Data from Independent Groups: Categorical Measures

Question 1

can only take on one of a limited number of values, often simply yes or no.

Answer 1

• Categorical or Nominal data

Question 2

very rarely used as an appropriate measure of central tendency.

Answer 2

mode

Question 3

• It does not tell much.

Answer 3

Summarizing Categorical Data

Question 4

First way is to look at the data is to use the ____

Answer 4

Absolute Difference

Question 5

Three main ways of showing the difference between two proportions. (fourth one as well)
* All look very similar to each other and it is often not clear which one people are talking about.

Answer 5

Absolute and Relative Change

Question 5

We usually describe the % of people in each group and the differences between them.

We also get on to the 95% CIs.

Answer 5

Summary Statistics

Question 6

the percentage of the decrease achieved by the group receiving intervention compared with the group that did not receive the intervention (i.e., the control group).

Answer 6

Relative Risk Decrease.

Question 7

Third way of showing the difference two proportions. *
Trickier than percentages and proportions but most common way.

Answer 7

odds ratio

Question 8

One more method of presenting the effect of an intervention which is commonly used in medicine, though less commonly used in psychology.

• Also known as NNH or number needed to harm.

Answer 8

Number Needed to treat (NNT)

Question 8

If we know the probability, p, we can calculate the odds using the following formula:
____

Answer 8

• Odds = p / 1 – p

Question 9

Although it is possible to compute for all the descriptive statistics that we calculated, most of them are rarely used so the only one we are going to concentrate on is the odds ratio.

Answer 9

Confidence Intervals

Question 9

The NNT is very easy to calculate. It is simply * NNT = ____

Answer 9

1 / Absolute Risk Difference

Question 10

Developed by Pearson and sometimes known as the Pearson χ² test.

Answer 10

Chi-Square χ²

Question 10

we have to calculate a statistic called ___, (Greek letter nu, pronounced “new” or “noo”)

Answer 10

v

Question 10

is a bit like the standard error of the odds ratio.

Answer 10

v

Question 11

There is only one way to calculate the probability value given the plethora of ways of displaying the difference between two proportions. (Sort of only one way)
* The test is called

Answer 11

Chi-square test.

Question 12

The first stage in the χ² test is to put the values into a table, but ____to it.

Answer 12

add totals

Question 12

We have to calculate the expected values for each cell, which are referred to as ___

Answer 12

E

Question 13

The E are the values that we would expect if the null hypothesis were ___, the null hypothesis in this case being that the task type had no effect.

Answer 13

true

Question 14

The expected values are given by:

Answer 14

E = R x C / T

Question 15

Where ____ refers to the total for a given row, ___ the total for a given column, and ___ for grand total.

Answer 15

R
C
T

Question 16

All we need to know is the distance between the ___ value and the _____ value so we can take the differences and add them up. (Almost but not quite)

Answer 16

observed
expected

Question 17

The difference needs to take account of the ___

Answer 17

sample size

Question 18

An assumption made by the χ² test is that all of the expected values (in a 2 x 2 table) must be greater than __

Answer 18

5

Question 18

If the difference between the observed and expected values is 6, and the expected value is also 6, we are out by a____
* On the other hand, if the expected value is 1,000,000, then that is ___

Answer 18

long way

pretty close.

Question 19

If the table is larger than 2 x 2, then___ of the expected values need to be above 5.

Answer 19

80%

Question 20

2nd, when we have a 2 x 2 table the χ² test is a little bit liberal, and statisticians do not like ____

Answer 20

liberal tests.

Question 20

One approach in dealing with this is to use ______ or _______

Answer 20

Yates’ Correction for Continuity

Continuity Correction.

Question 21

The values contained within the bars means “take the absolute value”, which means if there is a ______ ignore it.

Answer 21

minus sign

Question 22

The problem with Yates’ correction is that it makes the test a little conservative so the _____ rate is now smaller than 0.05.

Answer 22

Type I Error

Question 23

In fact, the correction only matters when the sample size is relatively ____

So if the sample size is large, the correction makes little difference.

Answer 23

small.

Question 23

If the sample size is small, there is a better test we can use called the _____

Answer 23

Fisher’s Exact test.

Question 23

Fisher’s exact test gives the probability of getting the exact result that was found in the study.

• However, we are not just interested in the exact result, we are interested in any result that is more____than the result we have

Answer 23

extreme

Question 24

the Idea of _____ is that for some events we can work out the exact probability of them occurring without needing to use test statistics and tables

Answer 24

Fisher’s exact test

Question 25

With Fisher’s exact test there is _____, and no need to look anything up in a table.

Answer 25

no test statistic