Question

Please show all work

A researcher is interested in understanding the predictors of why individuals bully other individuals.  She collects the following data.

ID of Respondent	# of Friends who Bully	Respondent was a Bully Victim (0 = No; 1 = Yes)	Gender (0 = Female; 1 = Male)	# of Times Respondent Bullied Others
1	2	1	1	5
2	4	1	0	2
3	3	0	1	8
4	2	0	0	4
5	6	1	1	6
6	3	0	0	2
7	7	1	1	7
8	4	0	0	0
9	2	1	1	1
10	7	1	1	8

If the researcher used all of these variables to predict whether a respondent was a Bully, which variable (# of friends who bully, respondent was a bully victim, or gender) do you believe would be the strongest predictor? Why?

Answer 1

Here I attach the R code and output

data=read.csv(file.choose())
fit=lm(data$respondendbullied~data$nofriends+data$respondentbullyvictim+data$gender)
summary(fit)

Here the response variable used are No. of friends who bully, respondent was a bully victim, or gender

Coefficients:
Estimate Std. Err t value Pr(>|t|)
(Intercept) 0.4909 1.6418 0.299 0.7750
nofriends 0.6395 0.4007 1.596 0.1616
respondentbullyvictim -2.2772 1.8084 -1.259 0.2547
gender 4.3623 1.7247 2.529 0.0447 *

From the output given we can see that the variable gender is the only significant one at 0.05 level of significance. Since the p value is 0.0447< 0.05

The strongest predictor is gender