Probability And Statistics Flashcards
What is probability (p)?
A numerical measure of likelihood/chance that a certain event will happen
E.g probability of rolling an odd number on a dice is 50percent
What is significance?
A statistical term used to indicate whether research findings are sufficiently strong enough to reject the null hypothesis and accept experimential hypothesis
In psychology the accepted level of significance is usually p less than/= 0.05
What is a type 1 error?
An error which occurs when a researcher rejects a null Hypothesis
E.g man is pregnant
What is a type II error?
An error which occure when a researcher accepts null Hypothesis which was not true
E.g women is pregnant not pregnant
Why are we more likely to make a type 1 error?
If the significance level is too leintent (too high)
E.g 0.1 (10 percent rather than 5 percent)
Why. are we more likely to make a type II error?
If the significance level is too stringent (too low)
E.g 0.01 ( 1 percent than 5 percent )
Why do psychologists favour 5percent significance level?
Best to balance the risk of making Type 1 or Type II error.
What is the difference of alternate and null Hypothesis?
Anull hypothesisis ahypothesisthat says there is no statistical significancebetweenthe two variables. It is usually thehypothesisa researcher or experimenter will try to disprove or discredit. Analternative hypothesisis one that states there is a statistically significant relationshipbetweentwo variables
Alternate providing evidence to support hypithesis and falsify the other hypothesis
What tests used to test for a difference?
- Mann whitney
- Wilicoxon
- Unrelated t- test
- Related t- test
What tests used to test for correlation?
- Spearman’s Rho
- Pearsons R
What test used for association?
Chi- squared test
Also used to test for difference - both aspects
What are the three factors used to devise which test used under certain circumstances?
- Whether you are looking for a difference or a correlation
- in case of difference - what experimental design used?
- what level of measurement of data is - e.g nominal ,ordinal , interval
Recap experimental design:
- Repeated measures : same participants do condition A and B
- Independent measures : Participants randomly allocated to condition A or B
- Matched Pairs: Grouos matched then randomly allocated to condition A or B
Three levels of measurement- QUANTATIVE
- Nominal
- Ordinal
- Interval
What is nominal data?
When data is in the form of categories, data and can only appear in one category
Most basic level of measurement
Everyday example of nominal data
Favourite animal?
- Dog
- Cat
- Fish
Psychology example of nominal data?
Ainsworth
Behavioural categories - secure attachment , insecure attachment
What is ordinal data? - SCALE
Data/information that has been ordered/ranked in some way
- Most precise level of measurement than nominal
- This level of measurement could be quite subjective
What is everyday example of ordinal data?
Race Position
1
2
3
What is psychology example of ordinal data?
Adorno
Facism scale - F scale developed
What is interval data?
Data which is based on measurements (on scale of equal intervals)
- Most precise level of data
- Most objective than ordinal
Everyday example of interval data?
Time taken to finish race
49s
39s
Data for Chi-Squared
Nominal
Related/unrelated design for chi- squared test
Unrelated
Related?Unrelated?
Repeated measures and matched pairs related
Independent group unrelated
Data for Spesrmans rho
Ordinal
Related? Unrelated - Spermans rho
-
Pearmans rho data
Interval
Related/unrelated design - Pearmans rho
-
Unrelated t - test
Data
Interval
Related or unrelated design? - unrelated t- test
Unrelated
Related t test data
Interval
Related? Unrelated design of related t test
Related
Mann- Whitney
Data
Ordinal
Mann- Whitney
Related or unrelated design?
Unrelated
Wilicoxon data
Ordinal
Wilicoxon design
Related
Acronym of test
Carrots should come
Mashed with Swede
Under roast potatoes
What is sign test used for?
Data- nominal data
Test a difference
Related design
