Samples and populations

Question 1

Normal distribution

Answer 1

-symmetrical and summarised by 2 parameters: mean, centre of distribution and SD
- If something is 4SD away from mean then it is highly unlikley.

Question 2

Standard normal

Answer 2

-Special case where mean is 0 and SD is 1
-Parametric tests assume data is normally distributed if not, alternative tests used

Question 3

Sub-samples

Answer 3

Representation to population
- some traits may be over represented
- recruit larger sample for balance
- bias is systematic –> people may be more or less likely to do something regardless of sample size

Question 4

Histograms

Answer 4

-Represents sample distribution of our value of interest
-There is a underlying population distribution that we can’t directly measure
-Sample is an approximation of underlying population
bigger sample - more accurate approximation

Question 5

Sample mean

Answer 5

-A sample estimate of the underlying population mean based on a given data set
-It is the sum of all individual data points divided by the total number of data points

Question 6

Sample SD

Answer 6

square root of sum of squared difference between the sample mean and each individual data point divided by the total number of data points

Question 7

The standard erorr of the mean

Answer 7

-Tests how close a sample mean is to the poplation mean

SEM = Standard deviation of sample divided by square root of total number of data points.

Question 8

What does the standard error test for?

Answer 8

Tests how consistent the mean is across many samples from a population

Question 9

Confidence intervals

Answer 9

Intuitive way to communicate reliability of estimates of mean
Provide 2 values which define a range that has a 95% chance of containing true mean
95% CI = 1.96* SEM
Upper = mean + CI
Lower = mean - CI