Social Research Methods Flashcards
what is reliability?
this refers to the consistency of data - if the research is reliable we would expect that if it were repeated, with similar types of participants in similar circumstances, the same results would be obtained
what is validity?
does the research actually measure what it is supposed to measure?
what is subjectivity?
this refers to the interpretation of data: could participants’ data be interpreted differently, is the interpretation of data completely free from bias?
what is objectivity?
essentially the opposite of subjectivity, is data able to be interpreted in such a way that it is deemed unbiased, untainted by attitudes, beliefs and values of the researcher
what is induction?
using known facts to produce general principles - moving from the specific to the general, i.e. general principles are inferred from specific cases
what is deduction?
using existing knowledge or assumptions to reach conclusions or understand something - moving from the general to the specific case, i.e. using existing theories and applying them to a specific case to explain it
what is qualitative data?
descriptive, non-numerical information, such as that generated by open-ended questions, unstructured interviews etc
what is quantitative data?
information is numerical in nature, such as that generated by closed questions, likert scales etc
what type of data do surveys like questionnaires and interviews generate?
self-report data, i.e. information elicited from questions which relies on the participants reporting their own behaviour, feelings, attitudes etc
what is the problem with the samples generated by surveys?
surveys reflect a number of biases, e.g. who can be bothered to complete them - also we tend to engage only with topics we care about, hence the fact that those who completed the survey care about the topic might make their responses unrepresentative
what kind of questions do interviews contain?
interviews can contain open and closed questions, although closed questions are rare
what are closed questions?
limited responses, participants select answer that applies to them: 1 word, yes/no answers, likert scales, multiple choice - yields quantitative data
what are open questions?
can be answered how participant chooses, without restriction - words not numerical response, allows participants to explain answers and express opinions, yields qualitative data, may generate unexpected content that gives researchers new lines of enquiry
where can self-report data come from?
open and closed questions and likert scales - this gives participants more flexibility in their responses, whilst still being easy to interpret and statistically analyse
what is a strength of likert scale questions?
easy to analyse and compare data, less time consuming than interviews so may get more participants and so more data
what is an unstructured interview?
questions are open-ended, not systematic, each question depends on answers given previously - qualitative data
what is a semi-structured interview?
is a schedule of questions but some flexibility to expand on responses
what is a structured interview?
systematic, standardised pre-set questions asked of every interviewee
why do psychologists rely on sampling methods?
the whole target population cannot be tested, so psychologists rely on sampling methods to recruit a representative sample of the target population
what is random sampling?
every member of the target population has an equal chance of taking part in research, like names being drawn out of a hat
what is stratified sampling?
a proportional representation of the target group, e.g. if target group has 60% males and 40% females our sample will have the same proportion of males and females
what is a volunteer/self-selected sample?
participants select themselves, e.g. respond to advert
what is an opportunity sample?
participants selected from whoever is available at the time
what is thematic analysis?
a technique used to identify patterns, trends and themes within qualitative data
what are measures of central tendency?
refers to the idea that one number can be used to represent the general trend or pattern in a set of numbers, i.e. represents the typical number or score
what is the mean?
this is the arithmetic average - often used with interval or ratio data
what is the median?
this is the middle number of a set of scores after they have been put in numerical order, exactly half the scores are above this number and half below
what is the mode?
this is the most frequently occurring number in a data set; there can be more than one mode in a data set: bimodal and multimodal
what are descriptive statistics?
they describe and summarise the data collected in research: measures of central tendency and measures of dispersion are ways of describing statistical information
what is the standard deviation?
a sophisticated measure of dispersion, as its calculation takes into account all numbers in a data set - it shows how much each score in a data set deviates on average from the mean of that set of data - it is the mean distance of scores from the mean of a set of scores
when is the range normally used?
when the median is the measure of central tendency
what is a problem with how the x axis could be manipulated?
the horizontal x axis could be manipulated to distort the graphical representation of data, e.g. on a bar graph bars may be distorted so that sample groups are of different sizes, so the resultant bars produce a distorted analysis, e.g. taxable income, bars might start with a £5000 range but then represent much bigger income variations, e.g. £30,000 range
what is a bar graph?
is used when the data is in discrete categories, rather than a continuous variable as with histograms and line graphs
when is a histogram used?
is used to present data that is continuous and occurs as a frequency, e.g. age of children and observed acts of aggression displayed
when are scattergraphs used?
these are used to show relationships between variables - two variables are used to plot scattergraphs: one score will be variable y on the vertical axis and the other score will be variable x on the horizontal axis
what does a frequency table show?
how many times - the frequency - the scores occurred in the data set
what are the three most important distributions?
normal distribution, positively skewed distribution and negatively skewed distribution