THE EFFECT OF COFFEE ON FACULTY OF ENGINEERING UNIVERSITAS

INDONESIA STUDENTS SLEEPING HOUR

Name1, Name2,
1
Department of Industrial Engineering, Universitas Indonesia.
2
Department of Chemical Engineering, Universitas Indonesia.

ABSTRACT
Coffee is one of the most popular drink and is drank by majority of the world. Coffee
contain caffeine that works by blocking the brain's ability to absorb adenosine, which slows down
nerve activity, which causes the human body to become drowsy. In other word, coffee can help
us to stay awake. The amount of activity that college students have during the day compelled
them to use their sleeping hour to finish their assignments. In order to help them to stay awake
and focus during the night, they consume coffee. This research presents the use of hypothesis
testing to prove whether the sleeping hour of college students of Faculty of Engineering
Universitas Indonesia are affected by the consumption of coffee. The statistical analysis methods
used were Ryan-Joiner normality test, F-test, and two sample with equal variances hypothesis
testing with the average of the college students normal sleeping hour is the same as the average
of their sleeping hour after consuming coffee as the null hypothesis and the average of the college
students normal sleeping hour is greater than the average of their sleeping hour after consuming
coffee as the alternative hypothesis. The result indicated that the average of normal sleeping hour
is greater than the average of the sleeping hour after consuming coffee, means that the alternative
hypothesis is accepted.

Keywords : Coffee; College students; Hypothesis testing; Sleeping hour

1. INTRODUCTION
Coffee is one of the most commonly consumed beverages in our everyday life. Coffee has
attracted a huge body of research in that it is a complex blend of bioactive compounds, exerting
different physiological effects. These recent studies report the beneficial properties of moderate
doses of coffee (3-4 cups per day) on alertness, vigilance, and cognitive abilities. On the other
hand, coffee can disturb sleep and generate anxiety. Its lifelong consumption slows down normal
cognitive aging and reduces the risk of developing Parkinson’s or Alzheimer’s disease, type 2
diabetes and numerous cancers (cancers of the digestive tract, breast, endometrial and skin cancer
in particular). Caffeine is a widely consumed stimulant that is found in a variety of commonly
consumed foods and beverages such as chocolate, soft drink (soda), tea, and coffee. Caffeine is
commonly used as a fatigue countermeasure. Due to its action on adenosine receptors caffeine
improves alertness. Therefore, it is important to examine the impact caffeine has on our sleep to
make more informed recommendations on consumption and to better understand the impact in
roles where caffeine consumption is higher.

The effect of caffeine on sleep in university and general populations has been examined
by several cross-sectional surveys and/or field studies. In these studies, increased caffeine
consumption has been associated with decreased total sleep time, increased naps, decreased time
in bed, increased sleep efficiency due to decreased time in bed, daytime sleepiness, and poor
subjective sleep quality. Additionally, it was not always clear what question was asked to calculate
coffee consumption, or how the participants recorded their intake. Also, many studies do not
consider caffeine from chocolate or examine the separate sources of caffeine individually. This is
important because different age groups may prefer particular sources of caffeine. Furthermore,
all the previous questionnaire studies rely on an individual knowing what amount of caffeinated
coffee they have intake during the day to increase their productivity rate for collage purposes. This
research also presents the use of hypothesis testing to prove whether the sleeping hour of college
students of Faculty of Engineering Universitas Indonesia are affected by the consumption of
coffee.

We also found that drinking regular caffeinated coffee, compared to decaffeinated coffee,
caused a decrease in the total amount of sleep and quality of sleep, and an increase in the length
of time of sleep induction. The results of our study confirm the widely held belief that coffee
consumption interferes with sleep quantity and quality. In addition, we found that the individuals
who suffer from sleep abnormalities should avoid caffeinated coffee during the evening hours.
Above all that the main purpose of our research is to prove the increase of productivity that had
been experienced by the respondent after consuming coffee. On the other hand, after consuming
caffeine from the coffee the respondent had a decreases amount of sleeping hours and does having
some increases on their focus level.
2. METHODS
2.1 Type of Research
The type of research that will be used in this study is quantitative research. Quantitative
methods emphasize objective measurements and the statistical, mathematical, or
numerical analysis of data collected through polls, questionnaires, and surveys, or by
manipulating pre-existing statistical data using computational techniques. Quantitative research
focuses on gathering numerical data and generalizing it across groups of people or to explain a
particular phenomenon. So, in our project we will examine the phenomenon through observations
in numerical representations and through statistical analysis. Along with questionnaires that will
be given out to respondents for the statistical representation of the findings in the study.

2.2 Sampling Method

The research sampling method that will be used in this study is random sampling to obtain
a more scientific result that could be used to represent the entirety of the population. A simple
random sample is a subset of a statistical population in which each member of the subset has an
equal probability of being chosen. A simple random sample is meant to be an unbiased
representation of a group. It is considered a fair way to select a sample from a larger population,
since every member of the population has an equal chance of getting selected. Our scope of the
survey is Faculty of Engineering of Universitas Indonesia students and we do not specifically
determine our survey target. So, every active Engineering student can be our respondent. From
around 4000 students, 50 will be picked through random sampling. All of the 50 students will
then be the target sources of respondents of the researcher. We designed a survey that consists of
questions that relates to our hypothesis “coffee affects normal sleep time of a college student”.

2.3 Analytical method

After we gathered the survey data, we will process the data by using three statistical
analysis methods. The statistical analysis methods used were;

2.3.1 Ryan-Joiner Normality Test

In statistics, normality tests are used to determine if a data set is well-modeled by
a normal distribution and to compute how likely it is for a random variable underlying the
data set to be normally distributed. Data processing cannot be proceeding before both of
the data is normally distributed. In order to do a hypothesis testing, we should perform a
null hypothesis that have a normal distribution. Minitab provides some common testing
procedures for normality. Ryan-Joiner is chosen as a normality test to conduct the
hypothesis test because it is based on the correlation between the sample data and the data
 one would expect from a normal distribution. To determine whether the data is normally
distributed or not, is from the P-value of the data. If the P-value is greater than 1 (P-value
> 1), the data is considered normally distributed. On the contrary, if the P-value is less
than 1 (P-value < 1), the data cannot be considered normally distributed.
The formula for Ryan-Joiner Normality Test is:

Since the mean of the b values is 0, we can simplify this expression to:

2.3.2 Hypothesis testing

The main objective of this paper is to test whether the sleeping hour of college
students of Faculty of Engineering Universitas Indonesia are affected by the consumption
of coffee. Thus, a hypothesis testing is conducted with the average of the college students
normal sleeping hour is the same as the average of their sleeping hour after consuming
coffee as the null hypothesis and the average of the college students normal sleeping hour
is greater than the average of their sleeping hour after consuming coffee as the alternative
hypothesis. To test the hypothesis, we use sample T-test which uses dependent variable and
independent variable.

We used the two sample hypothesis testing with equal variance, so

The degrees of freedom that will be used in deciding the critical t-value from the
distribution table to be compared with the calculated t-value is,
 If the calculated t-value is outside the critical t-value, we reject the null hypothesis.

2.3.3 F-test
An F-test is any statistical test in which the test statistic has an F-
distribution under the null hypothesis. It is most often used when comparing statistical
models that have been fitted to a data set, in order to identify the model that best fits
the population from which the data were sampled. F-test is conducted to test the
hypothesis that the sample have been taken from population with different variances. The
main objective is to check for difference among sample variance. The test variance used
will precisely compare the standard deviation value. Null Hypothesis (H0) of this
observation is the average of the college students normal sleeping hour is the same as
the average of their sleeping hour after consuming coffee and if the standard deviation
ratio of the two populations equals 1 (σ1 σ2 / = 1), meaning that both populations have
the same standard deviation value. The Alternative Hypothesis (H1) is the average of the
college students normal sleeping hour is greater than the average of their sleeping hour
after consuming coffee and it is the standard deviation ratio of the two populations not
equal to 1 (σ1 σ2 / ≠ 1). Significance level used is 5%. This test is done with Minitab
software.

The formula is:

3. RESULTS AND DISCUSSION
3.1 Result of Normality Test

Figure 3.2 Normality Test

In Normality test using significance level of 0,05, we gain the mean of normal sleep is
6.020 and the sleep after coffee is 4.843. Other than that, the standard deviation for normal
sleep is 1.503 and sleep after coffee is 1.454. Using Ryan-Joiner test in minitab, we found that
our sample data is normal. It is proven by the p-value which is greater than 0.100. As we can
see from the graph, the data distribution is either 3, 5 or 8. This happens because we use the
middle value of the range option in our survey, which are <3, 4-6, and 7-9 hours. Hence, the
data distribution of 3 hours sleeping in the graph shows more occurrences after taking coffee
than before. Furthermore, the data occurrence of 8 hours sleeping is much reduced on the plot.
In conclusion, the data is normal and appropriate to be used in the next calculation.
 3.2 Result of F-test
The F-test is calculated in minitab, the result shows that,

Test and CI for Two Variances: Normal, Coffee

Method Ratio of Standard Deviations

σ₁: standard deviation of Normal Sleep 95% Lower

Bound for
σ₂: standard deviation of Sleep after
Estimated Ratio
Taking Coffee
Ratio using F
Ratio: σ₁/σ₂
0.978337 0.774
F method was used. This method is
accurate for normal data only.
Test
Descriptive Statistics
Null hypothesis H₀: σ₁ / σ₂ = 1
95%

Lower Alternative hypothesis H₁: σ₁ / σ₂ > 1

Bound Significance level α = 0.05

Variable N StDev Variance for σ
Test

Normal 51 1.503 2.260 1.294 Method Statistic DF1 DF2 P-Value

Coffee 51 1.536 2.361 1.322 F 0.96 50 50 0.561

Using F-test, the test result shows that the P-Value is 0.561 with 0.05 significance level. We
can conclude that the variance from both population is equal. Thus, the calculation can be
continued with hypothesis test using Two-sample T-test assuming the variance is equal.
 Figure 3.3 F-Test

3.3 Result of Hypothesis Testing

Data Distribution Data Distribution
Normal Normal
35 Mean 6.020 Mean 4.863
StDev 1.503 30
StDev 1.536
N 51 N 51
30
25

25
20
Frequency
Frequency

20
15
15

10
10

5
5

0 0
3 4 5 6 7 8 9 2 3 4 5 6 7 8

Normal Sleep Sleep after Taking Coffee

Figure 3.4 Two-Sample T-Test Distribution

To test our hypothesis, we used Two T-Test assuming the variance is equal. The
hypothesis test is calculated by minitab software. We got the mean for the normal sleep is 6.02
and the mean for sleep after coffee is 4.82. Standard deviation value for sleep after coffee,
which is 1.54, is greater than standard deviation value for normal sleep, which is 1.50.
In Two-Sample T-Test we got the the critical region is the area which is greater than 0.657.
Meanwhile, the T-Value is 3.84 which is fall in the critical region. The hypothesis test shows
that the mean of normal sleep is greater than the mean of sleep after coffee at the 0.05 level of
significance. Therefore, we reject the null hypothesis and accept the alternative hypothesis. In
addition, the theory that coffee caused a decrease in the total amount of sleep is proven by the
hypothesis test.

Two-Sample T-Test and CI: Normal Sleep, Sleep after Coffee

Method Estimation for Difference

μ₁: mean of Normal Sleep Pooled 95% Lower Bound

Difference StDev for Difference

µ₂: mean of Sleep after Taking Coffee
1.157 1.520 0.657
Difference: μ₁ - µ₂
Equal variances are assumed for this
analysis. Test

Null hypothesis H₀: μ₁ - µ₂ = 0

Descriptive Statistics Alternative hypothesis H₁: μ₁ - µ₂ > 0

Sample N Mean StDev SE Mean T-Value DF

Normal 51 6.02 1.50 0.21 3.84 100

Coffee 51 4.86 1.54 0.22

4. CONCLUSION

The main idea of doing this research is to find the data research of the named research
as “coffee affects normal sleep time of a college student”. Our thesis statement which conclude
that when consuming caffeinated coffee does increases the amount of focus into the consumers.
On the other hand, having a caffeinated coffee intake could decrease normal sleep time of the
consumers by one hour averagely (using compared distribution data mean).

The fact that consuming coffee could affect the focus and decreasing the amount of
normal sleep significantly is sometimes could occurred into health issues if done repeatedly.
Based on the data calculation of our experiment we could also analyze that the effect of
caffeinated coffee could effectively decrease sleep hours by various numbers of hours, starting
from one hour upward. It is proven by the result of hypothesis test which we reject the null
hypothesis and accept the alternative hypothesis.

To conclude, the “coffee affects normal sleep time of a college student” experiment
research is based on the emerging problems of troubling times it takes to sleep by our fellow
FTUI collegian after consuming caffeinated coffee. Coffee intake is importance if we need a
surge of stimulant for our body to do various works, but by knowing the side effects that it
could also decreases hours of sleep and various of health issues if done uncontrollably many
times.

6. REFERENCES

1. A, Nehlig, 2012. Effects physiologiques du café et santé humaine. Une revue. Cah
Agric 21: 197 – 207.
2. Emily J. Watson, Alison M. Coates, Mark Kohler and Siobhan Banks. Caffeine
Consumption and Sleep Quality in Australian Adults. Nutrients 2016, 8, 479.
3. Kassem Sharif, Abdulla Watad, Nicola Luigi Bragazzi, Mohammad Adawi, Howard
Amital, Yehuda Shoenfeld. Coffee and autoimmunity: More than a mere hot beverage!
Autoimmunity Reviews 16 (2017) 712 – 721.
4. Lotan Shilo, Hussam Sabbah, Ruth Hadari, Susy Kovatz, Uzi Weinberg, Sara Dolev,
Yaron Dagan, Louis Shenkman. The effects of coffee consumption on sleep and
melatonin secretion. Sleep Medicine 3 (2012) 271 – 273.
5. http://blog.minitab.com/blog/adventures-in-statistics-2/understanding-analysis-of-
variance-anova-and-the-f-test accessed on 11th December 2017-12-17.
6. http://blog.minitab.com/blog/the-statistical-mentor/anderson-darling-ryan-joiner-or-
kolmogorov-smirnov-which-normality-test-is-the-best accessed on 11th December
2017-12-17.
7. http://blog.minitab.com/blog/understanding-statistics/guidelines-and-how-tos-for-the-
2-sample-t-test accessed on 11th December 2017-12-17.
 ATTACHMENT

Result of the Questionnaires

Sleep Normal Sleep After
Normal
No xi After xi No Sleep xi Coffee xi
Sleep
Coffee
1 7-9 8 4-6 5 27 7-9 8 7-9 8
2 4-6 5 4-6 5 28 4-6 5 4-6 5
3 4-6 5 4-6 5 29 4-6 5 <3 3
4 7-9 8 7-9 8 30 4-6 5 4-6 5
5 7-9 8 7-9 8 31 4-6 5 4-6 5
6 7-9 8 4-6 5 32 4-6 5 4-6 5
7 4-6 5 <3 3 33 4-6 5 <3 3
8 4-6 5 4-6 5 34 7-9 8 7-9 8
9 4-6 5 4-6 5 35 7-9 8 4-6 5
10 7-9 8 4-6 5 36 7-9 8 7-9 8
11 4-6 5 <3 3 37 4-6 5 <3 3
12 4-6 5 <3 3 38 4-6 5 <3 3
13 4-6 5 <3 3 39 7-9 8 4-6 5
14 4-6 5 4-6 5 40 4-6 5 4-6 5
15 4-6 5 4-6 5 41 4-6 5 4-6 5
16 7-9 8 7-9 8 42 4-6 5 4-6 5
17 4-6 5 4-6 4 43 4-6 5 4-6 5
18 4-6 5 <3 3 44 <3 3 <3 3
19 7-9 8 <3 3 45 4-6 5 4-6 5
20 4-6 5 <3 3 46 4-6 5 <3 3
21 7-9 8 7-9 8 47 7-9 8 4-6 5
22 4-6 5 4-6 5 48 7-9 8 4-6 5
23 4-6 5 <3 3 49 4-6 5 4-6 5
24 4-6 5 4-6 5 50 7-9 8 4-6 5
25 4-6 5 4-6 5 51 7-9 8 4-6 5
26 7-9 8 4-6 5