3h- Presentation of data

Question 1

What are the 3 kinds of data that discrete and continuous variation give rise to?

Answer 1

• qualitative
• quantitative
• ranked

Question 2

What are discrete variables?

Answer 2

Limited number of possible types of characteristics e.g. eye colour

Question 3

What are continuous variables?

Answer 3

Range of values e.g. height

Question 4

What is quantitative data?

Answer 4

Data which can be measured objectively, usually with a numerical value, e.g. time, height. Easy to plot in graphical form and can be analysed statistically

Question 5

What is qualitative data?

Answer 5

Data which is subjective and descriptive, it cannot necessarily be measured and is difficult to analyse statistically e.g. colour change, patient symptoms

Question 6

What is ranked data?

Answer 6

Refers to the data transformation in which numerical values are replaced by their rank when the data is sorted from lowest to highest e.g. observing animals and assigning dominance rank

Question 7

What does the type of variable being measured have consequences for?

Answer 7

Any graphical design or statistical tests which may be used

Question 8

What are the 3 main calculations that can be conducted on data?

Answer 8

• mean
• median
• mode

Question 9

What is the mean and how do you find it?

Answer 9

The mean is the average number. It is the sum of all the numbers divided by the number of measurements taken

Question 10

What is the median?

Answer 10

The median is the middle value when the data is placed in sequence

Question 11

What is the mode?

Answer 11

The mode is the most frequent value in the data set

Question 12

What can box plots be used to show?

Answer 12

Variation within and between data sets

Question 13

What 4 things should box plots include?

Answer 13

• median
• lower quartile
• upper quartile
• inter-quartile range

Question 14

What do error bars show?

Answer 14

They indicate the variability of data around the mean

Question 15

Why are error bars added to graphs?

Answer 15

They can show a direct measure of variation (using standard deviation) or probabilities (using confidence intervals)

Question 16

What does a smaller error bar mean?

Answer 16

That the data is less variable

Question 17

What is a confidence interval?

Answer 17

The statistical estimate of the range of values within which a certain percentage of the total population would be found

Question 18

What does a 95% confidence interval show?

Answer 18

That the range of values would include 95% of the whole population being studied

Question 19

When graphing data, when does correlation exist?

Answer 19

If there is a relationship between two variables

Question 20

When does a positive correlation exist?

Answer 20

When an increase in one variable is accompanied by an increase in the other variable

Question 21

When does a negative variable exist?

Answer 21

When an increase in one variable is accompanied by a decrease in the other variable

Question 22

What is the strength of correlation proportional to?

Answer 22

The spread of values from the line of best fit

Question 23

When can the correlation be described as strong?

Answer 23

When the values align closely to the line of best fit

Question 24

When can the correlation be described as weak?

Answer 24

When the values do not align closely to the line of best fit

Question 25

When, and only when, can causation be shown?

Answer 25

When all confounding variables are adequately controlled and thus is is difficult to demonstrate causation in observational studies

Question 26

When does causation exist?

Answer 26

If the changes in the values of the independent variable are known to cause changes to the value of the dependent variable