# 1/20/2023

## Methods of Collecting Data

• Census
• Sample
• Experiment
• Observational Study
• Anecdotal Evidence

## The Idea Behind Sampling

• parameters versus statistics

## Exploration with RStudio

• Open ClassDataS23.R in our Google Drive folder !Class-csv-Rscripts and run the commands on your laptop
• I will come around and help you with individual questions, but please work together to get comfortable with RStudio. You can also search on Google (or your favorite search engine) for lots of other examples to get started with R.

## Suggested In Class Exercises (Time to explore R on your own or with a partner.)

Note: A new file has been added to our !Class-csv-Rscripts folder. Please use ClassDataS23_Updated for the in class exercises today. The files are set up the same way, but the updated file contains data for more students.

1. Construct appropriate graphs to visually summarize the information collected on the class data survey for the following variables:
• Year
• Height
• Handedness
• Age
• HometownSize
• PulseRate
• TextMessages
• Varsity
• CatsDogs
• ExerciseMinutes
• FootLength
2. Use appropriate graphical displays and descriptive statistics to make appropriate comparisons between cat and dog lovers for different variables in the data set we collected during the first class.
3. Use appropriate graphical displays and descriptive statistics to make appropriate comparisons between the class years for different variables in the data set we collected during the first class.
4. Is the shape of the distribution for guesses of the length of the black string the same as the distribution of guesses for the length of the white string?
5. The actual length of the white sting is 46". Is the overall distribution of guesses centered at this value?
6. The actual length of the black string is 48". Is the overall distribution of guesses centered at the appropriate value?
7. (Do this exercise "by hand," not with R.) Caution is necessary when constructing histograms from frequency distributions given in magazines, newspapers, journal articles, etc.  The authors of "Self-Reports of Academic Performance," an article which appeared in Soc. Methods and Research (1981), studied the difference in GPA, reported - actual, for each of the students in a sample.  Specify the height of each bar in a correct histogram for the frequency distribution below and sketch the histogram.

Frequency distribution for errors in reported GPA

 Class Interval Relative Frequency Height [-2.0, -0.4) .023 [-0.4, -0.2) .055 [-0.2, -0.1) .097 [-0.1,  0.0) .210 [ 0.0,  0.1) .189 [ 0.1,  0.2) .139 [ 0.2,  0.4) .116 [ 0.4,  2.0) .171