YEAR 11 MATHEMATICS TASK 02

Topic: Social Media usage habits of teenagers

Aim: To Investigate the Social Media Habits of Teenage Boys in Y11

in Amity College

By: Rain Win & Muhammad Rasheed

Year: 11
Part 2 - Designing survey questionnaire
1. Do you enjoy using social media? Yes/No

2. How many hours do you spend on Social Media per day? 0-24 hours

3. Which social media platform do you use the most? TikTok, Snapchat, Instagram,

YouTube, Facebook, Other

Considerations:

2a - How did you minimise bias in your question design?

In order to reduce bias in the given set of questions, students are given an additional

option of “Other” in the question “Which social media platform do you use the most?” to

avoid forcing the student to answer a given option thus avoiding bias. Students were

given the option to provide any hour ranging from 0-24 hours within the day in the

question “How many hours do you spend on Social Media per day?” to capture the

students honest social media usage rather than forcing them to a reasonable hour

based on the researcher’s preferences. Questions are also worded to avoid a biassed

tone such as “Don’t you think that you should use social media for … hours as a student

per day?”. Therefore, these factors were considered in designing the questions to

minimise bias.
Part 3 - Sampling
(a) Select your sample using any sampling method

The sampling method chosen for this investigation is Simple Random Sampling through

Google Forms.

(b) Justify your choice of the sampling method selected. Explain what this sampling method

is.

Simple random sampling is a method where a random group of people are selected from a larger

population. Each person from the larger population has an equal chance of being selected thus

avoiding selection bias. The random selection process allows for unbiased approximation of

trends in a large population through responses from the chosen population thus providing a

valid statistical inference. Through this method, random students within Year 11 boys are sent a

Google Form (Image provided) which consists of relevant categorical and numerical questions.

The simplicity of google forms engages the students to participate in the survey which avoids

non-response bias. This method also allows for easier implementation of the responses without

the need of complex calculations. Simple random sampling avoids the need for prior knowledge

about the population easing the process of collecting data. Within google forms, the responses

are anonymous which avoids researcher bias further strengthening the validity and reliability of

the sampling method. Therefore, simple random sampling through Google Forms is an effective

method in collecting responses from students while avoiding various types of bias which allows

for an unbiased representation of the social media usage habits within the Year 11 population

through a randomly selected subset.

(c) What was your sample size? Why did you choose this sample size?

The chosen sample size is 15 students from the larger sample of 76 male students in Year 11.

This chosen sample justified as √(76) results in ~9 students thus being within the minimum

sample population. A small sample size of 15 allows for easier management within a limited

time. This includes a higher accuracy within results, control of bias and minimising error. A

smaller sample size also allows for a faster rate of data collection . A smaller sample size

results in higher participation and lower dropout rate which rids of non-response bias.

Considerations:
3a - Did you have any limitations in selecting your sample?

Disadvantages of simple random sampling includes difficulty in receiving responses from the

general population of Year 11 as students are randomly selected. Gathering a list of responses

from a randomly selected sample can be time consuming as students may choose to ignore the

sample. Despite its ability to provide an unbiased representation of the trend, a small sample

may not be enough to represent the trend of social media usage within the Year 11 boys thus

limiting the accuracy of the representation, creating a disadvantage.

3b - How did you minimise bias in your sampling?

Bias in the sample was minimised as 15 students in the grade were randomly selected and were

sent a Google Form, avoiding selection bias. Responses are all anonymous which encourages

honest responses thus reducing social desirability bias. Questions are also asked in a clear and

forward manner avoiding a leading tone, such as “Don’t you think?”. The option “Other” and

ability to put any number within 0-24 hours avoids bias as students are able to express

unbiased responses.
3c - How did you collect your data? Provide evidence, such as photos or screenshots.
Part 4 - Tabulate the data
Q1: Do you enjoy using social media?

Data Frequency Cumulative Percentage (%) Cumulative

Frequency Frequency (%)

Yes 13 13 86.7 86.7

No 2 15 13.3 100

Q2: How many hours do you spend on social media per day?

Hours Frequency Cumulative Percentage (%) Cumulative

Frequency Frequency (%)

0 0 0 0 0

1 0 0 0 0

2 3 3 20 20

3 4 7 26.7 46.7

4 4 11 26.7 73.3

5 3 14 20 93.3

6 1 15 6.7 100

6+ 0 15 0 100
Q3: Which social media platform do you use the most?

Data Frequency Cumulative Percentage (%) Cumulative

Frequency Frequency (%)

Tiktok 6 6 40 40

Snapchat 3 9 20 60

Instagram 2 11 13.3 73.3

YouTube 2 13 13.3 83.7

Facebook 1 14 6.7 93.3

Other 1 15 6.7 100

Considerations:

4a - Did you group your data? Explain.

Yes we did group our data. In question 1 we grouped our data into two categories which were

“yes” and “no”. For question 2 we grouped our data into discrete hourly categories which

ranged from 0-6+ hours. This grouping helps us clearly visualise the distribution of time spent

on social media. Lastly in question 3 we grouped the responses by different social media

platforms. This helps us identify the most popular social media platform amongst the users

surveyed.

4b - Were there any challenges in tabulating your results? Explain.

We faced various challenges when it came to tabulating our results. For example ensuring that

all responses are correctly counted and categorised especially when tabulating the responses.

Another challenge would be deciding on categories. For example in Q3 deciding which social

media platforms to list and which would be “other” was challenging. It is important to capture all

relevant platforms which respondents use without adding too many options to the table.
Part 5 - Graphical representation
Q1: Do you enjoy using social media?

Q2: How many hours do you spend on social media per day?
Q3: Which social media platform do you spend the most hours on?

Considerations:

5a - Is there bias in your graphical representation?

There is some level of bias as we have only collected the data of year 11 boys in amity

college. Our graphs only show the data which was collected from year 11 boys from amity

college. We could have asked a more broad audience ,for example all ages or boys and

girls, in order for our data and our graphical representation to be unbiased.

5b - How did you avoid bias in representing your data?

In order to avoid bias we collected our data from random year 11 students. As shown

above we put all the names in a random wheel and from there we randomly chose

people to survey. Due to the randomised selection of year 11 students we were able to

manage avoiding bias in the representation of our data.

Part 6 - Data analysis
Note: Question 1 and 3 are unable to be calculated as they are categorical questions

Chosen Question: How many hours do you spend on social media per day?

(a) Calculate the measures of central tendency (mean, median, mode). Show any

working out.
(b) Calculate the measures of spread (range, interquartile range, standard

deviation). Show any working out.

(c) Draw a box-plot of the measures of spread.

Considerations:

6a - Were you able to calculate measures of central tendency and measures of

spread for each data set? Explain.

Numerical datasets are often described through central tendency (mean, mode, median)

to identify the centre of the dataset and through spread indicators (Range, IQR,

Standard deviation) to determine the variability and distribution of the dataset. We

were unable to calculate the measures of central tendency and spread for questions 1

and 3 as they contain categorical variables which cannot be used to calculate the

central tendency and spread as they require numerical values. However, we were able to

calculate both measures of central tendency and spread for our numerical dataset with

the question “How many hours do you spend on social media per day?” as the x

variables are numerical. Through this, we were able to calculate the central tendencies

with the mean being 4 hours, the median being 4 hours and the modes being 3 and 4

hours. The measures of spread were also able to be calculated with the range being 3

hours, the IQR being 2 and a Standard Deviation of 1.23 (2 d.p).

Part 7 - Conclusion
Write a detailed report that provides a clear and concise summary of your

investigation.

(b) From your investigation, what conclusions can you make about your selected

topic? (Draw upon your analysis in Part 6 to answer this question).

In conclusion, the survey on the social media usage habits within a selected group of Year 11

teenage boys in Amity College provides trends that evaluate upon their preferences allowing

predictions/reasonings for their academic ability. We have collected data on whether

students enjoy using social media, daily usage of social media in hours and which social

media platform is most used. The survey was randomly distributed using simple random

sampling through Google Forms where we concluded that 86.7% of respondents enjoy social

media. We found the mean social media usage per day and the median were both 4 hours.

This dataset is a bimodal mode with a mode of 3 and 4 hours. We also found that 40% of

students indicated TikTok as their most used platform. The low standard deviation of 1.23

indicates that most students’ usage hours per day are relative to the mean of 4 hours. The

IQR of 2 implies that most students are consistent, ranging from 3-5 hours.

(c) Discuss any bias or limitations in your results by focusing on the

“considerations” listed in each part.

We have identified several limitations/biases in this investigation. Despite using Simple

Random Sampling, a sample size of 15 students may not accurately represent the entire Y11

population. Response bias may have occurred as hours were depicted to be answered as

discrete values, thus limiting the accuracy of the student’s response. The investigation’s

focus on specifically Year 11 boys at Amity College limits the applicability of the results to a

broader population, including age groups and genders which could provide a more accurate

understanding of teenage social media habits.

(d) What recommendations can you make to teenagers based on your investigation?
Based on our findings, we would recommend students to spend less time on social media as

the mode hours of social media usage per day was around 3 or 4 hours. We recommended

students to replace social media usage hours with tasks such as studying or sports which

enhances productivity of a Year 11 student. Another recommendation is for social media to

be utilised as an educational tool rather than only a source of entertainment. Our data

concludes that 60% of respondents spend their time on TikTok and Snapchat implying that

social media is not used for beneficial purposes. Therefore, we recommend teenagers to

replace their hours on social media with beneficial tasks and to utilise the social media for

educational purposes.

(e) What are potential areas of further investigation for your chosen topic?
One potential area of further investigation could be to have a more broad and different

variation of data. For example we could survey different year levels, genders and schools to

provide us with a better understanding of our topic. Another area of further investigation

could be analysing the usage patterns and preferences for different social media platforms

in more detail. This could help us understand what tends to keep teenagers engaged in

social media. By implementing these potential areas of further investigation these further

studies contribute to better informed recommendations.