## Summary and Analysis of Extension Program Evaluation in R

Salvatore S. Mangiafico

# Two-sample t-test

The two-sample unpaired t-test is a commonly used test that compares the means of two samples.

##### Appropriate data

•  Two-sample data.  That is, one measurement variable in two groups or samples

•  Dependent variable is interval/ratio, and is continuous

•  Independent variable is a factor with two levels.  That is, two groups

•  Data for each population are normally distributed

•  For Student's t-test, the two samples need to have the same variance.  However, Welch’s t-test, which is used by default in R, does not assume equal variances.

•  Observations between groups are independent.  That is, not paired or repeated measures data

•  Moderate skewness is permissible if the data distribution is unimodal without outliers

##### Hypotheses

•  Null hypothesis:  The means of the populations from which the data were sampled for each group are equal.

•  Alternative hypothesis (two-sided): The means of the populations from which the data were sampled for each group are not equal.

##### Interpretation

Reporting significant results as “Mean of variable Y for group A was different than that for group B.” is acceptable.

##### Other notes and alternative tests

•  The nonparametric analogue for this test is the two-sample Mann–Whitney U Test.  Another option is to use a permutation test.  See Mangiafico (2015b) in the “References” section.

•  Power analysis for the two-sample t-test can be found at Mangiafico (2015a) in the “References” section.

### Packages used in this chapter

The packages used in this chapter include:

•  psych

•  FSA

•  lattice

•  lsr

The following commands will install these packages if they are not already installed:

if(!require(psych)){install.packages("psych")}
if(!require(FSA)){install.packages("FSA")}
if(!require(lattice)){install.packages("lattice")}
if(!require(lsr)){install.packages("lsr")}

### Two-sample t-test example

In the following example, Brendon Small and Coach McGuirk have their SNAP-Ed students keep diaries of what they eat for a week, and then calculate the daily sodium intake in milligrams.  Since the classes have received different nutrition education programs, they want to see if the mean sodium intake is the same for both classes.

A two-sample t-test can be conducted with the t.test function in the native stats package.  The default is to use Welch’s t-test, which doesn’t require equal variance between groups.  Conveniently the output includes the mean of each sample, a confidence interval for the difference in means, and a p-value for the t-test.

We will use histograms with imposed normal curves to confirm data are approximately normal.

Input = ("
Instructor       Student  Sodium
'Brendon Small'  a        1200
'Brendon Small'  b        1400
'Brendon Small'  c        1350
'Brendon Small'  d         950
'Brendon Small'  e        1400
'Brendon Small'  f        1150
'Brendon Small'  g        1300
'Brendon Small'  h        1325
'Brendon Small'  i        1425
'Brendon Small'  j        1500
'Brendon Small'  k        1250
'Brendon Small'  l        1150
'Brendon Small'  m         950
'Brendon Small'  n        1150
'Brendon Small'  o        1600
'Brendon Small'  p        1300
'Brendon Small'  q        1050
'Brendon Small'  r        1300
'Brendon Small'  s        1700
'Brendon Small'  t        1300
'Coach McGuirk'  u        1100
'Coach McGuirk'  v        1200
'Coach McGuirk'  w        1250
'Coach McGuirk'  x        1050
'Coach McGuirk'  y        1200
'Coach McGuirk'  z        1250
'Coach McGuirk'  aa       1350
'Coach McGuirk'  ab       1350
'Coach McGuirk'  ac       1325
'Coach McGuirk'  ae       1225
'Coach McGuirk'  af       1125
'Coach McGuirk'  ag       1000
'Coach McGuirk'  ah       1125
'Coach McGuirk'  ai       1400
'Coach McGuirk'  aj       1200
'Coach McGuirk'  ak       1150
'Coach McGuirk'  al       1400
'Coach McGuirk'  am       1500
'Coach McGuirk'  an       1200
")

###  Check the data frame

library(psych)

str(Data)

summary(Data)

### Remove unnecessary objects

rm(Input)

#### Summarize data by group

library(FSA)

Summarize(Sodium ~ Instructor,
data=Data,
digits=3)

Instructor  n nvalid    mean      sd  min   Q1 median   Q3  max percZero
1 Brendon Small 20     20 1287.50 193.734  950 1150   1300 1400 1700        0
2 Coach McGuirk 20     20 1246.25 142.412 1000 1144   1212 1350 1525        0

#### Histograms for data by group

Histograms of each group could be examined.

The right = FALSE option is used with the McGuirk data to improve the appearance of the plot in this particular case.

Brendon = Data\$Sodium[Data\$Instructor == "Brendon Small"]

McGuirk = Data\$Sodium[Data\$Instructor == "Coach McGuirk"]

library(rcompanion)

plotNormalHistogram(Brendon)

plotNormalHistogram(McGuirk,
right = FALSE)

The lattice package could also be used, but adding normal curves to histograms by groups requires some extra code.

library(lattice)

histogram(~ Sodium | Instructor,
data   = Data,
type   = "density",
layout = c(1,2),           ###  columns and rows of individual plots

panel=function(x, ...) {
panel.histogram(x, ...)

panel.mathdensity(dmath = dnorm,
col   = "blue",
lwd   = 2,
args  = list(mean=mean(x),
sd=sd(x)), ...)})

#### Box plots for data by group

boxplot(Sodium ~ Instructor,
data = Data)

#### Two-sample unpaired t-test

t.test(Sodium ~ Instructor,
data = Data)

Welch Two Sample t-test

data:  Sodium by Instructor
t = 0.76722, df = 34.893, p-value = 0.4481

alternative hypothesis: true difference in means is not equal to 0

95 percent confidence interval:
-67.91132 150.41132

sample estimates:
mean in group Brandon Small mean in group Coach McGuirk
1287.50                     1246.25

### Effect size

Cohen’s d can be used as an effect size statistic for a two-sample t-test.  It is calculated as the difference between the means of each group, all divided by the pooled standard deviation of the data.

It ranges from 0 to infinity, with 0 indicating no effect where the means are equal.  In some versions, Cohen’s d can be positive or negative depending on which mean is greater.

A Cohen’s d of 0.5 suggests that the means differ by one-half the standard deviation of the data.  A Cohen’s d of 1.0 suggests that the means differ by one standard deviation of the data.

#### Interpretation of Cohen’s d

Interpretation of effect sizes necessarily varies by discipline and the expectations of the experiment, but for behavioral studies, the guidelines proposed by Cohen (1988) are sometimes followed.  They should not be considered universal.

 Small Medium Large Cohen’s d 0.2 – < 0.5 0.5 – < 0.8 ≥ 0.8

____________________________

Source: Cohen (1988).

#### Cohen’s d for two-sample t-test

The grammar in the cohensD function in the lsr package follows that of the t.test function.  Note that this function reports the value as a positive number.

library(lsr)

cohensD(Sodium ~ Instructor,
data = Data)

[1] 0.2426174

“Student's t–test for two samples” in McDonald, J.H. 2014. Handbook of Biological Statistics. www.biostathandbook.com/twosamplettest.html.

### References

“Student’s t–test for Two Samples” in Mangiafico, S.S. 2015a. An R Companion for the Handbook of Biological Statistics, version 1.09. rcompanion.org/rcompanion/d_02.html.

“Mann–Whitney and Two-sample Permutation Test” in Mangiafico, S.S. 2015b. An R Companion for the Handbook of Biological Statistics, version 1.09. rcompanion.org/rcompanion/d_02a.html.

### Exercises P

1. Considering Brendon and McGuirk’s data,

a.  What was the mean sodium intake for each class?

b.  Are the data distributions for each sample reasonably normal?

c.  Was the mean sodium intake significantly different between classes?

d.  What do you conclude practically?  Include a description of the difference between the means of the data. If they’re different, which is higher? Include effect size, any other relevant summary statistics, and your practical conclusions.

2.  As part of a professional skills program, a 4-H club tests its members for typing proficiency.  Dr. Katz and Laura want to compare their students’ mean typing speed between their classes.

Instructor                             Student  Words.per.minute
'Dr. Katz Professional Therapist'      a        35
'Dr. Katz Professional Therapist'      b        50
'Dr. Katz Professional Therapist'      c        55
'Dr. Katz Professional Therapist'      d        60
'Dr. Katz Professional Therapist'      e        65
'Dr. Katz Professional Therapist'      f        60
'Dr. Katz Professional Therapist'      g        70
'Dr. Katz Professional Therapist'      h        55
'Dr. Katz Professional Therapist'      i        45
'Dr. Katz Professional Therapist'      j        55
'Dr. Katz Professional Therapist'      k        60
'Dr. Katz Professional Therapist'      l        45
'Dr. Katz Professional Therapist'      m        65
'Dr. Katz Professional Therapist'      n        55
'Dr. Katz Professional Therapist'      o        50
'Dr. Katz Professional Therapist'      p        60
'Laura the Receptionist'               q        55
'Laura the Receptionist'               r        60
'Laura the Receptionist'               s        75
'Laura the Receptionist'               t        65
'Laura the Receptionist'               u        60
'Laura the Receptionist'               v        70
'Laura the Receptionist'               w        75
'Laura the Receptionist'               x        70
'Laura the Receptionist'               y        65
'Laura the Receptionist'               z        72
'Laura the Receptionist'               aa       73
'Laura the Receptionist'               ab       65
'Laura the Receptionist'               ac       80
'Laura the Receptionist'               ae       55
'Laura the Receptionist'               af       70

For each of the following, answer the question, and show the output from the analyses you used to answer the question.

a.  What was the mean typing speed for each class?

b.  Are the data distributions for each sample reasonably normal?

c.  Was the mean typing speed significantly different between the classes?

d.  What do you conclude practically?  Include a description of the difference between the means of the data. If they’re different, which is higher? Include effect size, any other relevant summary statistics, and your practical conclusions.