statistics Flashcards
What are the types of data and what can they be broken down into
Quantitative - numerical - levels of measurement
- > ordinal, nominal & interval
Qualitative - language
Primary -
Collected specifically for researcher
Secondary
Collected by someone other than the person who is conducting the research -> meta analysis
What is meant by the term quantitative data (2)
This is data that is expressed numerically (1).
This type of data can be gained from individual scores in experiments, such as the number of words recalled or the number of seconds it takes to complete a task or from self report methods and the use of closed questions (2)
The data is open to being analysed statistically and can be easily converted into graphs, charts etc.
What is meant by the term qualitative data (2)
Qualitative data is expressed in words/ is descriptive data (1)
and may take the form a written description of the thoughts, feelings and opinions of participants such as from a notes recorded within an interview, a diary entry or answers from open questions in a questionnaire (2)
Qualitative methods are concerned with the interpretation of language.
What is discrete data
Information/findings that can be categorised into groups, the data can only appear in one category. It can’t be sub-divided i.e. it needs to be whole numbers e.g. 25/30 on test.
What is continuous data
Data that can be measured using scientific tools e.g. height, weight, time.
What are the 3 types of quantitative data
Nominal - discrete
Ordinal - discrete
Interval - continuous
What is nominal data
Data in the form of categories
For example: you can count how many boys and girls are in your year group - male and female are the categories and you take a count of how many in each group
Other examples: hair colour, people’s favourite football team.
What is ordinal data
Ordinal data is ordered/ranked in some way e.g. from highest to lowest
e.g. 19, 2nd, 3rd
Ordinal data does not have equal/fixed intervals between each unit
E.g. if you were asked to rate your enjoyment of Psychology on a scale of 1-10, what is the difference in the amount of enjoyment between 6 and 7?
Data based on subjective opinions are an example of ordinal level data.
E.g. rate how much you enjoy psychology out of 10 (1 being ‘I do not like psychology, 10 being “ love psychology. If two people say ‘8’ they may have different opinions of what an 8 is.
Another example of ordinal data would be the amount of items recalled in a a memory test or score on an IQ test.
For these reasons, ordinal data is often known as ‘unsafe’ data due to its lack of precision and is not used as part of statistical testing. Instead raw scores are converted to ranks (15, 2”, 3”°) and it is the ranks, not the scores, that used in the calculation for the statistical test.
What are the key features of ordinal data
Ordered / ranked
Does not have equal/ fixed intervals
Subjective opinions
What is interval data
Data is a STANDARDISED/UNIVERSAL/OFFICIAL measurement.
Data based on objective (factual) measures e.g. time in seconds, height in centre metres
Interval is based on numerical scales that include units of equal, precisely defined size.
What is meant by the term secondary data (2)
Secondary data has previously been collected by a third party (1)
(another researcher or an official body), not specifically for the aim of the study, and then used by the researcher (2).
E.g. preexisting data such as Government statistics.
What is meant by the term meta-analysis (2)
A meta-analysis is a form of research method that uses secondary data (1) as it gains data from a large number of studies, which have investigated the same research questions and methods of research. It then combines this information from all the studies to make conclusions about behaviour (2)
Breakdown of analysing data
Quantitative -> inferential statistics -> descriptive statistics
Descriptive statistics -> central tendencies -> mean, median, mode
Descriptive statistics -> measures of dispersion -> range, standard deviation
Qualitative -> content analysis -> thematic analysis
Content analysis -> coding
Thematic analysis -> emergent themes
What are the two ways of analysing data
Content analysis
Thematic analysis
What does content analysis observe
Usually makes observations indirectly through books, films, advertisements, interview transcripts and photographs.
What is content analysis (2)
This is a method of analysing qualitative data by changing large amounts of qualitative data into quantitative (1)
This is done by identifying meaningful codes that can be counted enabling us to present the data in a graph (2)
Why is it appropriate to use content analysis (1)
The data (name what the data is from the scenario given e.g. video recordings) being analysed is qualitative data. (1)
What is meant by coding (1)
Coding is the initial process of a content analysis where qualitative data is placed into meaningful categories.
How is content analysis carried out/ explain how you would analyse qualitative data (4)
Read /view the video or transcript (link to whatever qualitative data it refers to in the scenario) (1)
Identify/create coding (categories) provide an example of a relevant category (1)
Re-read the diaries/ questionnaire or repeatedly listen to sections of the recording (choose appropriate one in relation to the scenario) and tally every time each code appears (1)
Present the quantitative data in a graph/table (1)
What is thematic analysis (2)
This is a method of analysing qualitative data by identifying emergent (keep cropping up) themes enabling us to present the data in a qualitative format.
E.g. Interview recordings, presentation/conversation, diary entries, newspapers, texts, social media, radio and tv ads.
How is a thematic analysis carried out (2-4)
If the data in the scenario is not already a transcript: watch the video or listen to recordings to create a transcript of (contextualise e.g. refer to specific data in scenario such as interview about aggressive behaviour) * (1)
Read & re-read transcript (familiarisation)
Identify coding (categories) - looking for words which cropped up repeatedly. (1)
Combine these codes to reduce the number of codes into three or four themes that are linked to (contextualis e.g. what is the topic being studied?/ Provide an example of a potential theme) (1)
Present the data in qualitative format not quantitative. (1)
Ways to assess reliability of content analysis
Test re-test
Inter-rated reliability
test re-test
- The researcher completes the content analysis by creating a series of coding categories, (provide an example category that links to scenario) and tallying every time it occurs within the qualitative data.
- Then the same researcher repeats the content analysis on the same qualitative data e.g. interview, tallying every time the coding category occurs.
- Compare the results from each content analysis
- Then correlate the results from each content analysis using stats test.
- A strong positive correlation of above +0.8 shows high reliability
Inter-rather reliability
- The two raters would read through the qualitative data seperately and create coding categories together. INCLUDEEXAMPLE OF CATEGORY HERE
- Two raters read exactly the same content (contextualise e.g. what is the content? but record/tally the occurrences of the categories separately.
- They(compare the tallies from both raters
- Which are then correlated using an appropriate stats test.
- A strong positive correlation shows high reliability (+0.8).