maths skills and cognitive random statistical bits Flashcards
what is a distribution
the way data is spread out
normal distribution
mean, median and mode are all at the midpoint
negatively skewed distribution
- median and mean are lower than the mode
how is a negatively skewed distribution caused
some participants score much lower than most students
positively skewed distribution
median and mean are higher than the mode
how is a positively skewed distribution caused
a few students have scored much higher than most students
skewed distribution
caused by an outlier score which doesn’t fit the rest of the results
outlier
an extremely low/high score = unusual
type 1 error
when researchers think they have found a significant result but they haven’t
- rejects alternative hypothesis
type 2 error
when researchers think they have not found a significant result but they have
what do correlation studies investigate
whether there are relationships between different co-variables
positive correlation
as one co variable increases, the other co variable increases
negative correlation
as one co-variable increases, the other co-variable decreases
no correlation
there is no definite trend and that the 2 co-variables to not appear to be related to each other
what variables are used in correlational research
- co-variables
research question
a broad question about the concept being investigated
research aim
identifying a more specific concept within the research question which the researcher wants to investigate
what do correlations investigate
relationships
what kind of data do correlations collect
ordinal
interval
ordinal data
rank data from highest to lowest, e.g rating
nominal data
counting the number of times something happens
interval data
measured in metric units
2 tailed correlational hypothesis
where there is a significant relationship between covariables but it doesn’t state whether it will be positive or negative - no direction
1 tailed correlational hypothesis
states there will be a significant relationship between the co-variables and the direction of the correlation
null correlational hypothesis
there will not be a significant correlation and any relationship will be due to chance factors
primary data
data gathered directly from the participant/researcher
secondary data
data which has already been gathered by someone other than the researcher
how are correlations shown
as scattergraphs
issues with scattergraphs
- it wouldn’t justify in concluding that co-variable x has had an effect on co-variable Y
- can’t justify in saying that a particular hypothesis can be retained or rejected
- don’t confused findings with conclusions
findings
raw data
conclusions
broad interferences you can make from the raw data
correlation co-efficient
a value between -1 and +1 which tells you about the direction/strength of a correlation
-1 correlation
perfect negative
-0.75 correlation
strong negative
-0.5 correlation
moderate negative
-0.25
weak negative
0
no correlation
+0.25
weak positive
+0.5
moderate positive
+0.75
strong positive
+1
perfect positive
positives of correlation studies
- tell us something new, if co-variables are related, we learn things from pre-existing data, tells us strength and direction of 2 co-variables
- useful technique when either practical or ethical reasons mean variables can’t be manipulated
- good starting point for research, as once relationships have been established between co-variables more research can be conducted
disadvantages about correlations
- cause and effect isn’t explained
- doesn’t state which co-variable is causing what effect
- inferential statistical tests won’t always pick up on a relationship between 2 co-variables even if there is a genuine pattern
- only collects quantitative data
academic reports
- psychologists research can’t be immediately put into a textbook, it must be put into a report which is published in a psychological journal - and all the reports follow the same structure
academic reports structure
abstract
introduction
method
results
discussion
references
appendices
abstract
allows readers to understand a study before reading full article - summarises research
includes: aim, methods, results, conclusions
introduction
considers previous research in the area, links it to the study
how does an introduction start
by broadly discussing the area of interest, then finishes by justifying the hypothesis being studied
method
includes:
sample
experimental design
materials
procedure
- helps to make the study as replicable as possible
results (AR)
contain raw data, descriptive statistics, inferential statistics and graphs with written explanations of results
discussion
- looks at what was found in the study, the implications of findings, and any limitations of the study
- future research ideas may be discussed
references
- any work from other authors must be clearly referenced
- this allows readers to easily find the referenced research
appendices
includes any relevant materials used for the study, could be tests, raw data, questionnaires, etc
what is a significant result
- if there’s 95% of the same result or higher, a real effect is going on
measures of central tendency
mean
median
mode
