This week’s assignment consists of importing, cleaning, and rudimentary analysis of the survey data. The attached data set contains the modified survey results of 5 classes. Your class is indicated by Class=5.
For R script project:
1. For this project, create 2 documents. Mark this week’s entry under a subheading “Week 2” within each document.
a. “R Script.R” – contains the R scripts associated with this work
b. “R Outputs.docx” – contains the outputs or the results
2. Import the file into R using read.csv( ) function
3. Prepare data.frame for analysis. Arrange variables (rename, drop, or keep variables), clean data (gsub or conditional assignments with ifelse() ), and apply appropriate data structure (i.e. integer, numerical, character, factors, etc.)
4. Prepare and export at least several frequency tables, cross-tabulations, and several histograms (preferrably clean and with color, with appropriate titles and axis labels, etc.). You may want to look into table( ), ftable( ), gmodles::CrossTable, hist( ), ggplot2, and plotly, among others. Question: How do you show and compare the results across mulitple classes?
For Quiz:
Calculate confidence intervals for the quiz. How do you calculate cumulative t-distribtuion with qt( ) and F-distrubtion with qf( )? See the following:
Use the class survey data and produce the following outputs. Provide the R codes in the R-script file under the sub-heading “Week 3”, and the statistical outputs under the sub-heading “Week 3” in the Word file. In general, your statistical outputs should be titled and labeled so that they can stand on their own (and can be understood by anyone who looks at them for the first time).
1. Produce several descriptive statistics tables (i.e. mean, SD, min, max, and N) for the entire sample, and by group (for example, by the class=1 to 4). You may use psych::describe( ) or other commands of your choice. What is a three-line table format that is commonly used in white papers? Provide several interpretive sentences with your table outputs.
2. Conduct one-sample t-test that the average survey responses were equal, greater than, or less than 3 for one of questions 5-9 using t.test( ). You may also use t.test( ) to conduct two-sample t-test. Provide the null and the alternative hypothesis for each test. Provide the test results and several sentences interpreting the results.
3. Use img( ) and par( ), and abline( ) with various plot making commands to produce scatter chart, jitter chart, and boxplot chart. When do you use jitter chart? How can you use boxplots to detect outliers? Export the charts to the Word document and provide several interpretative sentences of your findings.