descriptive statistics
what are the two types of statistics
1. descriptive statistics.
2. inferential statistics.
what does descriptive statistics mean
statstics which generally describe the data for example mean, median, mode and range.
what does inferential statistics mean
statistics which make predictions/generalisations based on you data, for example distrubution graphs, proability and significance leves, correlation co-efficients.
what does the mean mean
arthmetic average this is calculated by adding all the scores together in each condition and then divding by the number of scores.
what are the advantages of the mean
useful as takes all scores into account.
what are the disavantages of the mean
1. there can be extreme values which may inflate or deflate the average.
what is the median
middle number this is calculated by finding the mid point on a numberically ordered list.
what are the advantages of the median
1. used if there is an extreme value then it will be more representative of the data.
what are the disadvantages of the median
1. ignores scores - not all scoes are taken into account in the final value.
what is the mode
most commone value in a set of values.
what are the advantages of the mode
1. useful when there are categories of datae. for exampel most commone behaviour.
what are the disadvantages of the mode
1. doesn't include any other scores. ignores data.
what is standard deviation (SD)
1. it tells us how spread out the data is from the mean.
2. a high SD = data is very spread out from the mean.
3. a low SD = data is close to the mean.
4. a standard deviation of 0 = all the data values are the same.
how to solve a standard deviation
1. calculate the mean of the data.
2. take the mean away from each score at a time (difference).
3. square all of those differences individually.
4. work out the maen of those squared difference (add them all up to get a total, then divide by n-1) n is the number of p's data) so divide by 4 here.
5. then square root this number.
what is the variance
1. this is the value you calculate in the step 4 (before you square root).
2. it still tells us how spread out the data is but psychologists tend to just use the standard deviation.
what does distribution curves mean
1. a way to analyse and make conclusions about our data. they're graphs plooted to represent the mean and spread of the data (standard deviation).
2. they tell us mathematically where most results sit.
what is a bar chart
height of each represents the frequency of each category
space should be left between bars.
when would you use a bar chart
when you have data that is categorical for example nomianl data.
can be usedto demonstrate averages such as the mean, median and mode.
what is a histogram
similar to a bar chart but they show the 'frequency density' instead of just hte frequency.
they show the distribution of the data (how spread out it is).
when would you use a histogram
when the data is not categorical (called interval).
what is a scattergraph
used to represent relationships between data.
plots and not joined. can draw a line of best fit.
when would you use a scattergraph
only if you've conducted a correlation using ordinal/intervald.
what is a pie chart
alternative to a bar char. each pie slice is a category.
when would you use a pie chart
when there is non-continuous/nominal data.
divide each frequency by the total frequencies and multiply by 360 degrees.
what is a line graph
a graph which shows change overtime - a line connects each dot.
when would you a line graph
interval data - to show how something changes over time.
can be useful to compare 2 or more conditions.
what are the 5 types of graphs/charts
bar chart
histogram
scattergraph
pie chart
line graph
how to calculated the group width in a histogram
find the differnecne between the scores
how to found the frequency density in a histogram
you divdie the frequency by the group width.
what is quantitative data
1. data in the formm of numbers.
2. this numberical data can include percentages or frequencies etc.
3. quantitative methods are associated with experiments, questionaires (closed and rating scale questions) and tests (for example Iq and memory tests).
what is qulitative data
1. data in the form of words.
2. uses language/and description to provide rich detail.
3. for example you may write down what people say or do (unstructured), and people's answers to open questions are qualitative.
what are some examples of quantitative data
1. experiments.
2. surveys/questionnaires with closed questions.
3. structured observations with categories.
4. national statistics for example data on prejudice in police.
what are examples of qualitative data
1. unstructured interview.
2. open questions.
3. unstructured free flow observations.
what are the advantages of quantitative data
1. easy to analyse.
2. can look for cuase and effect.
3. you can make comparisons see patterns and trends.
4. can repeat to test reliablity.
what are the disadvantages of quantitative data
1. has no detail - very simple.
2. can distort the truth - it is reductionist - reduces behaviour down to a number (not valid).
3. does not give context i.e. meanings, lack depth and detail.
4. easy to be biased. you are likely to find what you are looking for.
what are the advantages of qualitative data
1. Depth, detail andinsight.
2. More holistic – better understanding of human behaviour.
3. Can get new information with open questions – find out something you hadn’t thought of.
what are the disadvantages of qualitative data
1. Can be hard to analyse.
2. Very difficult to make comparisons.
3. Hard to replicate.
4. Behaviour and interviews open to interpretation – might not be analysed correctly.
what is primany data
If the researcher collects the data themselves through either an observation, experiment, self report or correlation then it is primary data.
what are the advantages of primany data
Data will fit the needs of the experiment as they are collecting it themselves for the purpose of the study.
what are the disadvantages of primary data
1. Can take a lot of time to collect
2. Will cost more for the researcher
3. Could be more biased
what is secondary data
In some studies the researcher might makeuse of data collected by somebody else.
what are the advantages of secondary data
1. Saves time and money by using data already collected.
2. Less open to bias.
what are the disadvantages of secondary data
1. Data retrieved may not be appropriate or fit the needs of the study.
2. Could misunderstand it.
what are the 4 levels of measurement
1. nominal.
2. ordianl.
3. interval.
4. ratio but you don't need to know this one.
what is nominal level data
Nominal Level data is frequency or count data which consists of the number of data points that fall into each category E.G. Number of students who have blue, brown or green eyes.
which average measument is compares well with nomianl level data
mode
what is ordianl level data
Data presented in rank order, with data placed into groups telling us who is first, second and third E.G. Amazon reviews ranging from one to five stars.
which average measument is best used with ordianl level data
median
what is interval level data
Data measured in fixed units with equal distances between the units with no absolute zero E.G. Measuring temperature in degrees Celsius.
which measurment is best used with interval level data
any
what is ratio level data
Data measured in fixed units with equal distances between the units with an absolute zero E.G. Measuring time in seconds.
which measurement is best used with ratio level data
any
what does nominal level data show
frequency
what does ordinal level data show
order
what does interval level data show
real (standardised) numbers