Research Methods - Data Handling and Analysis Flashcards
What is central tendency?
- How sets of results are analysed and measured
- There are three sets of central tendencies - mean, mode and median
- They aim to find the middle value of research
What is the mean?
- Calculated by adding up all the data and dividing it by the number of readings
- Advantage - takes all the data into consideration when calculating
- Disadvantage - extreme readings can have a huge effect on the mean, making it an invalid reflection of results
What is the median?
- The central number in a set of results, found by ordering the results from smallest to largest and finding the middle one
- Advantage - not affected by extreme results
- Disadvantage - It doesn’t give an accurate result with varied or small sets of results
What is the mode?
- The most frequently recurring result in the data
- Advantage - not affected by extreme results
- Disadvantage - It is not a central measure as the mode can occur at extremes
What is quantitative and qualitative data?
Quantitative - numerical, objective, reliable
Qualitative - deep understanding, subjective, literacy based
Strengths
- Quantitative data
- Easy to analyse and interpret as the data is numerical
- The techniques used are easy to replicate and so it has high reliability - Qualitative data
- Gathers in-depth data, which is meaningful and detailed.
- The broader scope means that it had high construct validity
Limitations
1. Quantitative data
- Narrow in scope so consequently lacks ecological
validity making it hard to generalise
2. Qualitative data
- As the data tends to come from individual or small
group investigations it can be difficult to
generalise the findings
Primary data, secondary data and meta-analysis
- Primary data is data collected first hand by the researcher carrying out experiments, self-reports, observations and correlations.
- The main the advantage of using primary data is that it has been specifically designed for a particular investigation.
- However, this is time consuming and costly. - Secondary data has been collected by other researchers, using the same techniques and has already been subject to data analysis. This is then used as part of another study to support or reject a new research hypothesis.
- This data is easily accessible making it a quick and cheap option,
- but as it is not specific to the new research it may not quite be fit for purpose. - Meta-analysis is a powerful method that researchers use to analyse secondary data from many studies, all with similar research hypotheses, in order to develop a single conclusion that has greater statistical significance. This can be achieved through analysing qualitative data, by simply discussing the findings or conclusions or carrying out detailed statistical analysis of the previous qualitative data.
- If findings support the research hypothesis the researcher is able to generalise the findings to a wider population.
- However, meta-analysis can be subject to researcher bias as they may only choose the studies that support their research hypothesis.
What is dispersion?
The researcher also has to consider how spread out the data is; this is known as the measure of dispersion. It is measured with the range and the standard deviation.
- Range - calculated by subtracting the lowest score from the highest score.
- For example, if the highest score was 10 and the lowest score was 1, the range would be 9.
- A strength is that it is easy to calculate
- A limitation is that the range may not be very representative because the two most extreme values are used to calculate it.
- Standard deviation - measures how much the scores deviate from the mean in a normal distribution.
- A low standard deviation indicates that the data points tend to be very close to the same value (the mean); while high standard deviation indicates that the data are “spread out” over a large range of values.
- A strength is that it uses all the scores in a set of data and is therefore more precise than the range and so is the best measure of dispersion to use.
- A limitation is that it can be distorted by outliers
Graphs
Graphs are used as a visual description of the data collected in an investigation and how it is distributed.
- a visual representation of a relationship between two variables, x and y.
- two axes called the x (horizontal) and y (vertical) axes. These axes correspond to the two variables.
- The point where the two axes intersect is called the origin. The origin is also identified as the point (0, 0).
Bar charts
Bar charts consists of rectangular bars of lengths proportional to that value that they represent. Bar charts are used for comparing two or more values. The bars can be shown horizontally or vertically oriented and are not touching as they represent discreet categories
Histograms
Histograms show the frequency of continuous data and this is represented by the bars touching each other. They are an alternative to the line graph, which would show each piece of data plotted individually, as they group large amount of data into class intervals.
Line graphs
Lines graphs are often used to show a trend over a number of days or hours, therefore represents continuous data. It is plotted as a series of points, which are then joined with straight lines. Typically the IV is plotted on the X axis and the DV is placed on the Y axis. The ends of the line graph do not have to join to the axes.
Distributions - types
- In a representative sample, a bell-shaped curve, with the median, mode and mean all in the middle of the curve
- If you don’t have a representative sample, i.e. your participants are not distributed normally, this will result in a skewed distribution where the spread of frequency data is not symmetrical and is skewed to one end and can be positively or negatively skewed
- Positive skew - The long tail is on the positive side, skewed to the right, and the mean is on the right of the mode
- Negative skew - long tail on the negative side, skewed to the left, mean on the left of the mode
Correlations
A correlational study is probably the most common type of non-experimental design. It is used where you are specifically looking at the relationship between two variables. The outcome of the investigation is known as the correlation coefficient, which shows the direction and strength of the relationship
Correlations differ from experiments in the following ways:
- They don’t manipulate an IV but look at the relationship between two co-variables
- They don’t establish cause and effect, but look at the strength of the relationship known as the correlation coefficient
- The aim of an experimental investigation is to determine if there is a difference, whereas the aim of a non-experimental investigation is to determine if there is a relationship between two co-variables (V1 & V2)
- An experimental hypothesis tests for a difference, whereas an alternative hypothesis tests for a relationship between two variables
Correlational analysis
Correlational analysis can only be carried out on quantitative data as essentially it is a statistical test for a relationship between two co-variables. Therefore, it is essential to operationalise the co-variables to ensure that they are clearly defined and measurable.
- The analysis measures the strength and direction of the relationship between the two co-variables.
- The relationship can be illustrated either graphically through scattergrams or analysed mathematically with a correlation coefficient, which is always between +1 and -1.
Correlation directions
The direction of the correlation can be categorised in to positive (+), negative (-) or a zero correlation.
- A positive correlation; as the variable on the y axis increases, so does the variable on the x axis. A perfect positive correlation has a correlation coefficient of +1.
- A negative correlation; As the variable on the y axis increases, the variable on the x axis decreases. A perfect negative correlation has a correlation coefficient of -1.
- No correlation - Therefore, there is no relationship between the variables and the correlation coefficient is zero.
