Inferential Testing Flashcards Preview

Psychology research methods > Inferential Testing > Flashcards

Flashcards in Inferential Testing Deck (29):
1

In the sign test, how do you know whether or not a result is significant?

If the observed value is equal to or less than the critical value, so the null hypothesis is rejected

2

In the sign test, what happens if the observed value (s) is lower than or equal to the critical value?

The null hypothesis can be rejected

3

In the sign test, what is the observed value (s)?

The number of times the less frequent sign occurs

4

In the sign test, what is the N value?

The total number of pairs of scores, basically the total number of signs, omitting the '='

5

What is a one-tailed hypothesis?

Directional

6

What is a two-tailed hypothesis?

Non-directional

7

What does a correlational study produce?

A correlation coefficient

8

What is a correlation co-efficient?

A numerical value showing the degree to which two co-variables are related

9

What do measurements range from in a correlation co-efficient?

-1 to +1

10

What does +1 show?

A perfect positive correlation

11

What does -1 show?

A perfect negative correlation

12

The closer the correlation to a perfect correlation...?

The stronger the relationship between the two variables

13

What are the three statistical tests to measure correlation?

Chi-squared, Spearmans rho and Pearsons r

14

What are inferences?

Informed decisions

15

What is inferential testing?

A statistical procedure that makes predictions about populations from mathematical analysis of data taken from samples

16

What are the three types of data?

Nominal, ordinal and interval

17

What is nominal data?

Named data that can be separated into CATEGORIES which do not overlap
Tally charts are often used

18

What is ordinal data?

Data which is placed in an order or scale e.g. ratings from 1-10

19

What is interval data?

Data which is a standardised measurement unit e.g. weight, height, time, distance, temperature

20

What are the things you must think about when deciding what statistical test to use?

Is the experiment looking for difference or a correlation, is the data ordinal nominal or interval, what kind of experimental design is it? Related or unrelated? Related = repeated measures or matched pairs, unrelated = independent groups

21

What is the rhyme you must remember to remember what kind of statistical test to use?

Carrots Should Come Mashed With Sweed Under Roast Potatos

22

What is probability?

The likelihood of events being determined by chance

23

What is significance level?

Statistical criteria determining if the observed difference/relationship is beyond the boundaries of chance

24

In a sign test, if the observed value (s) is lower than or equal to the critical value for a critical value of 0.05, what does this mean in terms of significance?

That the result is significant, because there 5% or less probability that the result occurred due to chance

25

What is a type 1 error?

When the null hypothesis is wrongly rejected because it is accepted that there is a significant difference/correlation when actually there isn't one
The significance level has been set too high

26

What is a type II error?

When the null hypothesis is wrongly accepted because there actually is a significant difference/correlation but the researcher does not acknowledge it
The significance level has been set too low

27

When would you use a sign test?

Nominal data, looking for a difference, and repeated measures or matched pairs design is used

28

When would you use a chi-squared?

Nominal data, independent groups design is used, looking for a difference or a correlation

29

What is degrees of freedom?

N - 1