Wk 3- Biomed Skills- Data Interpretation and Analysis

Question 1

Types of data presentation

Answer 1

Tables
Graphs
Box-and whisker plots
Bar graph scatter plots
One-way scatter plots
Two-way scatter plots

Question 2

Features of tables

Answer 2

Numbered
Descriptive title
Column titles bolded
Footnotes

Question 3

Types of tables

Answer 3

Freq distribution
Relative freq

Question 4

Benefits of tables

Answer 4

Present raw data and allow own interpretations

Question 5

Features of graphs

Answer 5

No title
Figure legend
Labelled axes

Question 6

Types of graphs

Answer 6

Bar charts
Histograms

Question 7

Benefits of graphs

Answer 7

Visualise data
Show trends

Question 8

Features of box and whisker plots

Answer 8

5 no. summary
- Min
- Lower quartile
- Median
- Upper quartile
- Max

Question 9

Benefits of box and whisker plots

Answer 9

Show range and distribution

Question 10

Features of bar graph scatter plots

Answer 10

• = Stat analysis P <0.05
  ** = Stat analysis P <0.01

Question 11

Features of one-way scatterplot

Answer 11

Control on LHS
Dots represent inds

Question 12

Benefits of one-way scatterplot

Answer 12

Show patterns better than bar graphs

Question 13

Benefits of two-way scatterplots

Answer 13

Show correlation and distribution

Question 14

Population

Answer 14

Complete set of events
Often not viable

Question 15

Sample

Answer 15

Set of observations from pop
Can become pop

Question 16

Sampling methods

Answer 16

Representative samples
- Pop
- Representative sample
- Biased sample
Convenience samples
Systematic sampling
Random samples
Stratified random sample
Self-selected samples

Question 17

Systematic sampling

Answer 17

Inds selected at intervals

Question 18

Random samples

Answer 18

Inds noed then selected randomly

Question 19

Stratified random samples

Answer 19

Inds no.ed then randomly selected

Question 20

Self-selected samples

Answer 20

Can intro bias

Question 21

Effect of sampling method

Answer 21

Dif methods intro dif bias

Question 22

Example of sampling bias

Answer 22

Australian Schizophrenia Research Bank 2007 studied >1000 inds
- NSW, QLD, VIC selected via advertising
- WA, QLD selected via inpatient services

Question 23

What is the ideal sample size based on?

Answer 23

Type of study, i.e. the dif b/n control and case
Sampling method
Accuracy needed

Question 24

Why do larger sample sizes improve accuracy?

Answer 24

Allow smaller difs b/n cases and controls to be observed
Reduce effect of bio var
Allow larger dif to be seen b/n case and control

Question 25

Sampling error

Answer 25

Dif b/n true parameter and sample

Question 26

Types of data distribution

Answer 26

Direct correlation Normal distribution Bimodal distribution - or + skewed

Question 27

Descriptive statistics

Answer 27

Summarise data

Question 28

Central tendency

Answer 28

Most typical score

Question 29

Measures of central tendency

Answer 29

Mean- Sum of scores/no. of scores Median- Middle score Mode- Most common score

Question 30

Dispersion

Answer 30

Spread of data

Question 31

Measures of dispersion

Answer 31

Range- Highest score - lowest score SD

Question 32

What should be done w/ outliers?

Answer 32

They are real results and should be included unless a mistake occurred

Question 33

Regression line/ line of best fit

Answer 33

Linear Describes relationship b/n vars

Question 34

Coefficient of determination (R2)

Answer 34

How well the line predicts the relationship or how close dots are to the line Measures accuracy Out of 1

Question 35

Correlation coefficient (r)

Answer 35

Strength and direction of data From -1 to 1

Question 36

Aim

Answer 36

What you're trying to do

Question 37

Hypothesis

Answer 37

Proposition for exp. based on evidence Able to be rejected

Question 38

2 types of hypothesis

Answer 38

Null hypothesis (H0)- There is no dif b/n groups. Not what funders want to hear thus not usually written Alternate hypothesis (H)- There is a dif

Question 39

Hypothesis testing

Answer 39

Determines probability of rejecting hypothesis

Question 40

Steps in hypothesis testing

Answer 40

1. Propose H 2. Propose H0 3. Try to reject H0, i.e. prove thast the samples are dif based on reasonable prob 4. Try to prove H to confirm result 5. Find dif b/n control and intervention groups 6. If prob that the dif b/n groups could occur w/o intervention is <0.05, reject H0 because of the statistically significant effect

Question 41

Things to consider when coming to a conclusion

Answer 41

Did the exp have enough power to detect a dif? Was the sample large enough? Consider effect of gene var