K3. Why did the certain ethnic mother put her baby in a crib with 20-foot high legs? So she could hear it if it fell out of bed.

Transcription

1 Factor Analysis 1 COM 531, Spring 2009 K. Neuendorf MODEL: From Group Humor Data Set-- Responses to jokes: K1 K2 F1. F2. F3. F4. F5 K29 F6 K30 K31 For all items K1-K31, 0=not funny at all, 10=extremely funny: K1. Baseball is 90 percent mental. The other half is physical. --Yogi Berra K2. While you are away, movie stars are taking your women. Robert Redford is dating your girlfriend, Tom Selleck is kissing your lady, Bart Simpson is making love to your wife. -- Baghdad Betty, Iraqi radio announcer, to Gulf War troops K3. Why did the certain ethnic mother put her baby in a crib with 20-foot high legs? So she could hear it if it fell out of bed. K4. What do you get when you cross a proctologist with Purple Rain? Finger prince. K5. What s the difference between Florida and yogurt? Yogurt has an active culture. K6. In East Naples, Florida, a would-be robber became so angry at learning that his amputee-victim was not carrying drugs that he beat the man on the head with the man s artificial leg. K7. So, two blondes walk into a building. You d think one of them would have seen it. K8. Overheard in a bar: You know that alcohol kills brain cells. Yeah, but only the weak ones. K9. Sign on a dry cleaners: We don t tear your clothes with machines, we do it carefully by hand. K10. A young bull and an old bull are standing on top of a hill, looking down at the herd. The young bull says, Let s run down there and screw a couple cows. The old bull says, Let s walk down and screw them all. K11. It s no exaggeration to say the undecideds could go one way or another. -- George H. W. Bush

2 2 K12. K13. K14. A man walked into a lawyer's office and inquired about the lawyer's rates. "$50.00 for three questions." replied the lawyer. "Isn't that awfully steep?" asked the man. "Yes." the lawyer replied, "What was your third question?" K15. Why do Scotsmen wear kilts? So the sheep won't hear the zipper. K16. What's the difference between a married man and a bachelor? One kisses the Mrs. and the other misses the kisses. K17. What is the new O.J. web site address? Slash.slash.backslash.escape K18. What s is the difference between "ooooooh" and "aaaaaaah"? About three inches. K19. What s the difference between a snowman and a snowwoman? Snowballs.

3 K20. A guy goes into a doctors office with a frog growing out of his head the doctors says, Tell me how it started. And the frog says, It started out as a bump on my ass. 3 K21. How many guys does it take to open a beer? None. It should be opened by the time she brings it. K22. Q. What did the fish say when he hit a concrete wall? A. "Damn." K23. How do blonde brain cells die? Alone. K24. Q. What's the difference between roast beef and pea soup? A. Anyone can roast beef. K25. What do you call a handcuffed man? Trustworthy K26. If Ella Fitzgerald married Darth Vader, she'd be Ella Vader. K27. What do you call a man with half a brain? Gifted. K28. The Law of Motivation: Creativity is great, but plagiarism is faster. K29. What's the difference between a new husband and a new dog? After a year, the dog is still excited to see you. K30. Why do women fake orgasms? Because they think men care. K31.

4 ANALYZE --> DATA REDUCTION --> FACTOR 4 DESCRIPTIVES --> STATISTICS --> UNIVARIATE DESCRIPTIVES, INITIAL SOLUTION --> CORRELATION MATRIX --> COEFFICIENTS, SIGNIFICANCE LEVELS, KMO & BARTLETT S CONTINUE

5 EXTRACTION --> METHOD --> PRINCIPAL COMPONENTS --> ANALYZE --> CORRELATION MATRIX --> DISPLAY --> UNROTATED FACTOR SOLUTION, SCREE PLOT --> EXTRACT --> EIGENVALUES OVER 1 --> MAXIMUM ITERATIONS FOR CONVERGENCE 100 CONTINUE 5

6 ROTATION --> METHOD --> VARIMAX --> DISPLAY --> ROTATED SOLUTION --> MAXIMUM ITERATIONS FOR CONVERGENCE 100 CONTINUE 6

7 SCORES --> SAVE AS VARIABLES --> METHOD --> REGRESSION --> DISPLAY FACTOR SCORE COEFFICIENT MATRIX CONTINUE 7

8 OPTIONS --> MISSING VALUES --> EXCLUDE CASES LISTWISE --> COEFFICIENT DISPLAY FORMAT --> SORTED BY SIZE CONTINUE 8 OK

9 SPSS OUTPUT 9 GET FILE='C:\PROGRA~1\Eudora\Attach\humgr sav'. SAVE OUTFILE='C:\c531\S08\humgr sav' /COMPRESSED. FACTOR /VARIABLES k1 k2 k3 k4 k5 k6 k7 k8 k9 k10 k11 k12 k13 k14 k15 k16 k17 k18 k19 k20 k21 k22 k23 k24 k25 k26 k27 k28 k29 k30 k31 /MISSING LISTWISE /ANALYSIS k1 k2 k3 k4 k5 k6 k7 k8 k9 k10 k11 k12 k13 k14 k15 k16 k17 k18 k19 k20 k21 k22 k23 k24 k25 k26 k27 k28 k29 k30 k31 /PRINT UNIVARIATE INITIAL CORRELATION SIG KMO EXTRACTION ROTATION FSCORE /FORMAT SORT /PLOT EIGEN /CRITERIA MINEIGEN(1) ITERATE(100) /EXTRACTION PC /CRITERIA ITERATE(100) /ROTATION VARIMAX /SAVE REG(ALL) /METHOD=CORRELATION.

10 Factor Analysis 10 Descriptive Statistics k1--berra k2--baghdad Betty k3--baby crib k4--finger prince k5--active culture k6--amputee victim k7--two blondes k8--brain cells k9--dry cleaners k10--two bulls k11--george Bush k12--baby owls (PIC) k13--boo. (PIC) k14--three questions k15--scotsmen/kilts k16--misses kisses k17--oj website k18--ooooooh k19--snowballs k20--frog k21--open a beer k22--damn k23--blonde brain cells k24--roast beef k25--handcuffed man k26--ella Vader k27--half a brain k28--plagiarism k29--husband & dog k30--fake O k31--locust (PIC) Mean Std. Deviation Analysis N

11 11

12 12

13 13

14 14

15 15

16 16

17 17 KMO and Bartlett's Test Kaiser-Meyer-Olkin Measure of Sampling Adequacy..922 Bartlett's Test of Sphericity Approx. Chi-Square df Sig Communalities Initial Extraction k1--berra k2--baghdad Betty k3--baby crib k4--finger prince k5--active culture k6--amputee victim k7--two blondes k8--brain cells k9--dry cleaners k10--two bulls k11--george Bush k12--baby owls (PIC) k13--boo. (PIC) k14--three questions k15--scotsmen/kilts k16--misses kisses k17--oj website k18--ooooooh k19--snowballs k20--frog k21--open a beer k22--damn k23--blonde brain cells k24--roast beef k25--handcuffed man k26--ella Vader k27--half a brain k28--plagiarism k29--husband & dog k30--fake O k31--locust (PIC) Extraction Method: Principal Component Analysis.

18 18 Component Total Variance Explained Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative % Extraction Method: Principal Component Analysis.

19 19 12 Scree Plot Eigenvalue Component Number

20 20 k23--blonde brain cells k28--plagiarism k22--damn k25--handcuffed man k15--scotsmen/kilts k30--fake O k29--husband & dog k16--misses kisses k8--brain cells k20--frog k21--open a beer k7--two blondes k5--active culture k14--three questions k10--two bulls k9--dry cleaners k24--roast beef k19--snowballs k27--half a brain k17--oj website k31--locust (PIC) k18--ooooooh k26--ella Vader k13--boo. (PIC) k4--finger prince k6--amputee victim k11--george Bush k3--baby crib k1--berra k12--baby owls (PIC) k2--baghdad Betty Extraction Method: Principal Component Analysis. a. 6 components extracted. Component Matrix a Component E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E-02

21 21 k29--husband & dog k27--half a brain k30--fake O k16--misses kisses k25--handcuffed man k13--boo. (PIC) k31--locust (PIC) k24--roast beef k26--ella Vader k11--george Bush k15--scotsmen/kilts k8--brain cells k7--two blondes k23--blonde brain cells k22--damn k21--open a beer k28--plagiarism k19--snowballs k10--two bulls k18--ooooooh k20--frog k17--oj website k4--finger prince k3--baby crib k1--berra k2--baghdad Betty k5--active culture k6--amputee victim k12--baby owls (PIC) k9--dry cleaners k14--three questions Rotated Component Matrix a Component E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E E-02 Extraction Method: Principal Component Analysis. Rotation Method: Varimax with Kaiser Normalization. a. Rotation converged in 22 iterations E E E Component Transformation Matrix Component Extraction Method: Principal Component Analysis. Rotation Method: Varimax with Kaiser Normalization.

22 22 Component Score Coefficient Matrix Component k1--berra k2--baghdad Betty k3--baby crib k4--finger prince k5--active culture k6--amputee victim k7--two blondes k8--brain cells k9--dry cleaners k10--two bulls k11--george Bush k12--baby owls (PIC) k13--boo. (PIC) k14--three questions k15--scotsmen/kilts k16--misses kisses k17--oj website k18--ooooooh k19--snowballs k20--frog k21--open a beer k22--damn k23--blonde brain cells k24--roast beef k25--handcuffed man k26--ella Vader k27--half a brain k28--plagiarism k29--husband & dog k30--fake O k31--locust (PIC) Extraction Method: Principal Component Analysis. Rotation Method: Varimax with Kaiser Normalization. Component Scores.

23 23 Component Score Covariance Matrix Component E E E E E E E E E E E E E E E E E E Extraction Method: Principal Component Analysis. Rotation Method: Varimax with Kaiser Normalization. Component Scores.

24 Table 1 24 Orthogonal Factor Analysis for Responses to Jokes Dispar./ Marriage Verbal Incong. 1 Factor Loadings Dispar./ Stupid High Arousal/ Taboo Verbal Incong. 2 Classic Incong. Communality k29--husband & dog k27--half a brain k30--fake O k16--misses kisses k25--handcuffed man k13--boo. (PIC) k31--locust (PIC) k24--roast beef k26--ella Vader k11--george Bush k15--scotsmen/kilts k8--brain cells k7--two blondes k23--blonde brain cells k22--damn k21--open a beer k28--plagiarism k19--snowballs k10--two bulls k18--ooooooh k20--frog k17--oj website , k4--finger prince k3--baby crib k1--berra k2--baghdad Betty k5--active culture k6--amputee victim k12--baby owls (PIC) k9--dry cleaners k14--three questions Eigenvalue [18.11] Percent of Total Variance 11.5% 10.9% 10.0% 9.4% 9.4% 7.3% 58.4% Percent of Common Variance 19.7% 18.7% 17.1% 16.1% 16.0% 12.4% 100.0% KMO measure of sampling adequacy =.922 Bartlett s test of sphericity: approx. chi-square = , df = 465, p<.001

25 Factor Analysis Writeup 25 The 31 joke response measures were submitted to an exploratory factor analysis, with principal components factoring, orthogonal rotation and an extraction cutoff of eigenvalue=1.0 (i.e., latent root criterion). This resulted in six factors with eigenvalues ranging from 3.57 (11.5% of total variance) to 2.25 (7.3% of total variance). The full six-factor solution explained 58.4% of the total variance. The measure of sampling adequacy (MSA) was.922 (i.e., meritorious according to Kaiser; see Hair et al.) and the Bartlett s test of sphericity resulted in a highly significant chi-square (3415.8, p<.001), indicating the appropriateness of this set of 31 items for factor analysis. Communalities ranged from a low of.420 to a high of.722, indicating a reasonable amount of shared variance for all items. The six factors were given labels based on those items loading highly and cleanly on each factor. Factor 1 was titled Disparagement/Marriage due to high loadings for jokes related to the battle of the sexes, notably within marriage. Factor 2, Verbal Incongruity 1, was given that label because of high-loading jokes relying on verbal twists and puns. Factor 3 was called Disparagement/Stupid due to its dependence on jokes that poke fun at stupid people or stupid actions. Factor 4 was a High Arousal/Taboo factor its high-loading jokes contain sexual innuendo presented in a rather crass fashion. Factor 5 was labeled Verbal Incongruity 2 because, like Factor 2, it represented puns, double entendres, and other plays on words. Finally, Factor 6, Classic Incongruity, seemed to represent incongruous juxtapositions of words or images. [Could also comment on items that do not load very cleanly e.g., K15, K21, K28, K17, K6, K14.]