Chapter 52- Identifying customer needs: Market research analysis Flashcards
What needs consideration once the initial market research plan on how the information is to be collected is in place?
- Consideration needs to be given to the sampling method used
- If they don’t have enough data, then the results won’t be accurate
- To improve the likelihood of gaining reliable data there are several sampling techniques that can be applied
What are the two types of sampling?
- Probability
- Non-probability
Definition of population
- The total number of items or people that research is interested in
Probability sampling methods
- it gives all the members of the population a
known chance of being selected for inclusion in the sample
Simple random sampling
- Individuals are randomly selected from a list of the population
- Every single individual has an equal chance of selection
- this method insures that there is no bias in choosing the sample
- This method is very slow and expensive
Systematic sampling
- It’s a variant of the simple random sampling method
- When using this method, every ‘nth’ person from the list is selected
- A potential problem with this method of sampling concerns the arrangement of elements in the left
Quota sampling
- It involves splitting the population into subgroups according to the distribution in the population
- Example: 52% of a given population is male and 48% is female the samples that are questioned will be in this proportion
- This method is the cheapest and most effective method of sampling
- It’s a non-random form of sampling, so the results are not statistically representative
Convenience sampling
- Uses those people who are easy to do
- example: if doing house to house the researcher may only do those that are at home when they call on that day
- It may not consider everyone
- This method can cause the results of convenient sampling to be distorted
Stratified sampling
- only interview those with key characteristics
- This method can be then used with the quota and random method to breakdown the information further
- it is an effective way to target your specific customer
- This method means that others who may have an opinion on the product are not included as they do not fit the sample characteristics
- Stratified sampling methods also come in 2 types- proportionate and disproportionate
Proportionate sampling
- The strata sample sizes are in proportion to the strata population sizes
- Example: if the first Statum is made up of males then as there are around 50% of males in the UK population the male strata will need to represent around 50% of the total sample
Disproportionate sampling
- The strata are not sampled according to the population sizes but higher proportions are selected from some groups and not others
Cluster sampling
- Respondents drawn from a small geographical area selected to represent a target population as a whole
- This method makes sampling quicker and easier as the respondents are all in one area ( used when data is needed quickly )
- This method may be unreliable if area chosen is not representative of the target population
Non– sampling errors
- Respondent may give the answer they think is being asked for
- It’s usually a politically or socially accepted answer
- But it’s not a honest answer that reflects what they actually think
- May give the first answer that comes into their head when the respondent is in a hurry
- Deliberate false answer may be given
- occasions when respondents give an answer that they think will please the interviewer
Sampling errors
- It’s the difference between the mean value of the sample and the actual or true mean value of the population
- example:
Mean value of sample= 25
Actual meaning of population= 26
Sampling error= 1 - As sampling size increases sampling error falls
What is the average or mean also referred to as?
- Central tendency
How do you calculate the mean?
- Together the aggregate and divide by the number of results
Normal distribution
- when looking at the results of any research, the data can be considered in terms of how it is distributed
- Distribution is bow shaped
- Most figures fallen in the middle
- To consider the distribution of the data still further it can be compared to the mean (average).
Standard deviation
- This measures the spread of data compared to the mean
- It measures how far from the mean any finding, observation or response is, and can therefore be used to assess whether the result is roughly in line, more than, or less than the average or mean
- the closer the results are to the mean the narrower the spread of data is
- A large standard deviation suggest there is a wider spread around mean
How do you work out standard deviation?
- Calculate the mean
E.g. 36 - Find out how far each value deviates from the mean (compare to 36)
- If less than the mean, it will be a minus number and if more than the mean, it will be a positive number
- Square all the numbers
- once the numbers are squared they are added together and divided by the number of units
- square root this answer
What does standard deviation show?
How far away from the mean any result is
What does correlation mean?
- It’s a term used to show how closely two factors or variables are linked to each other
How can a future trend be seen?
- once the figures have been plotted, it’s possible to continue the line
-the data is extrapolated
Market segmentation
- After research to find out about its customer base, it can begin to split its market into different groups
- Each group will have different characteristics and needs
What does knowledge of different groups within a potential customer base help the business with?
- it can help the business to target those consumers