L06 - Probability and Statistics

Question 1

Bell Curve

Answer 1

A pictorial representation of the standard deviation of a set of data; in a bell curve, the mean is the centre line, and the number of data points tails off symmetrically as values are farther from the mean.

Question 2

Conditional Probability

Answer 2

A conjoint probability of dependent events where P(A|B) is read as “the probability of A given B.”

Question 3

Confidence Interval

Answer 3

The range of values within which we can be statistically confident (to some specified degree) that the true value falls.

Question 4

Gambler’s fallacy

Answer 4

The mistake of thinking that if a series of independent events has the conjoint probability p, then the probability of any single event in the series is somehow dependent on the probability of the series as a whole.

Question 5

Margin of Error

Answer 5

Half the confidence interval, expressed relative to the midpoint of that interval.

Question 6

Null Hypothesis

Answer 6

The assumption that any correlation observed between phenomena is purely random or accidental.

Question 7

Sample

Answer 7

A small selection from a larger group, the qualities or features of which purport to represent those of the group as a whole.

Question 8

Selection Bias

Answer 8

The incorporation of a bias into the selection of a sample from a group that is likely to result in the sample being unrepresentative of the relevant group.

Question 9

Standard Deviation

Answer 9

A representative number that shows the spread in the sample data.

Question 10

Statistical Significance

Answer 10

Statistical support for the conclusion that something was unlikely to have happened by chance.

Question 11

Type I Error

Answer 11

Also called a false positive, this is the error of rejecting the null hypothesis when it is actually true, or of finding an explanation other than chance when chance is in fact the right explanation.

Question 12

Type II Error

Answer 12

Also called a false negative, this is the error of failing to reject the null hypothesis when there is another hypothesis that is actually supported, or of inferring that something happens randomly or by chance, and as a result disregarding the actual explanation for the correlation or condition.

Question 13

Unrepresentative Sample

Answer 13

A sample that over-represents or under-represents some trait of the general population from which it is drawn; the product of biased selection.