# install any packages you have not previously used, then comment them back out.
#install.packages("car")
#nstall.packages("effsize")
library(psych) # for the describe() command
library(car) # for the leveneTest() command
## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:psych':
##
## logit
library(effsize) # for the cohen.d() command
##
## Attaching package: 'effsize'
## The following object is masked from 'package:psych':
##
## cohen.d
d <- read.csv(file="C:/Users/jd/OneDrive - Indiana University/M311/Research/Final Paper/Data/projectdata.csv", header=T)
# For the HW, you will import the project dataset you cleaned previously
# This will be the dataset you'll use for HWs throughout the rest of the semester
I predict that people with a higher education will report significantly higher levels of mindfulness than people without high levels of education.
# you **only** need to check the variables you're using in the current analysis
## Checking the Categorical variable (IV)
str(d)
## 'data.frame': 3074 obs. of 7 variables:
## $ ResponseID : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ edu : chr "2 Currently in college" "5 Completed Bachelors Degree" "2 Currently in college" "2 Currently in college" ...
## $ usdream : chr "american dream is important and achievable for me" "american dream is important and achievable for me" "american dream is not important and maybe not achievable for me" "american dream is not important and maybe not achievable for me" ...
## $ moa_independence: num 3.67 3.67 3.5 3 3.83 ...
## $ mindful : num 2.4 1.8 2.2 2.2 3.2 ...
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...
# if the categorical variable you're using is showing as a "chr" (character), you must change it to be a ** factor ** -- using the next line of code (as.factor)
d$edu <- as.factor(d$edu)
str(d)
## 'data.frame': 3074 obs. of 7 variables:
## $ ResponseID : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ edu : Factor w/ 7 levels "1 High school diploma or less, and NO COLLEGE",..: 2 5 2 2 2 2 5 2 2 2 ...
## $ usdream : chr "american dream is important and achievable for me" "american dream is important and achievable for me" "american dream is not important and maybe not achievable for me" "american dream is not important and maybe not achievable for me" ...
## $ moa_independence: num 3.67 3.67 3.5 3 3.83 ...
## $ mindful : num 2.4 1.8 2.2 2.2 3.2 ...
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...
table(d$edu, useNA = "always")
##
## 1 High school diploma or less, and NO COLLEGE
## 53
## 2 Currently in college
## 2487
## 3 Completed some college, but no longer in college
## 35
## 4 Complete 2 year College degree
## 177
## 5 Completed Bachelors Degree
## 135
## 6 Currently in graduate education
## 131
## 7 Completed some graduate degree
## 56
## <NA>
## 0
## Checking the Continuous variable (DV)
# you can use the describe() command on an entire dataframe (d) or just on a single variable within your dataframe -- which we will do here
describe(d$edu)
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1* 1 3074 2.5 1.24 2 2.18 0 1 7 6 2.2 3.74 0.02
# also use a histogram to visualize your continuous variable
hist(d$mindful)
# use tedu# use the describeBy() command to view the means and standard deviations by group
# it's very similar to the describe() command but splits the dataframe according to the 'group' variable
describeBy(d$mindful, group=d$edu)
##
## Descriptive statistics by group
## group: 1 High school diploma or less, and NO COLLEGE
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 53 3.6 0.95 3.6 3.65 0.99 1.33 5.4 4.07 -0.35 -0.4 0.13
## ------------------------------------------------------------
## group: 2 Currently in college
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 2487 3.67 0.84 3.67 3.68 0.79 1.13 6 4.87 -0.05 -0.13 0.02
## ------------------------------------------------------------
## group: 3 Completed some college, but no longer in college
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 35 3.77 0.8 3.73 3.78 0.79 2 5.53 3.53 -0.04 -0.45 0.14
## ------------------------------------------------------------
## group: 4 Complete 2 year College degree
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 177 3.9 0.79 3.93 3.9 0.79 1.67 5.6 3.93 -0.09 -0.24 0.06
## ------------------------------------------------------------
## group: 5 Completed Bachelors Degree
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 135 3.93 0.88 3.93 3.92 0.89 1.8 6 4.2 0.12 -0.46 0.08
## ------------------------------------------------------------
## group: 6 Currently in graduate education
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 131 3.77 0.85 3.8 3.79 0.79 1.87 6 4.13 -0.17 -0.14 0.07
## ------------------------------------------------------------
## group: 7 Completed some graduate degree
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 56 3.76 0.95 3.7 3.76 0.89 1.73 5.67 3.93 -0.08 -0.49 0.13
# lastly, use a boxplot to examine your chosen continuous and categorical variables together
boxplot(d$edu~d$mindful)
# If the IV has more than 2 levels, you must DROP any additional levels in order to meet the first assumption of a t-test.
## NOTE: This is a FOUR STEP process!
d <- subset(d, grepl("^[15] ", edu)) # use subset() to remove all participants from the additional level
table(d$edu, useNA = "always")# verify that now there are ZERO participants in the additional level
##
## 1 High school diploma or less, and NO COLLEGE
## 53
## 2 Currently in college
## 0
## 3 Completed some college, but no longer in college
## 0
## 4 Complete 2 year College degree
## 0
## 5 Completed Bachelors Degree
## 135
## 6 Currently in graduate education
## 0
## 7 Completed some graduate degree
## 0
## <NA>
## 0
d$edu <- droplevels(as.factor(d$edu)) # use droplevels() to drop the empty factor
table(d$edu, useNA = "always") # verify that now the entire factor level is removed
##
## 1 High school diploma or less, and NO COLLEGE
## 53
## 5 Completed Bachelors Degree
## 135
## <NA>
## 0
## Repeat ALL THE STEPS ABOVE if your IV has more levels that need to be DROPPED. Copy the 4 lines of code, and replace the level name in the subset() command.
We can test whether the variances of our two groups are equal using Levene’s test. The NULL hypothesis is that the variance between the two groups is equal, which is the result we WANT. So when running Levene’s test we’re hoping for a NON-SIGNIFICANT result!
# use the leveneTest() command from the car package to test homogeneity of variance
# it uses the same 'formula' setup that we'll use for our t-test: formula is y~x, where y is our DV and x is our IV
leveneTest(mindful~edu, data =d)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 1 0.3315 0.5655
## 186
LeveneLevene’s test revealed that our data does not have significantly different variances between the seven comparison groups, based on education level, on their levels of mindfulness
When running a t-test, we can account for heterogeneity in our variance by using the Welch’s t-test, which does not have the same assumption about variance as the Student’s t-test (the general default type of t-test in statistics). R defaults to using Welch’s t-test so this doesn’t require any changes on our part! Even if your data has no issues with homogeneity of variance, you’ll still use Welch’s t-test – it handles the potential issues around variance well and there are no real downsides. We’re using Levene’s test here to get into the habit of checking the homogeneity of our variance, even if we already have the solution for any potential problems.
My independent variable did not have more than two levels.
My data does not have an issue regarding homogeneity of variance, as Levene’s test was not significant. Since there is no significant heterogeneity of variance, I can use Student’s t-test in my analysis, although Welch’s t-test is also appropriate.
# Very simple! we use the same formula of y~x, where y is our DV and x is our IV
t_output <- t.test(d$mindful~d$edu) # t_output will now show in your Global Environment
t_output
##
## Welch Two Sample t-test
##
## data: d$mindful by d$edu
## t = -2.1875, df = 88.768, p-value = 0.03134
## alternative hypothesis: true difference in means between group 1 High school diploma or less, and NO COLLEGE and group 5 Completed Bachelors Degree is not equal to 0
## 95 percent confidence interval:
## -0.63175122 -0.03033124
## sample estimates:
## mean in group 1 High school diploma or less, and NO COLLEGE
## 3.603774
## mean in group 5 Completed Bachelors Degree
## 3.934815
# once again, we use the same formula, y~x, to calculate cohen's d
# We **only** calculate effect size if the test is SIG!
d_output <- cohen.d(d$mindful~d$edu) # d_output will now show in your Global Environment
d_output
##
## Cohen's d
##
## d estimate: -0.3671998 (small)
## 95 percent confidence interval:
## lower upper
## -0.68915898 -0.04524068
## Remember to always take the ABSOLAUTE VALUE of the effect size value (i.e., it will never be negative)
To test our hypothesis that participants in our sample with a completed Bachelor’s degree would report significantly higher levels of mindfulness than participants with a high school diploma or less, we used an independent samples t-test. This required us to drop the other education levels from our sample, as we are limited to a two-group comparison when using this test. We previously tested the homogeneity of variance with Levene’s test and found no signs of heterogeneity (p = .4427). However, this test included all seven education levels and should be rerun for our two comparison groups. We used Welch’s t-test, which does not assume homogeneity of variance.
As predicted, we found that participants with a completed Bachelor’s degree (M = 3.93) reported significantly higher levels of mindfulness than participants with a high school diploma or less (M = 3.60); t(88.77) = -2.19, p = .031 (see Figure 1). The effect size was calculated using Cohen’s d, with a value of -0.37 (small effect; Cohen, 1988).
References
Cohen J. (1988). Statistical Power Analysis for the Behavioral Sciences. New York, NY: Routledge Academic.