[L7] 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.
* It does not tell much.

Answer 2

Mode

Question 3

• Three main ways of showing the difference between two
  proportions. (fourth one as well)

Answer 3

Absolute and Relative Change

Question 4

All look very similar to each other and it is often not clear
which one people are talking about.

Answer 4

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

• Third way of showing the difference two proportions.

Answer 6

Odds Ratio

Question 7

Trickier than percentages and proportions but most
common way.

Answer 7

Odds Ratio (OR)

Question 8

Odds are always presented as

Answer 8

“something to one”.

Question 9

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

Answer 9

Absolute
Difference

Question 10

The___ in the percentage of people who
took the antibiotic is 15%.

Answer 10

absolute reduction

Question 11

Reduction in antibiotic use as a ___ of those in
the leaflet group

Answer 11

Proportion

Question 12

So giving a leaflet reduces the chances that the person
will take antibiotics by 24%. This is the ____

Answer 12

Relative Risk
Decrease.

Question 13

What are the odds of throwing a 6 on a die
/dice? Tricky because it is…

Answer 13

counter-intuitive

Question 14

The odds are 5 to 1, or 5: 1. The event will not
happen___ that it does happen.

Answer 14

5 times for each time

Question 15

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

Answer 15

probability

Question 16

Chi-square

Answer 16

Odds Ratio

Question 17

We then express the change in the ___ using the odds
ration, OR.

Answer 17

odds

Question 18

Easier way of calculating the odds ratio.

Answer 18

OR = AD / BC

Question 19

OR = AD / BC

Answer 19

distribution of frequency scores

Question 20

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

Answer 20

Number Needed to treat (NNT)

Question 21

Also known as NNH or

Answer 21

number needed to harm.

Question 22

The NNT is very easy to calculate. It is simply

Answer 22

• NNT = 1 / Absolute Risk Difference

Question 23

• 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
  \

Answer 23

odds ratio.

Question 24

v, (Greek
letter nu, pronounced ___

Answer 24

“new” or “noo”)

Question 25

v is a bit like the ___of the odds ratio

Answer 25

standard error

Question 26

First, when we had the confidence intervals of a mean, the intervals were symmetrical, so the lower CL was the same amount below the mean as the upper CL was above it. * This is not the case for the ___

Answer 26

odds ratio.

Question 27

Second the CIs do seem to be very _ _ _.

Answer 27

wide

Question 28

That’s just the way they are and upper CLs can stretch into ___, with small sample sizes.

Answer 28

hundreds

Question 29

If we want more certainty, we must have a ___

Answer 29

bigger sample.

Question 30

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 30

Chi-square test.

Question 31

Odds ratio

Answer 31

raw score

Question 32

t-test

Answer 32

standardized score (d)

Question 33

convert OR to ____, to know if its difference is significant

Answer 33

chi-square

Question 34

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

Answer 34

Chi-Square χ²

Question 35

The first stage in the χ² test is to put the ___

Answer 35

values into a table, but add totals to it.

Question 36

* We have to calculate the ___for each cell, which are referred to as ___.

Answer 36

expected values , E

Question 37

The E are the values that we would _ __,

Answer 37

expect if the null hypothesis were true

Question 38

The expected values are given by: __

Answer 38

* E = R x C / T

Question 39

Where R refers to the___, C the ___, and T for____

Answer 39

total for a given row; total for a given column; grand total.

Question 40

O = ___

Answer 40

Observed value

Question 41

All we need to know is the ____so we can take the differences and add them up. (Almost but not quite)

Answer 41

distance between the observed value and the expected value

Question 42

The difference needs to take account of the___

Answer 42

sample size

Question 43

χ² = Σ (O - E)² / E

Answer 43

similar, deviation score

Question 44

Issues with χ² / complications: An assumption made by the χ² test is that all of the expected values (in a 2 x 2 table) must be ___

Answer 44

greater than 5.

Question 45

Degrees of Freedom (df)

Answer 45

* df = (number of rows – 1) x (number of columns – 1)

Question 46

If the table is larger than 2 x 2, then __ of the expected values need to be above __

Answer 46

80%; 5.

Question 47

If our data do not satisfy this assumption we can use the ___ instead.

Answer 47

Fisher’s exact test

Question 48

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

Answer 48

liberal

Question 49

A __- is slightly more prone to say that a result is statistically significant than it should be, so the Type I Error rate is not 0.05, but a little bit higher than that

Answer 49

liberal test

Question 50

One approach in dealing with this is to use ____

Answer 50

Yates’ Correction for Continuity or Continuity Correction

Question 51

The values contained within the bars means ___, which means if there is a minus sign ignore it.

Answer 51

“take the absolute value”

Question 52

The problem with Yates’ correction is that it makes the test a little conservative so the ___is now ___

Answer 52

Type I Error rate; smaller than 0.05

Question 53

This in itself is not a problem, but it means that the test is now ___, when it should be giving one

Answer 53

less likely to give a significant result

Question 54

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

Answer 54

relatively small.

Question 55

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

Answer 55

large

Question 56

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

Answer 56

Fisher’s Exact test.

Question 57

The Idea of Fisher’s exact test is that for some events we can work out the exact probability of them occurring without needing to use ___

Answer 57

test statistics and tables.

Question 58

We can do the same thing for data which are in a___

Answer 58

2 x 2 contingency table.

Question 59

Fisher’s exact test gives the probability of getting the ___

Answer 59

exact result that was found in the study.

Question 60

However, we are not just interested in the exact result, we are interested in any result that is ___

Answer 60

more extreme than the result we have.

Question 61

Fischer, inspired by __, that led him to form a formula because his wife has a special talent to exactly pin point is a tea is made with tea first or tea

Answer 61

wife

Question 62

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

Answer 62

test statistic