1 Loading Libraries

#install.packages("apaTables")
#install.packages("kableExtra")

library(psych) # for the describe() command and the corr.test() command
library(apaTables) # to create our correlation table
library(kableExtra) # to create our correlation table

2 Importing Data

d <- read.csv(file="Data/projectdata.csv", header=T)

3 State Your Hypothesis

There will be a significant relationship between social media use, stress, and sense of belonging. Specifically, social media use will be positively related to stress and negatively related to sense of belonging, and stress will be negatively related to sense of belonging.

4 Check Your Variables

# you only need to check the variables you're using in the current analysis
# it's always a good idea to look them to be sure that everything is correct
str(d)
## 'data.frame':    3145 obs. of  7 variables:
##  $ ResponseID: chr  "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
##  $ gender    : chr  "f" "m" "m" "f" ...
##  $ income    : chr  "1 low" "1 low" "rather not say" "rather not say" ...
##  $ socmeduse : int  47 23 34 35 37 13 37 43 37 29 ...
##  $ stress    : num  3.3 3.3 4 3.2 3.1 3.5 3.3 2.4 2.9 2.7 ...
##  $ support   : num  6 6.75 5.17 5.58 6 ...
##  $ belong    : num  2.8 4.2 3.6 4 3.4 4.2 3.9 3.6 2.9 2.5 ...
# Since we're focusing only on our continuous variables, we're going to subset them into their own dataframe. This will make some stuff we're doing later on easier.

d2 <- subset(d, select=c(socmeduse, stress, belong))

# You can use the describe() command on an entire dataframe (d) or just on a single variable (d$pss)

describe(d2)
##           vars    n  mean   sd median trimmed  mad  min  max range  skew
## socmeduse    1 3145 34.46 8.57   35.0   34.74 7.41 11.0 55.0  44.0 -0.32
## stress       2 3145  3.05 0.60    3.0    3.05 0.59  1.3  4.7   3.4  0.03
## belong       3 3145  3.23 0.60    3.3    3.25 0.59  1.3  5.0   3.7 -0.26
##           kurtosis   se
## socmeduse     0.27 0.15
## stress       -0.16 0.01
## belong       -0.13 0.01
# NOTE: Our fake variable has high kurtosis, which we'll ignore for the lab because we created it to be problematic. If you have high skew or kurtosis for any of your project variables, you will need to discuss it below in the Issues with My Data and Write up Results sections, as well as in your final project manuscript if your data does not meet the normality assumption.


# also use histograms to examine your continuous variables
# Because we are looking at 3 variables, we will have 3 histograms.

hist(d$socmeduse)

hist(d$stress)

hist(d$belong)

# last, use scatterplots to examine your continuous variables together, for each pairing
# because we are looking at 3 variables, we will have 3 pairings/plots. 

plot(d$socmeduse, d$stress)

plot(d$socmeduse, d$belong)

plot(d$stress, d$belong)

5 Check Your Assumptions

5.1 Pearson’s Correlation Coefficient Assumptions

  • Should have two measurements for each participant.
  • Variables should be continuous and normally distributed.
  • Outliers should be identified and removed.
  • Relationship between the variables should be linear.

5.1.1 Checking for Outliers

Note: For correlations, you will NOT screen out outliers or take any action based on what you see here. This is something you will simply check and then discuss in your write-up.We will learn how to removed outliers in later analyses.

# We are going to standardize (z-score) all of our 3 variables, and check them for outliers.

d2$socmeduse <- scale(d2$socmeduse, center=T, scale=T)
hist(d2$socmeduse)

sum(d2$socmeduse < -3 | d2$unhappy > 3)
## [1] 0
d2$stress <- scale(d2$stress, center=T, scale=T)
hist(d2$stress)

sum(d2$stress < -3 | d2$life_satis > 3)
## [1] 0
d2$belong <- scale(d2$belong, center=T, scale=T)
hist(d2$belong)

sum(d2$belong < -3 | d2$fake > 3)
## [1] 0

5.2 Issues with My Data

Three of my variables meet all of the assumptions of Pearson’s correlation coefficient. None of the variables had high skewness or kurtosis, and no outliers were identified. The relationships between the variable appear to be linear. Therefore, correlations between social media use, stress, and sense of belonging can be interpreted without concern regarding violations of the assumptions of Pearson’s correlation coefficient.

6 Run a Single Correlation

corr_output <- corr.test(d2$socmeduse, d2$stress)

7 View Single Correlation

corr_output
## Call:corr.test(x = d2$socmeduse, y = d2$stress)
## Correlation matrix 
##      [,1]
## [1,] 0.09
## Sample Size 
## [1] 3145
## These are the unadjusted probability values.
##   The probability values  adjusted for multiple tests are in the p.adj object. 
##      [,1]
## [1,]    0
## 
##  To see confidence intervals of the correlations, print with the short=FALSE option

8 Create a Correlation Matrix

corr_output_m <- corr.test(d2)

9 View Test Output

corr_output_m
## Call:corr.test(x = d2)
## Correlation matrix 
##           socmeduse stress belong
## socmeduse      1.00   0.09   0.28
## stress         0.09   1.00   0.30
## belong         0.28   0.30   1.00
## Sample Size 
## [1] 3145
## Probability values (Entries above the diagonal are adjusted for multiple tests.) 
##           socmeduse stress belong
## socmeduse         0      0      0
## stress            0      0      0
## belong            0      0      0
## 
##  To see confidence intervals of the correlations, print with the short=FALSE option
# Remember to report the p-values from the matrix that are ABOVE the diagonal!

Remember, Pearson’s r is also an effect size! We don’t report effect sizes for non-sig correlations.

  • Strong: Between |0.50| and |1|
  • Moderate: Between |0.30| and |0.49|
  • Weak: Between |0.10| and |0.29|
  • Trivial: Less than |0.09|

10 Write Up Results

To test our hypothesis that social media use, stress, and sense of belonging would be correlated with one another, we calculated a series of Pearson’s correlation coefficients. All three of the variables met the required assumptions of the test, with both meeting the standards of normality and containing no outliers.

As predicted, we found that all 3 variables were significantly correlated (all ps < .001). The effect sizes of all correlations ranged from small to medium (rs > .09-.30 #; Cohen, 1988). Additionally, social media use was found to be positively related to stress, ass predicted, r= .09, p< .001. Contrary to our hypothesis, social media use was found to be positively related to sense of belonging, r= .28, p < .001. Similary, contrary to our hypothesis, stress was found to be positively related to sense of belonging, r=.30, p< .001. Please refer to the correlation coefficients reported in Table 1.

Table 1: Means, standard deviations, and correlations with confidence intervals
Variable M SD 1 2
Social Media Use 34.46 8.57
Stress 3.05 0.60 .09**
[.06, .13]
Sense of Belonging 3.23 0.60 .28** .30**
[.25, .31] [.27, .33]
Note:
M and SD are used to represent mean and standard deviation, respectively. Values in square brackets indicate the 95% confidence interval. The confidence interval is a plausible range of population correlations that could have caused the sample correlation.
* indicates p < .05
** indicates p < .01.

References

Cohen J. (1988). Statistical Power Analysis for the Behavioral Sciences. New York, NY: Routledge Academic.