presented without changing the results of the studies themselves. Participants recalled the salient titles better than the non salient titles. Participants who were given very brief training in meta-analytic techniques gave estimates of the similarity-attraction relation that were close to the actual magnitudes. Participants who were not given such training (narrative reviewers) were influenced by the salience manipulation and gave estimates that were biased toward the studies that had salient titles. Although the salience manipulation influenced participants in the meta-analytic and narrative groups equally, memory mediated the effects of salience on estimates of effect magnitude only for the narrative review participants.

(C3) Platt's strong inference, crucial experiment, competing hypotheses

Platt's strong inference method: Devise alternative hypothesis, devise a crucial experiment with hypothesis and alternatives, Carry out experiment, Return to step 1 with further refinements of the supported hypothesis. Crucial experiment: Determines if results support hypothesis Competing hypothesis: Aristotle (Heavier weight out of 2 will hit ground first) Galileo (doesnt matter about weight both hit at same time), once results are in competing hypothesis most supported wins and becomes further refined and redone.

(C8) Three designs of Campbell and Stanley

Posttest-only, pretest-postest, and Solomon four-group 1. Participants are randomly assigned to groups 2. atleast two levels of independent variable (One can be zero) 3. Control major threats to internal validity with history and selective selection 4? Platt strong inference -- have to alternative theoretical positions

(C7) Effect size

Power calculations help us to understand how many research participants we need, depending on the magnitude of the change Goal to reduce the chance of type 2 errors.

Steele, Bass, and Crook (1999). The mystery of the Mozart effect: Failure to replicate (1-5)

The Mozart effect is the purported increase in spatial-reasoning performance immediately after exposure to a Mozart piano sonata. Several laboratories have been unable to confirm the existence of the effect despite two positive reports from the original laboratory.The authors of the original studies have provided a list of key procedural components to produce the effect. This experiment attempted to produce a Mozart effect by following those procedural instructions and replicating the procedure of one of the original positive reports.The experiment failed to produce either a statistically significantMozart effect or an effect size suggesting practical significance. This general lack of effect is consistent with previous work by other investigators. We conclude that there is little evidence to support basing intellectual intervention programs on the existence of the Mozart effect.

(C8) Internal Validity

The ability to make valid inferences concerning the relationship between a dependent and an independent variable in an experimental situation

Cecil and Pinkerton (1998). Reliability and validity of a self-efficacy instrument for protective sexual behaviors (1-5)

The authors investigated the psychometric properties of a 22-item scale that measured respondents' perceptions of their ability to refuse sexual intercourse, question potential sexual partners, and use condoms. Two hundred twenty-one male and female undergraduates completed an anonymous questionnaire that measured a wide range of constructs. The scale exhibited good internal consistency, and convergent validity was demonstrated for 5 sexual behavior items (number of sexual partners ever and in the past 3 months, condom use in past 3 months, at last intercourse, and in the future). The instrument appeared to be free of social desirability bias and was reliable and valid for assessing college students' self-efficacy for protective sexual behaviors. College health- care professionals could administer the instrument to help students determine their levels of self-efficacy for engaging in self-protective behaviors and identify domains in which they may need to improve their skills to reduce their risks of acquiring a sexually transmitted disease or having or causing an unplanned pregnancy.

(C7) Treatment effect

The effect produced by the treatment or independent variable on the dependent variable

(C7) Null & alternative hypotheses

The hypothesis that the differences between two or more population parameters are zero. Used nontechnically to refer to the condition that no differences exist between groups in the experiment The condition that differences exist between groups in the experiment

9. Forced compliance

The study was done on them regardless of their knowledge. The cover story...

(C7) Independent, dependent, confounding variables

The variable that is defined by the experimenter and thus is outside the experimental situation (and thus is independent) In an experiment, the variable that is said to be depend on the action of another variable (the independent variable) A variable that systematically varies with the independent variable that could provide an alternative explanation for the influence of the independent variable on the dependent variable

7. Replication

This study has been proven to be highly replicable as it can be performed without much equipment and other general expenses. This study in itself is a 1986 replication and addition to the 1965 Zajonc's contention that the mere presence of another person is sufficient to increase people's generalized arousal and to produce the standard social facilitation effects.

2. Replication

This study has been replicated over and over and an effect has not been found. Provokes future research to continue to try to figure it out because no one has been able to get a positive outcome since the original laboratory. Edited original study to maximize possibility of positive results.

(C14) Fixed alternative

Type of question which limits the number of responses that a participant can make. (Close ended questions)

5. Data exclusion

Using the same approach as earlier studies (Chivers et al.,2004; Rieger et al.,2005), we ipsatized (i.e., standardized within subjects)the data to account for individual differences in overall levels of arousal across all stimuli and subsequently excluded 15 men (5 bisexual,4 homosexual,and 6 heterosexual) for genital non-responding.Analyses that included nonresponders did not affect the direction or significance of results. Whenever arousal to sexual stimuli was used in analyses, we first subtracted arousal to the neutral stimulus in order to facilitate interpretation.

(C14) Funneling

When researchers begin a line of questioning with an open-ended question and then follows with more specific items. Important to go in that order to draw connections between open-ended and close-ended responses.

(C7) Between & within group variance

Within group variance is due to chance (all received same treatment) Between group variance is due to chance (results may vary) and systematically (Treatments vary).

2. Law of small numbers

judgmental bias which occurs when it is assumed that the characteristics of a sample population can be estimated from a small number of observations or data points. This article argues that due to the fact that social psychologists fall for the law of small numbers that they fear of making a low certainty conclusion on an experiment, and tend to make a type 1 error by failing to reject the true null hypothesis (that there is no difference) Too many psychologists fail to recognize the random nature of research results, so that they give too much weight to the question whether any one finding met the conventional .05 level.

1. Recruitment

recruited using stringent criteria involving sexual and romantic experience with both men and women in order to increase the likelihood of finding a bisexual arousal pattern. Participants were 35 bisexual men , 31 homosexual men, and 34 heterosexual men from the greater Chicago area who were recruited from Internet personal advertisement lists for those respective populations. To be eligible ,bisexual participants were required to have had atleast two sexual partners of each sex and a romantic relationship of atleast three months' duration with atleast one person of each sex.

2. mixed design

research involving different research designs for various independent variables used in research. 2x3 factorial design: with the within-subject variable of task difficulty (novel versus well-learned) crossed with the between-subjects variable of type of audience (alone, mere presence, and evaluation apprehension). - Therefore, the mere social facilitation study was a mixed design study as: 1). it tested the independent variables of task difficultly with research design of a within-subject study. 2). it tested the independent variables of type of audience with research design of a between-subject study.

4. Between Ss design

the experimental design was a 2 X 2 factorial in which the extremity of the initial attitude and the incentive for commitment were the manipulated variables. Subjects were randomly assigned to four experimental groups:(a) high thirst/low incentive;(b) high thirst/high incentive,(c) low thirst/low incentive, and (d) low thirst/high incentive.

(Lab) Mediating Variables

the mechanism or process that underlies an observed relationship between an independent variable and a dependent variable via the inclusion of a third hypothetical variable, known as a mediator variable

1. Mozart effect

the purported increase in spatial-reasoning performance immediately after exposure to a Mozart piano sonata.

6. Construct validity

uhhhh... methodology of measuring penile strain?