chapter 1 Flashcards
what is bivariate data
Data that is made up of two variables
What is multi variate data
data that is made up of more than two variables
What is the difference between PMCC and Spearman’s rank correlation
PMCC measures the strength of linear correlation while spearman’s rank correlation is used for ranked data or paired data.
what are the pros and cons of random sampling
pros
every member of the population has an equal chance of being picked
it is completely unbiased
the sample should represent resent the whole population
cons
it’s not always practical or convenient (if the population is spread over a large area it will take a while)
It might be impossible to list the whole population
There are two types of random sampling methods, explain both
Simple random sampling
assign a number to every member in the sample frame
use any material (calculator number generator) to create a list of random numbers
match up the numbers of the members in the sample frame to the numbers on the random list to create sample.
Stratified sampling
split the group into different categories (strata)
Calculate the number of people to sample from each strata using (strata/total number x sample size)
Use random sampling to the sample members from each category
When should you use simple random sampling
When you have a small, well-defined population
When should you use stratified sampling
When people of different groups are likely to give different results
eg. Younger and older people have different opinions about different films so both need to be represented
When do you use systematic sampling
When the population is very large
What is systematic sampling
choosing a random sampling point
taking a sample at regular intervals afterwards (every nth item)
What are the pros and cons of systematic sampling
pros
should produce an unbiased sample
can be carried out by a machine
cons
sample could end up biased
what is cluster sampling
Create many clusters (a group where everyone shares the same characteristic) and then choose at random one cluster
Pros and cons of cluster sampling
Pros
it’s convenient
saves time
cons
can easily be biased
What is quota sampling
The population is divided into groups these groups could be based on age, gender and so
The interviewer is told to interview a certain number of people from each group
What are the pros and cons of quota sampling
pros
It’s quick to use
represents each population
cons
can be biased
what is Opportunity sampling
Where a sample is taken from a section of the population present at one particular place and time
Pros and cons of opportunity sampling
pros
it’s easy
doesn’t take time
cons
there is no attempt to make the sample representative so it could be biased
In questionnaires what are closed questions
They have a fixed number of possible answers
You can easily process the data being collected
but the answers are limited to the options given
In questionnaires what are open questions
Questions that allow any answers
they are good to help gather more information
but are harder to process because of a wide range of answers
What should and shouldn’t you do when designing questionnaire questions
Don’t put leading questions
don’t put biased questions
or sensitive questions
know that people may not answer truthfully
include a wide range of answers options
questions should be relevant
questions should be easy to understand
What are the pros and cons of questionnaires
pros
cheap
quick
shouldn’t be biased
likely to be truthful
lots of ways to distribute them
cons
if wrong questions it could be biased
a lot of non-responses
questions might not be understood
How do you test your questionnaire
With a pilot study, this is where you test out your questionnaire on a small group first
How can we tackle sensitive questions
With the random response technique
what is a the explanatory variable?
The variable you are in control of
What is the response variable
The variable you measure.
It changes in response to the explanatory variable