Datasets

• Most often rectangular format
  • Columns: variables
  • Rows: observations
• Example: titanic3 data set; passenger characteristics and survival status after disaster with the Titanic cruise ship

For now, we work with subset of titanic data set:

Data: selections within a single column

• Each column is a vector of values
• Single column from data set selected via “$”, e.g. titanic$age
• Elements of vector selected via numbers within square brackets [ ]

Select age of passengers 6 and 10

Select age of passengers 6 to 10

Flexibility of seq function

Exercise 1

1. Create a vector named vec that consists of the numbers from 11 to 30
2. Select the 7th element of the vector
3. Select all elements except the 15th. Hint: use a minus sign
4. Select the 2nd and 5th element of the vector

5. Select only the odd valued elements of vec.

Remark: Exercise e. is not an easy exercise. We advise you to do this is in two steps. First create a vector index that selects the odd numbers in vec, using the function seq. You may need to consult the help page of seq via help(seq).

Exercise 2

Use the elementary functions /, -, ^ and the function sum to calculate the mean \[\bar{x}=\sum_{i=1}^n x_i/n\] and the standard deviation \[\sqrt{\sum_{i=1}^{n}(x_i-\bar{x})^2/(n-1)}\] of the fare paid by the titanic passengers. Note: \(n=10\).
Verify your answer by using the built-in R functions mean and sd.

Functions (II)

Modes

• Data (variables) come in different types. The most important ones are:
  • numeric:
  • logical: values TRUE and FALSE
  • character:
  • You can change the mode of some data objects

Modes: logical (I)

• TRUE and FALSE can be used for selection

• Logical statements arise from comparing values:

  • Smaller/larger than: <, >, <=, >=
  • Exact equality: ==
  • Not equal to: !=

• Converted to integer if a numeric value is required:

  TRUE equals 1, FALSE equals 0

Modes: logical (II)

We can calculate with logicals. Main operators are:

• &: all must be true “AND”
• |: at least one must be true “OR”
• !: negation “NOT”

Logical statements about fare

Select fares between 10 and 40

Help

• To know more about a function or dataset you can often use help function
• help(mean) gives

Description: Generic function for the (trimmed) arithmetic mean.

Usage: mean(x, …)

Default S3 method:

mean(x, trim = 0, na.rm = FALSE, ...)

Arguments:

x: an R object. Currently there are methods for numeric/logical vectors and date, date-time and time interval objects.

trim:

na.rm: a logical evaluating to ‘TRUE’ or ‘FALSE’ indicating whether NA values should be stripped before the computation proceeds.

Value: If trim is zero (the default), the arithmetic mean of the values in x is computed, as a numeric or complex vector of length one.

Missing data

• Special value: NA (short for “not available”) The function is.na checks for missingness

• Most functions exclude missings by default

  Not always what you want

  • table excludes missings; we can include them via argument useNA="always"

• quantile and mean (and some others) give error if there are missings; specify argument na.rm=TRUE