Project 2 Reflection
In this project, I am using R studio to analyse the data. Since the secondary data is used, I don’t have to prepare questionnaire and collect. In order to conduct the survey, the data analysis process must be undergone. Firstly, we have to understand what the types of data are and test them using different kind of analysis. The suitable variables is filtered and chose so that some errors will be prevented else we can provide a more accurate testing. For example, the chi-square test of independence and goodness of fit test are used in the nominal data. The 2 sample mean test is used in the ratio data. Pearson‘s Product–Moment correlation coefficient is used in ratio or interval data while Spearman’s Rho Rank is used in ordinal data. Regression is done as well to test the causal effect between 2 variables. I do all this tests is to know that whether students’ background and their attitudes will affects their Mathematics grades.
I face some problems in this project 2. Firstly, I have to really spend time to think of what are the suitable variables to be used and pick some of the variables from the data set. At the same time, what kind of testing should be done with these variables. As we know, we have to come up with conclusion after doing the hypothesis testing. I am poor in this section because I am not good in describing and I have to think hard what to describe after we get the conclusion. A good description will make the flow of content looks good. After the report is completed, I have to make a clear presentation about the survey we have carried out. There are a lot of animations and extra small conclusions added in the slides to make the video presentation looks more interesting.
I did learn something from this project. This project 2 is about statistical inference which is concerned with selecting and using a sample to draw inference about population from which sample is drawn. I know how to generalize findings to a large population after doing the inference testing. We can just estimate what to happen in a population by analyzing the sample getting from it. The thing to take note is the sample size must be greater than 30 to have an accurate testing.