RCT (Analysing the data from each trial arm to see if the outcome was present or not)

Question 1

What should quantitative data be?

Answer 1

It should either be primarily in a numerical form or able to be transformed into a numerical form

Question 2

What can quantitative data sometimes be and how to resolve this?

Answer 2

Quantitative data can be very large numerical data and so needs to be reduced down used descriptive statistics.

Question 3

What are descriptive statistics?

Answer 3

Are ways to summarise and display quantitative dataa

Question 4

What are the 4 different levels of measurement (the quantitative date will in one of these formats)?

Answer 4

1) Nominal
2) Ordinal
3) Interval
4) Ratio

Question 5

How can quantitative data be presented?

Answer 5

1) Tables
2) Charts
3) Measure of central tendency
4) Measure of dispersion

Question 6

What are the 3 measures of central tendency?

Answer 6

Mode - most frequent value
Median - central value
Mean - Arithmetic average

Question 7

What are the 3 measures of dispersion?

Answer 7

1) Range - the difference between the highest and lowest value
2) Inter-quartile range - the difference between the value at 25% and 75%
3) Standard deviation - subtracting the ean from each value, then finding out the mean of the remaining values
4) Variance - SD x SD

Question 8

Which 2 levels of measurement can use the measures of dispersion to display the data?

Answer 8

ONLY interval or ratio

Question 9

Why do we need to statistically analyse the data?

Answer 9

In order to draw inferences from them in which we can generalise to the rest of the target population

Question 10

What are the 2 ways to statistically analyse the data?

Answer 10

1) Hypothesis testing (using the P value)

2) Estimation (using confidence intervals)

Question 11

What are the 7 steps in hypothesis testing?

Answer 11

1) Obtain null hypothesis
2) Obtain alternative hypothesis
3) Carry out the significance test
4) Obtain the test statistics
5) Compare the test statistics with the hypothesised critical value.
6) Obtain P value
7) Decision - can the null hypothesis be rejected?

Question 12

What is the P value?

Answer 12

It is the probability that the data from the study allows us to ACCEPT the null hypothesis. Therefore, stating there is NOT a link between the IV and DV.

Question 13

How do we know whether to accept or reject the null hypothesis using the P value?

Answer 13

The closer the P value is to 0, the more likely we can reject the null hypothesis. The closer it is to 1, we must accept the null hypothesis.

Question 14

What is the statistical significance?

Answer 14

5%. Once the test statistic has been compared to the hypothesised critical value and the value obtained is equal or less than 0.05 - then the null hypothesis can be rejected and the alternative hypothesis can be accepted.

Question 15

What is an alternative hypothesis?

Answer 15

A hypothesis which states there is a difference between the IV and DV, but does not state the direction of this difference.

Question 16

What is the ‘power’ of a study?

Answer 16

It is represented as a percentage. It is an indication of the power the trial has to be able to detect differences between the trial arms

Question 17

What are the 2 disadvantages of the ‘P value’ ?

Answer 17

Doesn’t tell you about:

1) Effect size
2) The clinical significance of the results.

Question 18

What is a Type 1 effect?

Answer 18

When you reject the null (there is a difference) when in fact the null should have been accepted (as there actually wasn’t a difference)

Question 19

What is a Type 2 effect?

Answer 19

When you accept the null (there is no difference) when in fact the null should have been rejected (as there is a difference)

Question 20

What is a confidence interval?

Answer 20

A estimated range of values is calculated from the data. The confidence interval will be able to determine how confident we are that the unknown population parameter is within that range.

Question 21

How do we know if there is a difference between the 2 trial arms using the confidence intervals?

Answer 21

95% = the unknown population parameter is estimated to be 95% of this estimated range and there is a difference between the trial arms
10% = the unknown population parameter is estimated to be seen 10% of the estimated range and so it is unlikely there is a difference between the trial arms.

Question 22

Why are confidence intervals better than ‘P values’?

Answer 22

They can be used to determine the results:

1) Effect size
2) Their clinical significance