Paper 2 data handling + statistical testing Flashcards
Mean
the mean is calaculated by adding up available data scores, and dividing by the number of actual data scores
S - Representative of all the scores/values collected.
L- distorted by extreme values / No values should be ignored
Mode
most frequently ocurring score in a data set, and this becomes your mode
S - easy to calculate to identify/calculate
L - The mode does not consider all the values in the data.
There can be more than one mode or no mode for the data.
Median
rank all scores from smallest to largest, and then work out which is the middle value. 2 scores that sit in the middle, then the median is the sum of the 2 scores, divide by 2.
S - easy to identify and extreme scores do not affected it
L - Not all values are included
Range
highest value - lowest value
s - easy to calculate
l - only takes into account the most extreme values unrepresentative of the dataset as a whole.
Negative skew
long tail on the negative left side of the peak.
most of the distribution is concentrated on the right
the mean is lower than the median/mode
Postive skew
long tail on the positive right side of the peak
the mean is higher than the mode
Distributions
Normal
symmetry on both sides of the curve
mean, median, mode are equal
Display of quantitaive data
table - converted to descriptive statistics
bar chart - bars are separate to show we are dealing with separate conditions
scattergram - depict associations between co-variables
histogram - distribution of s continuous data set
Line graph - displays continuous data and use points connected by lines to show how something changes in value over time.
standard deviation is a meaure of dispersion that shows the spread of scores around the mean.
is a meaure of dispersion that shows the spread of scores around the mean.
the greater the SD the greater the spread of scores around the mean.
S- precise measure of dispersion than the range as it included all the values
L - only takes into account the extreme values - not giving a full representation of the spread of scores - it can be distorted by a single extreme value , extreme values cant be revealed.
Experimental/alternative Hypothesis
A clear, precise testable statement/prediction about the relationship between the variables in the investigation
Directional (one-tailed)
States the direction of the investigation
Non-directional (2-tailed)
States that there will be a difference between 2 variables but not what the difference will be
Null Hypothesis
Written along side alternative/experimental hypothesis
states that there is no difference between variables/conditions and any differences is due to chance
Significance level
psychologists can never be 100% certain aboout anything. So they have settled on a 95% confidence level .
this is written as p<0.05
this means there is a 5% or less that the results are due to chance and we must reject our null hypothesis
alternative you can say there is a 95% likelihood/confidence that the findings are not due to chance
if the null hypothesis has been rejected the results are significant
if the null hypothesis has been accepted the results are insignificant
Type 1 error
false positive
**D: A type 1 error It is where you accept the alternative/experimental hypothesis when it is false.
- occurs when a researcher incorrectly rejects a true null hypothesis
**
5% chance of making a type 1 error
psychologist use a 0.05 level of significance as it is halfway between type 1 and type 2 error, because 0.01 and 0.1 level of significance so the chance of making an error is reduced
too lenient - optimistic level of significance 10%
type 2 error
False Negative
happens when you accept the null hypothesis when it should actually be rejected.
occurs if the investigator fails to reject a null hypothesis that is actually false
A type 2 error occurs when the p value is set too low, for example, p<0.01. - too strict - pessimistic
How to use statistical tests
- calculate the calculated value using the correct statistical test
- Compare the calculated values with the critical value using a critical value table.
- if the calculated value - equal to or greater then or smaller than
Choosing a statistical test
- am i looking for
difference/relationship - What is experimental design?
- independent group design - unrelated - Ps in each condition are different
repeated measures - same ps used in all conditions
matched pairs design - Ps are matched together - Which level of measurement is the data?
Nomial counting things and putting them in categories - mode
Ordinal - measuring things and data has been put in rank order of size - median/range
Interval. - measuring things on an equal scale that has equal units - mean/standard deviation
Sign test is used when ?
- test of difference
- Nomial data
- Repeated measures-The same Ps are used in more than one condition
Sign test step 1
- calculate the observer/calculated value using the sign test
- data need to be converted to nomial data (named categories
- calculate the difference between 2 scores of the Ps
- if there is an increase between condition 1 and condition 2 write a +
- if there is a decrease between conditions 1 and 2 write a -
- if there’s no increase/decrease write 0 - theses scores will not be included in the investigation
- add up all the + and -
- count the number of the less frequent sign this is the calculated/observer value
- for example if there are 9+ and 4- then the observer/calculated value is 4
Sign test step 2 + 3
- use the critical value table to work out the critical value for the investigation
- the critical value needs to be compared with the observer/calculated value
the observer/calculated value must be equal to or less than the critical value for the investigation/findings to be considered significant (the null hypothesis needs to be rejected)
Spearman’s Rho
- testing for a correlation- a relationship between 2 variables
- data is related ( comes from same person ) - repeated measures design
- level of measurement: Ordinal (put iin order) or interval
- Needs number of Ps
- Significant = OV must be greater / equal than CV= Null hypothesis rejected
Pearson’s r
Predicts correlation-a relationship between two co-variables.
Data is related
level of measurement: Interval data
Significant = OV must be greater / equal the CV= Null hypothesis rejected
Chi-squared
Predicts a difference between 2 conditions
data is unrelated / independent
Independent group design used
level of measurement: Nominal data
Degree of freedom needed
Significant = OV must be greater / equal the CV= Null hypothesis rejected
Sign test
predicts a difference between 2 sets of data
data is related (comes from same person)
Repeated measure / Matched pair design used
level of measurement: Nominal data
Significant = OV must be less / equal the CV
= Null hypothesis rejected
Wilcoxon T
Predicts a difference between 2 sets of data
Data is related
Repeated measure design used
level of measurement: Ordinal / Interval / Ratio
Significant = OV needs to be less / equal the CV= Null hypothesis rejected
Man Whitney U
predicts difference
data is unrelated / independent
independent group design used
level of measurement: Ordinal / Interval / Ratio
number of ps in each group needed
Significant = OV needs to be less / equal the CV
Unrelated T test
predicts a difference
data is unrelated / independent
Independent group design used
level of measurement: Interval
Significant = OV must be greater / equal the CV
Related T test
predicts a difference
data is related
repeated measure used
level of measurement: Interval
Significant = OV must be greater / equal the CV
Statement of significance - explaining why findings are significant / insignificant
what needs to be included?
You will be required to explain why research findings are significant/insignificant
1. the number of ps
2. type of hypothesis (1 or 2 tailed )
3. level of significance used
4. The observer value
5. Critical value
6. If the OV is less/greater/equal the CV
7. If the null hypothesis can be rejected/accepted
Example - For 10 Ps one-tailed, level of significance 5%, the critical values for Spearmans r is 0.564.
The observer value of Spearmans r is 0.703, which is greater than the critical value, so there is a less than a 5% probability that the results are due to chance.
The null hypothesis can be rejected and the alternative hypothesis can be accepted.
The use of statistical tables
Step 1. What type of hypothesis was used in the investigation? = One-tailed (Directional) or Two-tailed (Non-directional)
Step 2
- How many Ps in the investigation
- This usually appears as N in the table
- For some tests this may be the degrees of freedom (df)
Step 3
The level of significance/p value
The 0.05 level of significance is the standard for psychology
A directional (one-tailed) hypothesis
A directional (one-tailed) hypothesis predicts the nature of the effect of the independent variable on the dependent variable. It predicts in which direction the change will take place.
past research supports that the findings will go in a particular direction
Non-directional hypothesis
A non-directional hypothesis is a two-tailed hypothesis that does not predict the direction of the difference or relationship
its used when past research is unclear or contradictory
Naturalistic observations
Watching and recording behaviour in the setting within which it would normally occur.
Strengths
- High ecological validity - it can be easily generalised to everyday life
- High external validity as it’s done in a natural environment
Limitations
- Low ecological validity if participants become aware that they are being watched
Replication can be difficult
uncontrolled confounding variables and extraneous variables are presented
Controlled Observations
Watching and recording behaviour within a structured environment e.g lab setting
Strengths
- Researchers is able to focus on a particular aspect of behaviour
- There is more control over extraneous variables
- Easy replication
Limitations
more likely to be observing unnatural behaviour as it takes place in an unnatural environment
- Low mundane realism so low ecological validity
Demand characteristics presented
Covert
Ps behaviour is watched and recorded without their knowledge or consent.
Strengths
- Natural behaviour recorded hence high internal validity of results
- Removes demand characteristics, Ps can’t easily guess the aim of the study
Limitations
- Ethical issues as no informed consent is given, there is also an invasion of participants’ privacy
Overt
Participants are watched and their behaviour is recorded with them knowing that they are being watched
Strengths
- Ethically acceptable as informed consent is given
Limitations
- More likely to be recording unnatural behaviour as Ps know that they are being watched
- Demand characteristics are present this reduces the validity of the findings
Participant observation
The researcher becomes a member of the group whose behaviour he/she is watching/recording.
Strengths
- Can be more insightful which increases the validity of the findings
Limitations
- Demand characteristics
- The researcher may lose objectivity as may start to identify too strongly with the participants
Non-participant
The researcher observes from a distance so is not a part of the group being observed.
Strengths
The researcher can be more objective as less likely to identify with participants since they are watching from outside the group
Limitations
- open to observer bias
- The researcher may lose some valuable insight
Behaviour categories
When a target behaviour is broken up into more specific components that are observable and measurable.
This allows for operationalisation of the behaviour.
Sampling methods
Observer bias
Observer bias occurs when a researcher’s expectations, opinions, or prejudices influence what they perceive or record in a study.
It usually affects studies when observers are aware of the research aims or hypotheses.
Issues with behavioural categories
Categories should not over-overlap.
