W2: Intro to R and RStudio

Question 1

< OR %1%

Answer 1

Less than

Question 2

<= OR %le%

Answer 2

less than or equal

Question 3

%gl%

Answer 3

greater than AND less than

Question 4

%gel%

Answer 4

greater than or equal AND less than

Question 5

%gle%

Answer 5

greater than AND less than or equal

Question 6

%gele%

Answer 6

greater than or equal AND less than or equal

Question 7

%!in% OR %nin%

Answer 7

not in

Question 8

.N

Answer 8

all sample size

Question 9

d[UserID ! = 56 & NA <= 4]

Answer 9

Exclude ID 56, select observation with NA at or below 4

Question 10

What are the 4 data types using class()?

Answer 10

Logical, integer, numeric, character

Question 11

What is logical data?

Answer 11

True (1) or False (0)

Question 12

What is integer type data?

Answer 12

Whole numbers (pos / neg) e.g -1,0,1,2

Question 13

What is numeric type data?

Answer 13

Real numbers (whole, decimals, fractions)

Question 14

What is character data?

Answer 14

Text data, including numbers stored as strings

Question 15

What does this represent D [ i, j, by] ?

Answer 15

i = rows, j = columns, by = grouping variable

Question 16

%Y - %m - %d

Answer 16

4 digit 2019 - 03 - 12

Question 17

%d / %m / %y

Answer 17

12 / 03 / 19 (2 digit)

Question 18

%Y - %b - %d

Answer 18

2019 - Mar - 12

Question 19

What does using factor() need?

Answer 19

levels = c(1, 0, 2) and
labels = c(“dog”, “cat”, rabbit”)

Question 20

Name the join and argument used for:
Data with only rows present in both x and y

Answer 20

Natural Join, all = FALSE

Question 21

Name the join and argument used for:
Data with all rows in x and y

Answer 21

Full Outer Join, all = TRUE

Question 22

Name the join and argument used for:
Data with all rows in x

Answer 22

Left Outer Join, all.x = TRUE

Question 23

Name the join and argument used for:
Data with all rows in y

Answer 23

Right Outer Join, all.y = TRUE

Question 24

Which join / merge will have most rows?

Answer 24

Full Outer Join

Question 25

What do you need to check for before merging if grouping by ID?

Answer 25

If there are duplicates

Question 26

What does anyDuplicated( ) do?

Answer 26

Returns the position of duplicated data or 0 if no duplicates

Question 27

What does unique(x) %in% unique(y) do?

Answer 27

Checks how many IDs from dataset x is in dataset y

Question 28

When is it necessary to reshape data to long format?

Answer 28

For RM / longitudinal / panel data

Question 29

What arguments are required when using reshape() to long format?

Answer 29

IDs will have multiple rows. varying = list( stress = c("stress1", stress2") v.names = "Stress" timevar = "weeks" times = c(0, 6, 24) becomes a variable idvar = "ID" direction = "long"

Question 30

What arguments are required when using reshape() to wide format?

Answer 30

v.names = c ("stress", "happy"), time.var = weeks idvar = "ID" direction = "wide"

Question 31

How do you merge multiple IDs?

Answer 31

by = c("ID", "Time")

Question 32

If data has more extreme large values (upper tail) than extreme small values (lower tail), what kind of skewness is this?

Answer 32

Positively skewed

Question 33

If data has more extreme small values (lower tail) than extreme large values (upper tail), what kind of skewness is this?

Answer 33

Negatively skewed

Question 34

If there is no skewness (normal distribution), what value will the skewness be?

Answer 34

skewness = near 0

Question 35

Skewness of -.93 is positive/negative?

Answer 35

Negative

Question 36

Skewness of .76 is positive/negative?

Answer 36

Positive

Question 37

z-score is also known as ____ score

Answer 37

standard score

Question 38

What is the z-score formula?

Answer 38

z = raw score - mean / SD

Question 39

What are 3 measures of variability?

Answer 39

range, IQ range, SD

Question 40

What is the default origin date and time in R?

Answer 40

1970-01-01 00:00:00

Question 41

What is happening here: as.numeric(d1[1] - d1[2])/365.25

Answer 41

comparison of 2 dates and converted to a number and to years

Question 42

surveys2 <- data.table( ID = c(1, 2, 2, 3), Age = c(19, 18, 18, 20)) acti2 <- data.table( ID = c(2, 2, 3, 4), Sleep = c(8, 7, 6, 7)) How many rows would full outer join have?

Answer 42

7 ## ID Age Sleep ## 1: 1 19 NA ## 2: 2 18 8 ## 3: 2 18 7 ## 4: 2 18 8 ## 5: 2 18 7 ## 6: 3 20 6 ## 7: 4 NA 7