1. Lab 2: Descriptive Statistics

2. Today’s Activities Complete Brief Personality Inventory – Must put PID on Scantron Calculate Scales and Compute Descriptive Statistics with SPSS

3. Outline Complete Short Personality Survey Again IPIP Analyses – Correctly Recode Reverse Scored Items – Calculate Means, SDs, and Medians for all five scales – Examine Histograms for all 5 scales – Create Z-Scores for all 5 scales – Interpret Z-Score profile for one individual – Identify potential outliers

4. What you need to turn in for HW #2 Survey #2 – in lab (2 pts) A nice looking table with Means, SDs, and Medians for all five scales. These numbers must match the correct values to get credit. (2 pts) A comment on the shape of the distributions for each of the Five factors. (2 pts) A table with the z-score IPIP profile for the individual with the same ID number as this lab section. Provide an interpretation of this profile in words. (2 pts) A comment on whether or not there were any potential outliers for the IPIP and how you made that judgment. Identify those outliers. (2 pts)

5. Complete IPIP Survey Again (Dependability Data) We are collecting data in PSY 395 for educational purposes only. Use PIDs on the short Survey (50 items). PIDs will be used for identification purposes. We will use these scores next week in lab.

6. International Personality Item Pool (IPIP) (Goldberg 1999; Goldberg et al., 2006)

7. The Five Factors I. Extraversion (Talkative, Energetic, Outgoing) II. Agreeableness (Helpful, Trusting, Cooperative) III. Conscientiousness (Reliable, Hardworking, Dependable) IV. Neuroticism (Anxious, Tense, Moody) V. Openness (Curious about intellectual and artistic matters, Values artistic experiences, Has an active imagination) REMEMBER OCEAN

8. Recoding Reversed Items & Calculating Scale Scores

9. Example: Item #e2 Measures Extraversion e2 (item 6 on questionnaire): Don’t talk a lot. High scorers on this item are actually saying they are low on this indicator of Extraversion Therefore, we need to reverse score this item. Given that the responses go from 1 to 5 we can use an easy trick to reverse score this item. Under Transform – Compute: e2_r = 6 – e2.

10. Reverse Scoring with a 1 to 5 Scale 6 – 5 = 6 – 4 = 6 – 3 = 6 – 2 = 6 – 1 = Formula 15 24 33 42 51 RecodedOriginal

11. Extraversion Scale (10 items) Reverse Items: e2, e4, e6, e8, e10 Average Items: e1, e3, e5, e7, e9, e2_r, e4_r, e6_r, e8_r, e10_r Under Transform – Compute: EXTRA = MEAN (e1, e3, e5, e7, e9, e2_r, e4_r, e6_r, e8_r, e10_r).

12. Agreeableness Scale (10 items) Reverse Items: a1, a3, a5, a7, Average Items: a2, a4, a6, a8, a9, a10, a1_r, a3_r, a5_r, a7_r Under Transform – Compute: AGREE = MEAN (a2, a4, a6, a8, a9, a10, a1_r, a3_r, a5_r, a7_r).

13. Conscientiousness Scale (10 items) Reverse: c2, c4, c6, c8, Average Items: c1, c3, c5, c7, c9, c10, c2_r, c4_r, c6_r, c8_r Under Transform – Compute: CONS = MEAN(c1, c3, c5, c7, c9, c10, c2_r, c4_r, c6_r, c8_r).

14. Neuroticism Scale (10 items) Reverse Items: n2, n4 Average Items: n1, n3, n5, n6, n7, n8, n9, n10, n2_r, n4_r Under Transform – Compute: NEURO = MEAN (n1, n3, n5, n6, n7, n8, n9, n10, n2_r, n4_r).

15. Openness (10 Items) Reverse Items: o2, o4, o6, Average Items: o1, o3, o5, o7, o8, o9, o10, o2_r, o4_r, o6_r Under Transform – Compute: OPEN = MEAN (o1, o3, o5, o7, o8, o9, o10, o2_r, o4_r, o6_r).

16. Descriptive Statistics and Histograms

17. Three Descriptive Statistics Mean: Arithmetic Average Median: The Middle Score or the 50 th percentile. It is the value that divides the ordered scores into two equal groups (one high and one low). Standard Deviation: The square root of the Variance. SPSS calculates the Variance as the sum of the squared deviations from the sample mean divided by (n – 1).

18. Sample Data (Mean = 7.4, SD = 2.3) 5.767.45Richard 2.567.49Jane 5.767.45Bob.367.48Roger 6.767.410Sally Squared Mean Deviation MeanHW ScorePerson

19. Histograms

21. How to Get Required Information Under Analyze – Descriptive Statistics  Frequencies Select Variables Under Statistics – Request: Mean, Median, Std. deviation Under Charts – Request: Histograms – Select “With normal curve” Finally, click OK

22. Nonnormality Skewness – Assymetry Negative Positive

23. Nonnormality Kurtosis – More peaked or flat than normal

24. Output Means, SDs, and Medians Frequencies – Visually Examine Range of Scores Note Shape of the Distributions Record the Necessary Information for Homework

25. Z-Scores

26. Z-Score Formula

27. Quickly …. What is the Mean and SD of the Z Scores for any sample?

28. What is a Z-Score? The z-score indicates how many standard deviations above or below the mean the individual score falls. This is considered a readily interpretable score by measurement experts Consider the following battery of achievement tests for John Doe

29. Profile of Scores for a John Doe -.2597History.75120Biology 084Math -.5067English z-ScoreRaw ScoreTest

30. Examples of How to Calculate Z- Scores in SPSS Method 1: Direct Calculation – Assume Mean of E = 3.365 and SD =.700 – Under Transform – Compute: ZEXTRA = (e - 3.365)/.70. Method 2: Use SPSS – Under Analyze  Descriptive Statistics  Descriptives – Select Variables and Click “Save Standardized Values as Variables” – New Variable: Ze is the Z-Scored variable “e”

31. Select Person with ID that Equals Your Lab Section and Interpret her/his IPIP profile -.45OPEN -1.23NEURO.38CONS.29AGREE.37EXTRA Z-ScoreTrait

32. Z-Scores and Outliers Outliers are data points that are very different from the rest of the data Two Possibilities – Data entry error – The data point is unusual For large datasets we might think that z-scores ≥│3.0│ deserve to be examined as potential outliers. Why? 99% of the observations should fall the between the -3.0 and 3.0 range. Other options include looking at Box Plots – Graphs  Legacy Dialogs  Boxplots – Select Simple and Summaries of Separate Variables