Statistics

Question 1

what are three reasons you would use the sample instead of the population data?

Answer 1

1. population data is not available
2. population data is available but is so large it would be v difficult to analyse
3. sample data is quicker

Question 2

variance symbol

Answer 2

σ2 
sigma squared

Question 3

discreet vs continuous variable

Answer 3

discreet is countable (amount in bank account), continuous is measureable (time)

e.g. age is a continuous variable because you are 25, and 40 days, and 4 hours, a 3 minutes, and 2 seconds, a 23 picoseconds. You can make age discreet by limiting it to your age in years.

Question 4

variance definition

Answer 4

average of the squared difference from the mean

Question 5

vector (in R)

Answer 5

way to store data

Question 6

parameter

Answer 6

a characteristic of a population

Question 7

statistic

Answer 7

a characteristic of a sample 

vs a parameter which is a character of a population

Question 8

4 levels of measurement

Answer 8

- nominal : categories, not ordered e.g. race 

- ordinal : ordered but differences are meaningless e.g. rank in a race, 1st, 2nd, 3rd

- interval : ordered and differences are meaningful but there is no natural zero e.g. temperature 

- ratio : interval measurements where there is a natural zero e.g. money

Question 9

why do you square every difference from the mean when calculating variance?

Answer 9

to make them all positive numbers 
e.g. if you had a 5 and a -5 they would cancel eachother out, so the variance would 0.