Section 3: Data Handling and Data Analysis Flashcards
what is quantitative data?
numerical data (data in the form of numbers)
quantitative data collection techniques tend to be more tightly controlled in order to produce precise numerical measures
for example:
- experiments such as laboratory experiments tend to measure the DV quantitatively (eg. number of words recalled from a list, or reaction time),
- the use of closed questions in a questionnaire (eg. number of hours revising per week, or ratings)
- behavioural catergories in an observation
…are all quantitative in nature
what is qualitative data?
non-numerical data
usually data in the form of words (eg. a transcription of an interview) but could be any non-numerical data (eg. a drawing)
qualitative data collection techniques are often used when more depth or detail is required and where tight control and precise measurements would be seen as unrepresentative and limited (eg, when analysing more complex thoughts, feelings and opinions)
for example:
- interviews are more likely to produce more detail and elaboration than questionnaires
- observational studies where written records are made rather than simply counting behavioural categories such as case studies
difference between quantitative and qualitative data
quantitive data is numerical data (data in the form of numbers) whereas non-numerical data is usually data in the form of words (eg. a transcription of an interview) but could be any non-numerical data (eg. a drawing)
quantitative data collection techniques tend to be more tightly controlled in order to produce precise numerical measures. for example, experiments such as laboratory experiments tend to measure the DV quantitatively (eg. number of words recalled from a list, or reaction time), the use of closed questions in a questionnaire (eg. number of hours revising per week, or ratings), and behavioural catergories in an observation are all quantitative in nature. whereas qualitative data collection techniques are often used when more depth or detail is required and where tight control and precise measurements would be seen as unrepresentative and limited (eg, when analysing more complex thoughts, feelings and opinions). for example, interviews are more likely to produce more detail and elaboration than questionnaires, and observational studies where written records are made rather than simply counting behavioural categories such as case studies
explain the overlap between quantitative and qualitative data collection techniques
researchers collecting quantitative data as part of an experiment may often interview their ppts as a way of gaining a more detailed insight into their experience of the investigation
likewise, there are a number of different ways of converting qualitative data into quantitative data in order to analyse the data in a clearer way
what is primary data?
primary data refers to original data that has been directly observed and collected specifically of the purposes of the investigation by the researcher
it is data that arrives first-hand from the ppts themselves
for example, data gathered from your own experiment, questionnaire, interview of observation would be classed as primary data
what is secondary data?
secondary data refers to data that has been collected by someone other than the person conducting the research
in other words, this is data that already exists (second-hand data) before the psychologist begins their investigation
for example, data from research journals, books, websites, government data (eg. population records) or data held within organisations (eg. population records) or data held within organisations (eg. employee absence rates) would be classed as secondary data
a meta-analysis is also secondary data
strengths of primary data
- can control the quality and accuracy of data (eg can standardise to ensure high validity)
- can ensure data covers research objective (firm conclusions can be drawn)
limitations of primary data
- difficult to access data as it does not already exist, so it is time consuming
- significance not known as there is limited prior research (statistical tests needed)
strengths of secondary data
- easy to access data as it already exists, so it saves time
- significance is already known from prior research (no statistical tests needed)
limitations of secondary data
- cannot control the quality and accuracy of data (eg cant ensure high validity)
- cannot ensure data covers research objective (unable to draw firm conclusions)
what is a meta analysis
a meta analysis refers to the process of combining results from a number of studies on a particular topic to provide an overall view
it is a form of secondary data because the data is not gather first-hand from the researchers own research
a meta-analysis may involve a qualitative review of conclusions (i.e. a discussion) and/or a quantitative analysis of the of the results producing an effect size across the different studies
advantage of a meta-analysis
P: easier to gather results on a large scale
E: because meta-analyses draw findings together from a range of studies, each with their own samples of ppts, it is easier to gather results which represent a wider, more representative sample than most single studies can
E: eg, research can consider studies of a similar type conducted in many countries to compare effects of a particular variable cross-culturally
L: allows us to view the data with more confidence and the findings may be said to be higher in population validity
disadvantage of a meta-analysis
P: may suffer from the file-drawer effect
E: meta-analysis research relies on the researcher selecting a series of studies in order to analyse the overall view, but this process of selection can be open to researcher bias
E: eg, the researcher may choose to leave out any studies which do not support their hypothesis
L: the results would be biased and not a true reflection of the research rate
types of descriptive statistics
- measures of central tendency
- measures of dispersion
what is raw data?
when you carry out research, the results you generate are known as raw data
why may you need to calculate a measure of central tendency or summarise data
when you carry out research, the results you generate are known as raw data
there did often so much raw data it becomes difficult to see an overall effect or pattern
as a result, the data often needs to be summarised so that you can clearly see the effects
measures of central tendency
- mean
- median
- mode
what is the mean?
a measure of central tendency where all scores are totalled & divided by the number of scores
this is the only measure of central tendency that includes all the data/scores in the calculation
what is the median
a measure of central tendency in which scores are placed in rank order and the middle value is taken
if there is an even number of scores, the midpoint between the two middle scores is taken
