Repeated Measures Experiments

Question 1

Two types of experimental designs

Answer 1

1. repeated measures design
2. independent groups design

Question 2

comparing the scores of
individuals in one condition against their scores in
another condition.

Answer 2

Repeated Measures Design

Question 2

comparing the scores of
one group of people taking one condition against the
scores of a different group of people in the other condition

Answer 2

Independent Groups Design

Question 3

change within a
group of individuals, rather than between two groups.

Answer 3

Within-subjects studies / designs

Question 4

other names for repeated measures design

Answer 4

1. Within-subjects studies / designs
2. Related groups / design
3. Cross-over studies / design

Question 5

people undergoing two
different treatments are closely matched, so that the two
groups are not independent, rather they are related.

Answer 5

Related groups / design

Question 6

*strictly speaking, a __________ is a type
of related design; however, it is very rare to encounter
a study where both groups are sufficiently closely
matched.

Answer 6

repeated measures design

Question 7

term mainly used in
medical research than commonly used in psychology.
People cross-over from one group to the other group.

Answer 7

Cross-over studies / design

Question 8

Common Mistakes: _______ and Repeated Measures Designs

when we want to see if people who
were high scorers on one test are also high scorers on
the second test. We are not interested in whether the
scores overall have gone up or down.

Answer 8

correlational

Question 8

Common Mistakes: Correlational and ________

if people on average, score
higher on one occasion than the other.

Answer 8

repeated measures

Question 9

Advantages of Repeated Measures Design

1. There is no need for many ________.
2. Each person acts as their own______ matched
   control group.

Answer 9

1. participants
2. (perfectly)

Question 10

Disadvantages of Repeated Measures Design

1._______ participants gets better at a task over
time. (solutions: counterbalancing and practice items)

Answer 10

Practice effects

Question 11

Disadvantages of Repeated Measures Design

2. participants may perceive that a
   dependency exists between two measures, and
   deliberately keep their answers similar when we are
   looking for change. Alternatively, because the
   participants perceive that the researcher is looking for
   change, they might change their answers.

Answer 11

sensitization

Question 12

Disadvantages of Repeated Measures Design

3. occurs when something about the
   previous condition is “carried over” into the next condition.

Answer 12

carry-over-effects

Question 13

Disadvantages of Repeated Measures Design

Answer 13

1. practice effects
2. sensitization
3. carry-over effect

Question 14

Statistical Tests for Repeated Measures Designs

Answer 14

1. the repeated measures t-test
2. the wilcoxon test
3. the sign test

Question 15

Statistical Tests for Repeated Measures Designs

parametric test for
continuous data.

Answer 15

The Repeated Measures t-test

Question 16

Statistical Tests for Repeated Measures Designs

non-parametric test for ordinal
data

Answer 16

The Wilcoxon test

Question 17

Statistical Tests for Repeated Measures Designs

non-parametric test for categorical data

Answer 17

The Sign Test

Question 18

the most powerful, and most likely to spot
significant differences in data. It can not be used however with all repeated measures data. Data should
also satisfy some conditions before this test can be
used.

Answer 18

t-test

Question 19

Sign test – only deals with data in the form of
categories _____ Easy to understand and
calculate.

Answer 19

(nominal data).

Question 19

Wilcoxon test – deals with all data that can be ordered
________.

Answer 19

(ordinal data)

Question 20

The Repeated Measures t-test

To use this test, we need to make 2 assumptions about our
Data:

1. The data are measured on a continuous ______ level.
2. The differences between the two scores are ______

Answer 20

1. (interval)
2. normally
   distributed.

Question 21

Common Mistakes: Assumptions of the Repeated Measures t-test

It makes no assumption about the______ of the scores. Only the differences between the scores.

Answer 21

distribution

Question 22

Common Mistakes: Assumptions of the Repeated Measures t-test It is possible to have variables which have highly ______, but which have normally distributed differences.

Answer 22

non-normal distributions

Question 23

Common Mistakes: Assumptions of the Repeated Measures t-test It makes no assumption about the ______ of the variables.

Answer 23

variances

Question 24

Common Mistakes: Assumptions of the Repeated Measures t-test Given a sufficiently ________, the repeated measures t-test is robust against violations of both these assumptions.

Answer 24

large sample

Question 25

Common Mistakes: Assumptions of the Repeated Measures t-test Above sample sizes of approximately ____, the test becomes very robust to violations of distributional assumptions.

Answer 25

50

Question 26

tells us about the likely range of the true value of the score

Answer 26

Confidence interval

Question 27

to test the statistical significance of a t-score get the p-value of it to get the score as a result of chance if the NULL is true. For result to be significant, p-value should be____. It should be equal to or _____the alpha level we use for significance testing (alpha levels could be 0.05, 0.01, 0.001 etc.

Answer 27

low less than

Question 28

t-test p-value of our score should be____ because we assume in the first place that the Null Hypothesis is probably true.

Answer 28

low

Question 29

Get the t-critical value and compare the t we got. * The t-critical is the t-score which has a p-value equal to the ______ we use. It is relative to the sample size as exemplified by the use of the concept of _______

Answer 29

alpha level degrees of freedom.

Question 30

Get the t-critical value and compare the t we got. For our t (the t-score we got) to be significant it should be equal to or ______ the t-critical value.

Answer 30

more than

Question 31

calculate the confidence interval The CI tells us the likely range of the score in the population, or if the _____ is measured instead of the sample.

Answer 31

population

Question 31

The CI, as an estimate, gives us the possible values the _______ could take or be.

Answer 31

TRUE SCORE

Question 32

calculate the confidence interval In this test, the score we are referring to is the ______(summation of difference scores computed from the two groups/conditions)

Answer 32

difference score

Question 33

These range of possible values cover the middle _______of the cases in the distribution.

Answer 33

95%

Question 34

Why the middle 95% of cases? Because, the scores within this area, range, or interval are the scores considered to have higher ____ or ____ of occurring compared to the other scores in the distribution.

Answer 34

p-values or probabilities

Question 34

This is opposite of what we assume in the first place that if the Null Hypothesis is true, our result should have a ____ or ____ of occurring.

Answer 34

low p-value or probability

Question 35

It follows the rule that, if the alternative hypothesis could be true, it should have a_______ of occurring.

Answer 35

high probability

Question 35

if our result is statistically significant, it should be contained within the_____

Answer 35

CI

Question 36

The Null Hypothesis then should not be contained ______ for our result to be significant.

Answer 36

within the CI

Question 37

If it happens that the Null hypothesis is contained in the CI, the result is ______

Answer 37

not significant

Question 38

Used when data do not satisfy the assumptions of the repeated measures t-test.

Answer 38

The Wilcoxon Test

Question 39

The Wilcoxon Test The differences are not _______

Answer 39

normally distributed

Question 40

The Wilcoxon Test The measures are ____

Answer 40

ordinal.

Question 41

The Wilcoxon Test Non-parametric test or parametric test

Answer 41

non-parametric test

Question 42

The Wilcoxon Test If data were not measured on an ordinal scale we ______

Answer 42

convert them.

Question 42

The Wilcoxon Test Parametric test – makes inferences about population parameters. Non-parametric tests use____

Answer 42

ranks.

Question 42

Frank Wilcoxon – developed two statistical tests namely the 1. 2.

Answer 42

1. Wilcoxon-rank sum 2. Wilcoxon signed ranks test.

Question 43

developed two statistical tests namely the Wilcoxon-rank sum and the Wilcoxon signed ranks test.

Answer 43

Frank Wilcoxon

Question 43

equivalent to Mann-Whitney test which is easier to calculate.

Answer 43

rank sum

Question 44

Thus when we refer to a Wilcoxon test, we refer to the ______ test only.

Answer 44

Signed ranks

Question 45

The test statistic for the Wilcoxon Test is known as T (capital T) and is given by whichever is the_____ of these two values.

Answer 45

lower

Question 46

Used when we have nominal data with two categories, and have repeated measures data

Answer 46

the sign test

Question 46

used to correct for continuity. The z distribution is continuous – that is, any value at all is possible. However, the Wilcoxon T distribution is not truly continuous, because it can only change in steps.

Answer 46

continuity correction

Question 47

Easiest statistical test

Answer 47

the sign test

Question 47

in the sign test, N is different from in other test. * The sign test uses N as the ________ from whom there was not a tie.

Answer 47

total number of people

Question 48

The test statistic from the sign test is called ___

Answer 48

S