lecture 1 & 2

Question 1

estimates

Answer 1

claims about the population

Question 2

why is statistics important

Answer 2

1. Statistical models also help us draw inferences from huge datasets
2. Uncertainty → inferences always come with some level of uncertainty - statistics allows us to measure this uncertainty
3. Gives tools to process info in a principled manner in order to draw inferences (claims) about the world

Question 3

spurious correlations

Answer 3

occurs when two variables are statistically related but not directly causally related. These two variables falsely appear to be related, normally due to an unseen, third factor.
e.g. eating ice cream increases the chances of being involved in a shark attack
third factor –> being at the beach

Question 4

causes of spurious correlations

Answer 4

1. coincidence
2. confounding variables
3. small sample size
4. overfitting

Question 5

overfitting

Answer 5

occurs when a statistical model fits exactly against its training data. When this happens, the algorithm unfortunately cannot perform accurately against unseen data, defeating its purpose.
When the model memorizes the noise and fits too closely to the training set, the model becomes “overfitted,” and it is unable to generalize well to new data.

Question 6

variables

Answer 6

a characteristic of a concept that takes on different values from one case to another or, for a given case, from one time to another

Question 7

types of variables

Answer 7

1. nominal
2. ordinal
3. quantitative

Question 8

nominal variables

Answer 8

Different categories, no natural ordering (one category is not “more” than another)
E.g. Religion - Continent - Colours - Party - Etc.
blue is different from red.
blue is more than red. → nonsensical

Question 9

ordinal variables

Answer 9

Different categories, with a meaningful ordering.
The distance between the two categories is not meaningful.

E.g. very dissatisfied < dissatisfied < neither dissatisfied or satisfied < satisfied < very satisfied

Question 10

quantitative variables

Answer 10

Different categories, with a meaningful ordering AND the distance between two categories, have a meaning.

e.g. Number of votes, Temperature (Degrees), GDP (€)