data analysis Flashcards
What is qualitative data
- language based data collected through interviews, open questions and content analysis
- gathered in wirtten form- words!
What is quantitative data
- collected through analysing numerical data
- gathered in numerical form- numbers
Strengths of quantitative data
- gives objective numerical data
- easy to compare findings and draw conclusions
- can predict trends and patterns
Weaknesses of quantitative data
- no emotions/feelings to understand the experience
- no real detail or personal insight
- data collected in artificial settings
Strengths of qualitative data
- allows researchers to develop insights into the nature of subjective experiences, opinions and feelings
- real feel for emotions
Weaknesses of qualitative data
- time consuming to analyse
- not often replicable
What is data
information gathered during the course of a study
What is triangulation
- using a combination of quantitative and qualitative data
- usually using a qualitative method first and then quantitative
What are the 4 stages of conducting an experiment
1) causal observations about a feature of the world
2) these observations will then form a theory
3) theories will produce a number of further explanations
4) experimenter sets out to support or challenge the hypothesis
What is raw data
information gathered during research before any analysis has been done
what is descriptive data
hu
what is inferential statistic
efefj
what is nominal data
-data allocated to categories and frequencies counted under each named heading
-crudest type of data- most uninformative type of data.
doesn’t tell us HOW sunny/rainy it was for example
what is ordinal data?
- involves ranking data into place order, with rating scales often being used to achieve this.
- tells us which are better than the others but doesn’t tell us about distances between athletes
- more informative than nominal but still lacks being fully informative
- distance between 1st and 2nd is likely to differ from 2nd to 3rd
what is interval/ratio data?
- standardised measurement e.g. time, weight, temp, distance
- most sensitive, informative and accurate
- uses equal measurement intervals e.g. a second in time is the same length as any other second
what are descriptive statistics?
refers to the ways data sets can be summarised, described and presented - its not useful for researcher to get raw data, they need a summary
e.g. table, graph, numerical averages, dispersion
what are measures of central tendency?
any way in which a type of average is calculated showing the midpoint or finding a typical value from the middle of the data set e.g. mean, median, mode
what is the mean
average found by adding all data together and dividing by the amount of values
advantages of mean
more sensitive than the median - makes use of all values of data
disadvantage of mean
can be misrepresentative if theres an extreme value (outlier)
what is the median
middle value, when data is placed in order
advantage of median
not affected by extreme scores, outliers, gives a representative value
disadvantage of median
less sensitive than mean, doesn’t take into account all values
what is the mode
the most frequent value
advantage of mode
useful when data is in categories e.g. number of babies securely attached
disadvantage of mode
not a useful way of describing data when there are several modes (bimodal or trimodal)
what are measures of dispersion
shows how spread out the scores in a set are, tells us whether they are similar to one another or whether they vary hugely
what is the range
difference between highest and lowest scores in a set of data
advantage of range
quick and easy to calculate
disadvantage of range
affected by extreme values (outliers), doesn’t take into account all values
what is the standard deviation
average amount that each score differs from the mean
advantage of SD
more precise measure of dispersion because all values are taken into account
disadvantage of SD
much harder to calculate than range
what is a normal distribution curve
bell shaped curve symmetrical which often forms a view of psychological data
mean is midpoint
median and mode either side
68% of normally distributed data is within 1 SD, 95% within 2, almost all (99%) within 3
what is positive skew on normal distribution curve
most values are clustered around the left tail of the distribution
mean is greater than the median and mode
median is middle value
what is a negative skew on a normal distribution
most values are clustered around the right tail of the distribution
mean is less than the median and mode
median is middle value
