Research methods 2:

qualitative data

qualitative data

non numerical data, opinions and thoughts from a subjective experience

quantitative data

numerical data: scores, scales ranks, etc

Advantages of qualitative data

• more in depth and detailed

• providing a better insight into ops or individual experiences

disadvantages of qualitative data

• time consuming

• difficult to analyse

• subjectivity and lacks generalisation

advantages of quantitative data

• easy to compare and analyse

• objective

disadvantages of quantitative data

• lacks detail

• a descriptive stat that doesn't tell you why

primary data

information collected for the specific purpose at hand

secondary data

information that already exists somewhere, having been collected for another purpose

advantages of primary data

• fit for purpose

• increased validity and reliability

disadvantages of primary data

• time consuming

• needs to be reviewed before publication

advantages of secondary data

• quick and easy to access

• already been peer reviewed

disadvantages of secondary data

• lacks validity (unable to check methods)

nominal data

qualitative values - usually tallied - not able to rank

ordinal data

scaled or ranked data, will be subjective, often seen as score

interval data

ranked data with equal measurement intervals

ratio data

same as interval data but has an absolute zero

central tendency

any measure of the average value in a dataset

Most common measures of central tendency

mean, median, mode

dispersion

Any measure of the spread or variation in a set of scores

most common measures of dispersion

range and standard deviation

bar chart

nominal data only (separated bars)

Histogram

continuous data (ordinal, interval, ratio)

no gaps needed between bars

contingency table

raw scores displayed in columns and rows

scatter graph/scattergram

provides a good visual picture of the relationship between 2 variables

negatively skewed distribution

more values are concentrated on the right side (e.g mean, median, mode)

positively skewed distribution

more values are concentrated on the left side (mode, median, mean)

normal distribution

mean, median, and mode are all the same/very close to one another

probability

• likelihood that a particular event will occur

• between 0 and 1

psychologists typically use this significance level

p<0.05

when challenging well known theories psychologists tend to adopt this significance level

p<0.01

Proof

doesn't exist in psychology unless 100% accuracy is found

Type 1 error

False Positive; Rejecting the null hypothesis when it is true

Type 2 error

False Negative; Accepting the null hypothesis when it is false

The mnemonic to remember the test table

Carrots Should Come, Mashed With Swede, Under Roast Potatoes

Why referencing is important

• enables the reader to track down the sources used

• can avoid plagiarism

• gives the authors the credit

Harvard referencing order

Author, Year, Title, Edition, Place, Publisher