Choose one of David Robinson’s tidytuesday screencasts, watch the video, and summarise. https://www.youtube.com/channel/UCeiiqmVK07qhY-wvg3IZiZQ
The title of the screencast is: Analyzing Simpsons guest stars and dialogue in R.
The screencast was made on August 30,2019
Hint: What’s the source of the data; what does the row represent; how many observations?; what are the variables; and what do they mean?
The source of the data is mtcars from the EPA. The row represents big EPA cars which are bigger cars that use a lot of fuel in our environment. It was much bigger than mtcars. The columns shows numerous amounts of information about the cars like the drive, displacement of the volume, engine ID, FE score, fuel type, etc. There are 41,804 observations in this specific data set which like I said, is bigger than mtcars. The variables he uses in this data set to help him prove his hypothesis was using city08, highway08, make, model, cyinders, displacement, drive, engineID, and enginediscription. All of these variables are the best way to see how fuel efficiency has improved.
Hint: For example, importing data, understanding the data, data exploration, etc.
When Dave approached the data he started with importing the data. to get the full data dictionary we went to fueleconomy.gov. At first he had a tough time understanding the data because it was in alphabetical order and on R it wasnt. However, Dave chose to convert the data in R to alphabetical order. After he put them into alphabetical order it was easier for him to decide which data parts he was going to use. Which ones were significant, which ones weren’t. Doing all of this helped him understand and explore the data easier. Also, he showed how adding more and more degrees of freedom show a change in the shape of the line that were predicting. It helps adjust to the data a little bit more and how that affected the adjusted Rsquared. Dave did a really good job going through the data making it easier for not only himself but the viewers as well.
Right away David started his video and coding just as if we would start class. He started with Librarytidyverse and then onto the ggplot theme of the code. After that saved it under a specific title and then read in the data set. immidietely I felt like I was in class and ready to learn about car fuel efficiency. Also, he looked a lot of things up that he did not know which is what we have to do in class whether it’s going to the textbook for codes or to yahoofinance for abbriviations. I thought it was ony us who had to do that because we don’t know much but everyone does it even if you know how to use R or not. I really liked how Dave set up and taught this topic.
After creating the hypothesis and going through the data set and picking out which variables would be important, Dave finally found a mojor key factor in the anaylsis. Because a lot of cars switched to electric engines and engine sizes started to shrink early 2009, there was a major increase in fuel efficiency from 2009 to 2013-2014 across a couple differnt types of cars.
One thing that really caught my attention in the video was quickly learning about augment. Augment is used in to add extra varibale into the data set, or at least for this data set. It was basically saying that we have the original data as well as the fitted values and the residuals which are really important in this data set. Another thing I really liked about the analysis was how in depth he got into things. There were times he didn’t even know what some things were but he always explained why he was either not using it or why it is not significant to the data set. It made it much more helpful when following along with the video and understanding the data. Overall it was a very good video that was jammed pack with information about car fuel efficieny in R.