Due Thursday

profilen33dpap3rs
PredictionModelsanalysis.docx

Logistic Regression Analysis

Lacourse, Claes, and Villeneuve (2001) carried out a study to see whether a love of heavy metal could predict suicide risk. Eric Lacourse and his colleagues used questionnaires to measure several variables: suicide risk (yes or no), marital status of parents (together or divorced/separated), the extent to which the person’s mother and father were neglectful, self-estrangement/powerlessness (adolescents who have negative self-perceptions, are bored with life, etc.), social isolation (feelings of a lack of support), normlessness (beliefs that socially disapproved behaviors can be used to achieve certain goals), meaninglessness (doubting that school is relevant to gain employment) and drug use. In addition, the authors measured liking of heavy metal; they included the sub-genres of classic (Black Sabbath, Iron Maiden), thrash metal (Slayer, Metallica), death/black metal (Obituary, Burzum) and gothic (Marilyn Manson). As well as liking, they measured behavioral manifestations of worshipping these bands (e.g., hanging posters, hanging out with other metal fans) and what the authors termed ‘vicarious music listening’ (whether music was used when angry or to bring out aggressive moods). They used logistic regression to predict suicide risk from these variables for males and females separately.

Upon running a logistic regression analysis, you obtain the following output:

Omnibus Tests of Model Coefficients

Chi-square

df

Sig.

Step 1

Step

5.833

3

.120

Block

5.833

3

.120

Model

50.417

12

.000

Model Summary

Step

-2 Log likelihood

Cox & Snell R Square

Nagelkerke R Square

1

85.116a

.341

.506

a. Estimation terminated at iteration number 6 because parameter estimates changed by less than .001.

Classification Tablea

Observed

Predicted

Suicide Risk

Percentage Correct

Non-Suicidal

Suicidal

Step 1

Suicide Risk

Non-Suicidal

85

6

93.4

Suicidal

13

17

56.7

Overall Percentage

84.3

a. The cut value is .500

Variables in the Equation

B

S.E.

Wald

df

Sig.

Exp(B)

Step 1a

Age

.693

.323

4.589

1

.032

1.999

Marital Status(1)

-.183

.677

.073

1

.786

.832

Drug Use

.317

.103

9.446

1

.002

1.373

Father Negligence

.085

.048

3.127

1

.077

1.088

Social Isolation

-.006

.076

.006

1

.939

.994

Meaninglessness

-.067

.061

1.191

1

.275

.936

Mother Negligence

-.020

.053

.136

1

.713

.981

Normlessness

.191

.109

3.089

1

.079

1.211

Self-Estrangement/Powerlessness

.155

.065

5.727

1

.017

1.168

Liking Metal Music

.136

.092

2.184

1

.139

1.145

Vicarious Listening

-.342

.196

3.033

1

.082

.710

Worshipping

.159

.129

1.506

1

.220

1.172

Constant

-18.828

6.314

8.891

1

.003

.000

a. Variable(s) entered on step 1: Liking Metal Music, Vicarious Listening, Worshipping.

1) Does listening to heavy metal music (Variables: Liking Metal Music, Vicarious Listening, Worshipping) predict suicide risk in women?

2) What factors predict suicide risk in women?

Stepwise Multiple Regression

Ong et al. (2011) conducted an interesting study that examined the relationship between narcissism and behavior on Facebook in 275 adolescents. They measured the Age, Gender and Grade (at school), as well as extroversion and narcissism. They also measured how often (per week) these people updated their Facebook status (FB_Status), and also how they rated their own profile picture on each of four dimensions: coolness, glamour, fashionableness and attractiveness. These ratings were summed as an indicator of how positively they perceived the profile picture they had selected for their page (FB_Profile_TOT). They hypothesized that narcissism would predict, above and beyond the other variables, the frequency of status updates, and how positive a profile picture the person chose. To test this, they conducted two hierarchical regressions: one with FB_Status as the outcome and one with FB_Profile_TOT as the outcome. In both models they entered Age, Gender and Grade in the first block, then added extroversion (NEO_FFI) in a second block, and finally narcissism (NPQC_R) in a third block. Use the provided output to answer the questions below.

This regression will assess whether narcissism predicts, above and beyond the other variables, the rating of profile pictures.

Block 1

Age, Gender, Grade

Block 2

Extraversion

Block 3

Narcissism

Variables Entered/Removeda

Model

Variables Entered

Variables Removed

Method

1

Extraversion - Totalb

.

Enter

2

NPQC-R Totalb

.

Enter

a. Dependent Variable: Sum of Profile picture ratings

b. All requested variables entered.

Model Summaryc

Model

R

R Square

Adjusted R Square

Std. Error of the Estimate

Change Statistics

R Square Change

Sig. F Change

1

.355a

.126

.121

3.438

.126

.000

2

.504b

.254

.245

3.187

.127

.000

a. Predictors: (Constant), Extraversion - Total

b. Predictors: (Constant), Extraversion - Total, NPQC-R Total

c. Dependent Variable: Sum of Profile picture ratings

ANOVAa

Model

Sum of Squares

df

Mean Square

F

Sig.

1

Regression

283.715

1

283.715

24.001

.000b

Residual

1962.262

166

11.821

Total

2245.976

167

2

Regression

569.702

2

284.851

28.039

.000c

Residual

1676.274

165

10.159

Total

2245.976

167

a. Dependent Variable: Sum of Profile picture ratings

b. Predictors: (Constant), Extraversion - Total

c. Predictors: (Constant), Extraversion - Total, NPQC-R Total

Coefficientsa

Model

Unstandardized Coefficients

Standardized Coefficients

t

Sig.

B

Std. Error

Beta

1

(Constant)

1.486

2.064

.720

.473

Extraversion - Total

.228

.046

.355

4.899

.000

2

(Constant)

.614

1.920

.320

.749

Extraversion - Total

.099

.049

.155

2.013

.046

NPQC-R Total

.196

.037

.409

5.306

.000

a. Dependent Variable: Sum of Profile picture ratings

1. Interpret your results. How much of the variance in frequency of status updates can be explained by extraversion and narcissism?

2. Does narcissism predict profile picture ratings above and beyond extraversion?

3. What do the results tell us about teenagers and Facebook?