lecture 4 - data types, collection, management and exploratory data analysis

Question 1

numeric discrete data -

Answer 1

numbers are regularly gapped

Question 2

numerical continuous data

Answer 2

numbers can take any value in a continuum

Question 3

categorical nominal data

Answer 3

categories are arbitrary and can be recorded

Question 4

categorical ordinal

Answer 4

the order of the categories are important

Question 5

what is the goal of explatory data analysis

Answer 5

describe dats numerically and visualise it graphically

Question 6

what are the things used to describe data

Answer 6

1. centre - bulk of the data
2. spread - consistency of data
3. shape - symmetrical or skewed

Question 7

what is the goal of summary statistics

Answer 7

convey as much information about the data in as few numbers as possible

Question 8

median

Answer 8

midpoint of the data

Question 9

what are the measurements of spread?

Answer 9

1. percentiles, range and interquartile range
2. variance and standard deviation

Question 10

pth percentile

Answer 10

value at which p% of the data is less than or equal to

Question 11

Q1

Answer 11

25th percentile

Question 12

Q2

Answer 12

50th percentile

Question 13

Q3

Answer 13

75th percentile

Question 14

what does a 5 number summary contain

Answer 14

min, Q1, median, Q3, max

Question 15

variance

Answer 15

measure of the amount the data is spread around the mean

Question 16

sample standard deviation

Answer 16

positive square root of the sample variance

Question 17

what are the 2 measures of shape of the data

Answer 17

1. skewness - symmetry of the data
2. kurtosis - peakedness or tailedness of the data

Question 18

probability

Answer 18

the likelihood of an event occurring

Question 19

discrete probability distribution

Answer 19

model discrete data

Question 20

continuous probability distribution

Answer 20

to model continuous data

Question 21

examples of discrete probability distribution

Answer 21

Bernoulli distribution, binominal distribution, negative binomial distribution

Question 22

examples of continuous distribution

Answer 22

normal distribution, gamma distribution

Question 23

why are normal distribution curves important

Answer 23

1. a lot of random variables do follow a normal distribution
2. a lot of random variables can be approximated as following a normal distribution
3. the normal distribution has a special property that makes it very useful