Lecture 4

Question 1

Types of Distribution

Answer 1

Normal and Non-normal

Question 2

Normal Distribution

Answer 2

AKA: Gaussian or Parametric distribution. Curve centred around the mean. Most of the data clustered around the centre. A perfect normal distribution: the mean, median and mode would all be the same value and there would be an equal number of data points either side of the mean.

Question 3

Non- normal Distribution

Answer 3

Less common than normal distribution. Majority of data found either to the left (positive skew) or right (negative skew) of the centre of the data

Question 4

Left Skewed Example

Answer 4

Age related condition - increases with age.

Question 5

Kurtosis

Answer 5

A measure of how wide or narrow the tails of a distribution are. We can think of this tailed-ness as a representation of how often outliers occur. We always measure the kurtosis of a distribution relative to normal distribution.

Question 6

Mesokurtic

Answer 6

Medium-Tailed

Question 7

Platykurtic

Answer 7

Thin-Tailed

Question 8

Leptokurtic

Answer 8

Fat-Tailed

Question 9

Non-normal Distribution Examples

Answer 9

Continuous Uniform Distribution, Negative Exponential Distribution

Question 10

Z-Scores

Answer 10

The number of SD’s an observation is away from the population mean. The formula for z-scores is simply the deviation from the mean divided by the standard deviation
+1SD gives a z-score of 1
-1SD gives a z-score of -1

Question 11

Positive Z-Score

Answer 11

An observation has a value above the population mean

Question 12

Negative Z-Score

Answer 12

A value below the mean

Question 13

Why are Z-Scores Useful?

Answer 13

Z-scores allow us to standardise differences across different distributions. E.g. infant birth weight/growth