Instructions: Ready for an assignment that incorporates all the skills that you have learned this semester? Using your methodology skills, your statistics skills, and your SPSS skills (as well as links to a few SPSS data sets), complete the questions below. IMPORTANT: Answer options may be in a different order, so make sure to choose carefully!

Part One (Use the SPSS DataAnalysisFIU#1PrimacyFall.sav data set for this section).

Study: Imagine Solomon Asch's 1946 classic study on the primacy effect, where he provided participants with a list of words describing another person that either started positively and ended negatively OR started negatively and ended positively. Those in the positive condition saw the following order of words: Intelligent, Industrious, Impulsive, Loyal, Critical, Stubborn, Envious. Those in the negative condition saw the following order of words: Envious, Stubborn, Critical, Loyal Impulsive, Industrious, Intelligent. Ashe found that the first few words participants saw impacted their impressions of the person associated with those words. That is, first impressions led to a more positive assessment of the person when the first words saw were positive.

A researcher is interested in seeing if Ashe's findings can be replicated today in a social media environment. The researcher presents participants with a fake social media page where the page owner asks her friends in a "Facebook poll" to provide one word that best describes her. These descriptions, however, are manipulated by the researcher, all containing the words Intelligent, Industrious, Impulsive, Critical, Stubborn, Envious, although in a different order. Like Asch's original study, some participants see the words listed positive to negative (positive condition) and some see them listed negative to positive (negative condition), but a third group sees a more neutral version (the trait words start with the neutral word "loyal", but the rest of the words are in no particular order - neutral condition).

Trait Order Manipulation: Positive versus Negative versus Neutral

Measures: First, as a manipulation check, participants were asked to recall whether the first word provided by the first friend who responded to the Facebook poll was positive, negative, or neutral. Second, participants rated their level of agreement with the statement, "I have a positive impression of the Facebook page owner" (1 = Strongly disagree to 6 = Strongly agree).

Predictions: The researcher predicted that participants who read a list of traits describing a Facebook user that started positively but ended negatively would rate the user more positively than participants who read a word list that started negatively but ended positively, with those who read a neutral order falling between these extremes.

Using this study design, answer the following four questions:

1). What is the independent variable in this study, and how many levels are there in this independent variable? Choose the correct response (.5 points)

A. IV: Manipulation check recall, with three levels (Positive, Negative, Neutral)

B. IV: Facebook page owner impression rating (Strongly disagree to strongly agree that the participant has a positive impression of the Facebook page owner)

C. IV: Trait order manipulation, with two levels (Positive, Negative)

D. IV: Trait order manipulation, with three levels (Positive, Negative, Neutral)

2). What are the dependent variables in this study, and what scale of measurement are they based on (using NOIR)? Choose the BEST option (.5 points)

A. DV #1: First word recall: Nominal scale - DV #2: Positive impression rating: Interval scale

B. DV #1: First word recall: Interval scale - DV #2: Positive impression rating: Interval scale

C. DV #1: Trait order manipulation: Nominal scale - DV #2: Positive impression rating: Interval scale

D. DV #1: Positive impression rating: Nominal scale - DV #2: Trait order manipulation: Interval scale

3). We are going to run some analyses on the data (Use the DataAnalysisFIU#1PrimacyFall.sav SPSS file). First, use the independent variable and the nominal dependent variable in an SPSS analysis. (Hint: Your scale of measurement for the nominal dependent variable should let you know which specific statistical test to use!). Choose the correct analysis, write-up, and conclusion from the options below (1.5 points)

A. We ran a chi square using trait condition as the independent variable (Positive, Negative, Neutral) and whether participants recalled the first word listed as positive, negative, or neutral. A significant effect emerged, ² (4) = 52.85, p < .001. The majority of participants in the positive condition recalled seeing a positive word (66.7%), the majority of participants in the negative condition recalled seeing a negative word (63.8%), and a majority of participants in the neutral condition correctly recalled seeing a neutral word (51.0%). This indicates that participants paid attention to the photo that they saw. Cramer's V, which is appropriate for this design, was very strong.

B. We ran a chi square using trait condition as the independent variable (Positive, Negative, Neutral) and whether participants recalled the first word listed as positive, negative, or neutral. A significant effect emerged, ² (2) = 52.85, p < .001. The majority of participants in the positive condition recalled seeing a positive word (66.7%), the majority of participants in the negative condition recalled seeing a negative word (63.8%), and a majority of participants in the neutral condition correctly recalled seeing a neutral word (51.0%). This indicates that participants paid attention to the photo that they saw. Cramer's V, which is appropriate for this design, was very strong.

C. We ran a chi square using trait condition as the independent variable (Positive, Negative, Neutral) and whether participants recalled the first word listed as positive, negative, or neutral. A significant effect did not emerge, ² (4) = 52.85, p < .05. There was no difference in recall between the three conditions, indicating that participants did not recall the first word that they saw. Cramer's V, which is appropriate for this design, was very weak.

D. We ran a One Way ANOVA condition using trait condition as the independent variable (Positive, Negative, Neutral) and whether participants recalled the first word listed as positive, negative, or neutral. A significant effect emerge, F(2, 138) = 15.22, p < .001. Tukey post hoc tests showed that participants found the positive condition (M = 1.38, SD = 0.58) lower than the negative condition (M = 1.89, SD = 0.60) and the neutral condition (M = 2.18, SD = 0.91), though the negative and neutral conditions did not differ from each other. This indicates that participants correctly recalled the trait word they saw.

4). For the main analysis, the researcher predicted that participants who read a list of traits describing a Facebook user that started positively but ended negatively would rate the user more positively than participants who read a word list that started negatively but ended positively, with those who read a neutral order falling between these extremes. Run the correct analysis to see if they confirmed their predictions, and choose the correct conclusion from the options below (1.5 points)

A. We ran an independent samples t-Test using condition as the independent variable (Positive, Negative, Neutral) and participants agreement with the statement, "I have a positive impression of the Facebook page owner" as the dependent variable. A significant effect emerged, t(90) = 5.79, p < .001. Participants had more favorable ratings of the Facebook page owner in the positive condition (M = 3.40, SD = 1.23) than in the negative condition (M = 2.13, SD = 0.85). This supports the prediction that the order of traits does impact participant perceptions.

B. We ran a One Way ANOVA using condition as the independent variable (Positive, Negative, Neutral) and participants agreement with the statement, "I have a positive impression of the Facebook page owner" as the dependent variable. A significant effect emerged, F(2, 138) = 15.15, p < .001. Tukey post hoc tests showed that participants agreed with the statement more in the positive order condition (M = 3.40, SD = 1.23) than in the both the neutral order condition (M = 2.73, SD = 1.20) and the negative order condition (M = 2.13, SD = 0.85), and they agreed with the statement more in the neutral condition than in the negative condition. This supports the prediction that the order of traits does impact participant perceptions.

C. We ran a One Way ANOVA using condition as the independent variable (Positive, Negative, Neutral) and participants agreement with the statement, "I have a positive impression of the Facebook page owner" as the dependent variable. A significant effect emerged, F(2, 138) = 15.15, p < .001. Tukey post hoc tests showed that participants agreed with the statement more in the positive order condition (M = 2.73, SD = 1.20) than in the both the neutral order condition (M = 2.13, SD = 0.85) and the negative order condition (M = 3.40, SD = 1.23), and they agreed with the statement more in the neutral condition than in the negative condition. This supports the prediction that the order of traits does impact participant perceptions.

D. We ran a One Way ANOVA using condition as the independent variable (Positive, Negative, Neutral) and participants agreement with the statement, "I have a positive impression of the Facebook page owner" as the dependent variable. A significant effect did not emerge, F(2, 138) = 15.15, p > .05. Participants did not differ in their positive impressions of the Facebook page owner between the positive order condition (M = 3.40, SD = 1.23), the neutral order condition (M = 2.73, SD = 1.20), and the negative order condition (M = 2.13, SD = 0.85), indicating that participants impression ratings do not differ based on the first word that they see.

Part Two (Use the SPSS DataAnalysisFIU#2PrimacyFall.sav data set for this section).

Imagine we alter the design a bit. First, in terms of trait order, we focus only on the positive and the negative trait order conditions (dropping the neutral condition). Second, after doing some research that shows that being in a good mood often facilitates the primacy effect while being in a bad mood negates the effect, we alter the mood of the participant (good mood versus bad mood). The dependent variables remain the same, though we add a new manipulation check questions that asks participants to rate their own mood (I am in a good mood versus I am in a bad mood). Using this new design, answer the following questions.

5). What is/are the independent variable(s) in this study, and how many levels are there to each? (.5 points)

A. IV#1: Trait order manipulation, two levels (Negative versus Positive) - IV #2: Participant Mood, two levels (Good mood versus Bad mood).

B. IV#1: Trait order manipulation, three levels (Negative versus Positive versus Neutral) - IV #2: Participant Mood, two levels (Good mood versus Bad mood).

C. IV#1: Trait order manipulation, three levels (Negative versus Positive versus Neutral) - IV #2: Participant Mood, three levels (Good mood versus Bad mood versus Neutral mood).

D. IV#1: Trait order manipulation, two levels (Negative versus Positive) - IV #2: Participant Mood, three levels (Good mood versus Bad mood versus Neutral mood).

6). Consider all of the possible main effects and interactions for this study. Use the SPSS file named DataAnalysisFIU#2PrimacyFall.sav to run a 2 X 2 ANOVA (I will let YOU figure out which dependent variable to use for this!). Choose the option below that best describes the outcome. (.5 points)

A. There are two significant main effects and a significant interaction

B. There is one significant main effect, one non-significant main effect, and a significant interaction

C. There is one significant main effect, one non-significant main effect, and no significant interaction

D. There are two significant main effects but there is no significant interaction