Day 2–Population parameters and sampling

We will ignore everything above this

Before starting the activity

• Before beginning the class activity we talked about the big picture of statistics.
  • We start with some research question that describes our population. For example:
    • what proportion of people think a hotdog is a sandwich?
    • by how much does a new medication reduce average blood pressure?
    • which car model has better safety features on average?
  • Often there is a particular feature from the population we want to know about, this is called the population parameter
  • describing a population or sample is called descriptive statistics
  • Since getting information about an entire population is typically impossible, we need to sample the population.
    • samples need to be representative of the population
    • sampling is a difficult process
    • we will usually assume a simple random sample, you will likely encounter field specific methods in your future
  • Our goal, then, is to describe the sample and somehow measure how good it is at describing the population. This is called inferrential statistics

1. In the space below create an R code chunk that saves the value 15 to a variable called b.

b <- 15

2. Create a new code chunk below and type code that will calculate b to the 10th power.

b^10

## [1] 576650390625

3. Now review the code chunk below. It lists the calories for the meals I ate yesterday and then adds up my calories for the day. In the empty code chunk write code that will save a list called scores with the values 25,65,33 and find the sum of those values.

calories <- c(550,920,1000)
sum(calories)

## [1] 2470

# Delete this comment and write code that creates a list of scores: 25,65,33 and finds the sum of that list
scores <- c(25,65,33)
sum(scores)

## [1] 123

4. Create two lists of numbers of the same size. Try adding the two lists, explain what is happening in the output. Try multiplying lists also. What happens if you try this but the lists aren’t the same size?

list1 <- c(6,3,2,1)
list2 <- c(0,3,1,2)
list3 <- c(1,2,4)
list4 <- c(5,8)

list1+list2

## [1] 6 6 3 3

# this adds each piece of the lists together to make a new list

list1*list2

## [1] 0 9 2 2

# this multiplies each piece of the lists together to make a new list

list1+list3

## Warning in list1 + list3: longer object length is not a multiple of shorter
## object length

## [1] 7 5 6 2

# this provides an error because they are not the correct length

list1+list4

## [1] 11 11  7  9

# even though the lists are not the same size, list1 is exactly double the size of list 4. So, R just repeats list4 twice (so that it is now the same length of list1) and adds it to list1

5. Type mpg into the console below. Describe the output.

The console is the pane below this pane. We are currently in the workspace, the pane below this is where coding happens. So, type mpg down there. It will output a large data set about cars

6. You can’t see all of the output from the previous line of code and the data is not in your environment. To add the data to your environment, save mpg to some variable name, just like you did with 15 in problem 1

car_data <- mpg

7. Click on the new thing in your environment which has the mpg data, describe what happens

This opens up a data set in the R workspace that looks way nicer and allows you to scroll around to explore.