Lecture 3 - Descriptive statistics

Question 1

What are descriptive statistics?

Answer 1

They summarise the mid-point and spread in your data

Question 2

What are inferential statistics?

Answer 2

• they identify significant differences or relationships
• you should combine descriptive and inferential statistics to address your research question

Question 3

What are the 3 measures of central tendency?

Answer 3

1. mode
2. median
3. mean

Question 4

Mode?

Answer 4

• calculated by looking at the most frequently occurring score
• advantage = simple to explain and easy to calculate
• disadvantage = can have more than 1 value: bimodal (2) or multimodal (3+)
• use when we have nominal data

Question 5

Median?

Answer 5

• calculated by looking at the middle score when data points are arranged from smallest to largest
• advantage = unaffected by outlying scores and skewed distributions
• disadvantage = can fluctuate across samples as it is taken from a single data point
• use when we have ordinal data

Question 6

Mean?

Answer 6

• calculated by adding up all the data points and then dividing by the number of data points
• advantage = resistant to differences across samples because it is calculated from all data points
• disadvantage = very influenced by any extreme or outlying scores as calculated from every data point
• use when we have interval/ ratio data

Question 7

What are the measures of dispersion?

Answer 7

1. range
2. interquartile range (IQR)
3. variance and standard deviation

Question 8

Range?

Answer 8

• is the difference between the largest and smallest data points

Question 9

IQR?

Answer 9

• tells you the range of the middle 50% of your data ignoring the smallest 25% and the largest 25%
• to calculate: Q3-Q1 look at diagram

Question 10

Variance and standard deviation?

Answer 10

• there are 2 types of variance: between groups variance (experimental variance) and within groups variance (random variance)
• variability is measured using standard deviation
• standard deviation measures how spread out numbers are
• is more precise than range

Question 11

What is the difference between a sample and population?

Answer 11

• a sample is all the participants that you collect data from in your study
• a population is all the possible people that could have been included in your study
• you study a sample and hope that from your findings you can infer something about the entire population

Question 12

What is a null hypothesis?

Answer 12

• predicts that no effects will be found

Question 13

What is an alternative hypothesis?

Answer 13

• predicts that effects will be found
• there are 2 types:
  -> one tailed = the direction of predicted effects is specified
  -> two tailed = no directional predictions

Question 14

What is a type I error?

Answer 14

• false positive (incorrect rejection of null hypothesis)
• when you find an effect in your sample that doesn’t exist at the population level
• very serious error as findings don’t reflect what you want to study outside of your sample

Question 15

What is a type II error?

Answer 15

• false negative
• when you accept the null hypothesis when it is false
• when you fail to find a real effect

Question 16

How does significance work?

Answer 16

• a p≤ .050 = significant findings
• a p> .050 = analysis is not significant
• the smaller the p value the smaller the chance of making a type I error
• if there is more variance between than within groups then there is more chance of findings being significant