Probability and Statistics Data Analysis

In project 1, my group members and I are conducted a study about the daily average time spent on social media. Our study is focused on the usage of social media among a random sample of respondents. We had collected the data from 125 respondents via Google Form (primary data).

When conducted this study, we show the multiple relationships between respondents and the usage of social media such as daily average time spent (in hour) on social media, the purposes of using social media, respondents’ behaviors (reasons behind these behavior) and their opinions on social media. To compare the data, we must use different types of graphical methods to represent them as well as the data is suitable present by the graph/plot/chart. Besides, we also know that many people are addicted to the social media and most of them prefer to use social media to spend their free time nowadys. They depend on the social media with different purposes.

After conducted this study, we found some weaknesse of our study. Our respondents are mainly students because we share the survey link among our friends. It caused the inaccurate comparison of our data based on frequency. Thus, we should spreading the survey to collect our data from more spreadly occupation area of respondents which may include different level of occupation such as workers, office lady, promoters, bussiness man and housewife.    

After project 1 is finish conducted, I learned how to differentiate and analyze the various form of data such as ordinal, interval and ratio data. I also know how the R-studio works and how to implement the calculation and get the result by using R-studio. R-studio is an efficient application that ease the process of calculation and drawing of the graph, plot and chart.  I learned a lot from the mistakes we made. I believe that realised the self-weaknesses and mistakes and the process of correcting them made people improve.

In project 2, my group members and I are conducted a study about the demography and epidemiology of HIV among adolescents in the world. Our study is focused on comparing and analysing the difference between estimated number of male adolescents living with HIV over female adolescents, the proportion of adolescents living with HIV in different continents and also the relationship between the estimated number of adolescents living with HIV and the number of AIDS deaths among adolescents. These data are come from a website (UNICEF Data - https://data.unicef.org/resources/dataset/gender-and-hiv-data/ ). Thus we use and collect these secondary data in our project 2.

When conducted this study, we learned different methods of parameter estimation from different distributions. Besides, we also know how to using hypothesis testing conduct and analyse our data to estimate mean, proportion, standard deviation and dependency of different types of data. During this project, we faced some difficulties and challenges whcih is we are very confused on decided which hypothesis testing shall we used to analyse our data to get the most precise estimation and conclusion. Moreover, most of the secondary data found on website is come from large organization which consist of large sample size. The large sample size make us easily to do the calculation mistakes because the values of data is too large.

Fortunately, we found the UNICEF data which is consider as a smaller data from large sample size and the data are clearly and easily to understand. R-studio is our chosen application which used to do the calculation of hypothesis testing. It is easy to implement by enter all the data inside and the result will come out as same as the result we calculated manually. From here, I learned how to manually calculate the value of hypothesis testing by using formulas and also know how to implement the calculation by using R-studio.

After project 1 is finish conducted, I learned how to differentiate the types of hypothesis testing and apply the different methods of parameter estimation from different distributions. I also learned how to determine the conclusion after conducted the hypothesis testing. I learned a lot of analytical skills from this project. I learned a lot from this project included the ability to collect and analyze information, solve problems and to make decisions. I believe that these ability will advance me when I meet the complex statistics problems in the future.

In conclusion, the HIV and AIDS issues should more concerned by the public users especially the adolescents which is occupied a large size in our study. From this study, we realised that people as young as adolescents are already infected with HIV. There are a lot of deaths are caused by AIDS because it made people infected with HIV. It shows a relationship between the number of people infected with HIV and the number of deaths caused by AIDS. We must aware with this issue and government should do more inventions to protect the people and adolescents from being infect by HIV.