sample surveys

22
Sample Surveys Ms. Carter

Upload: mscartersmaths

Post on 28-Aug-2014

1.783 views

Category:

Documents


0 download

DESCRIPTION

 

TRANSCRIPT

Page 1: Sample Surveys

Sample Surveys

Ms. Carter

Page 2: Sample Surveys

SAMPLE SurveysSAMPLE SURVEYS: are designed to ask questions of a small group of people in hope to learn something about the entire population.The POPULATION is the entire group that is being studied. A CENSUS is a survey of the whole population.A SAMPLE is a group that is selected from the population in order to gather information.

Page 3: Sample Surveys

Example:An online poll use voluntary response

samples.

Why would these samples have bias?

Page 4: Sample Surveys

1. SIMPLE RANDOM SAMPLING;A sample size of n is selected in such a way that every possible sample of size n from the population has an equal chance of being selected.

2. STRATIFIED RANDOM SAMPLING; To do this first divide the population into at least two different subgroups so that the individuals or subjects within each subgroup share the same characteristics. Then a simple random sample is drawn from each subgroup and combined to form the full sample.

Types of Sampling

Page 5: Sample Surveys

3. SYSTEMATIC RANDOM SAMPLE;Basically there is a system to applying a random sampling.That is say we wanted to have a sample of size 500 from a population of 10,000, we assign each member of the population with a number. Then we divide the population by the sample size, thus 10,000÷500=20. Now we randomly pick some number between 1 and 20 say 13! Then 13 becomes our starting point and we select every 20th number from 13 onwards.

Page 6: Sample Surveys

4. CLUSTER SAMPLING;For this the population is divided into sections or clusters. Then some of those clusters are randomly selected and all members from those clusters are chosen.

5. QUOTA SAMPLING;In quota sampling the selection of the sample is made by the interviewer, who has been given quotas to fill from specified sub-groups of the population.  For example, an interviewer may be told to sample 50 females between the age of 45 and 60.There are similarities with stratified sampling, but in quota sampling the selection of the sample is non-random.  Anyone who has had the experience of trying to interview people in the street knows how tempting it is to ask those who look most helpful, hence it is not the most representative of samples, but extremely useful.

Page 7: Sample Surveys

6. CONVENIENCE SAMPLING;

Subjects are chosen in the most convenient way possible.

Page 8: Sample Surveys

A marketing expert from RTE is conducting a survey in which 500 people will be selected from each age group of 10-19, 20-29, 30-39 and so on.

Examples: In each of the following, identify the type of sampling used:

Page 9: Sample Surveys

A STRATIFIED RANDOM SAMPLE is used. Here the population is divided into distinct groups and each group is sampled. As all the age groups should contain the same number of people, the same sample size is taken from each group. If the groups or strata were of different sizes, our samples would have to be reflect these proportions.

Solution

Page 10: Sample Surveys

The past pupils association of Colaiste an Phiarsaigh would like to see whether past students would be interested in a reunion. They have obtained a list of all past pupils of the school. They decide to randomly select a sample of people from the list and to use this sample to gauge the interest in the reunion. They randomly select a number between 1 and 20. The person with this number is chosen and then every 20th name from the first selection onwards.

Test Ladies

Page 11: Sample Surveys

• A researcher is testing a new drug. She has already administered the drug to a large number of patients. She now wants to select a sample of 20 from this group. Fortunately, she has just addressed envelopes which all she will use to send information to the patients. She decides to put all the envelopes in a bag and randomly select 20.

• Explain how you would carry out Systematic Random Sampling on a sample of 1000 from a population of 20,000.

Page 12: Sample Surveys

• When choosing a sample from a population, try to ensure:

• That the sample is large enough• That the sample is a random

selection from the population• That everybody has an equal

chance of being selected• As high a response rate as possible

Reliability of Data

If sample data is not collected in an appropriate way, then the data may be unreliable.

Page 13: Sample Surveys

Collecting Data

Page 14: Sample Surveys

Surveys• Face-to-face interviews• Telephone interviews• Sending a questionnaire by

post• Making a questionnaire

available online• Observation

Most Surveys use a questionnaire and can be carried out by:

What do you think are the positives and negatives of each type of survey?

Page 15: Sample Surveys

Survey Advantages

Disadvantages

Face-to face interview

Questions can be explained to the interviews.

- Not random.- Expensive to carry out.

Telephone interview

- It is possible to select sample from almost the entire adult population.- Questions can be explained to the interviewee.

Expensive in comparison to postal and online surveys.

Postal questionnaire

Inexpensive. People do not always reply to postal surveys and those who reply may not be representative of the whole population.

Online questionnaires

- Very low cost.- Anonymity of respondents ensures

more honest answers to sensitive questions.

Not representative of the whole population.Only those who go online and do online surveys are represented.

Observations

- Low cost.- Easy to administer.

- Not suitable for many surveys.- Questions cannot be explained.

Page 16: Sample Surveys

How do we design a questionnaire?

• Be useful and relevant to the survey you are understanding

• Use clear and simple language• Be as brief as possible• Begin with simple questions to encourage

people to complete them• Accommodate all possible answers• Be clear where answers should be recorded• Contain no leading questions• Contain no questions which ask for a

response to more than one topic

A questionnaire is a set of questions designed to obtain data from a population.QUESTIONS SHOULD:

Page 17: Sample Surveys

Homework Check!

1. What are the advantages and disadvantages of using an online questionnaires when carrying out a survey?

2. You are asked to advise a 1st year students on designing a questionnaire, what four points of information would you give them?

Page 18: Sample Surveys

1. What is your favourite sport?(i) Tennis(ii) Rugby(iii)Athletics

2.How far would you travel to see a competitive sports fixture?

(i) Less than 1 km(ii) 5-10 km(iii)Greater than 20 km3. Do you participate in sport ow watch sport on TV?(i) Yes(ii) No

(a) What is wrong with these questions?(b) Design better questions for Britney to use?

Britney wants to gather information on people’s interest in sport. Here is the questionnaire she designs.

Page 19: Sample Surveys

Steps in a Statistical Investigation

1. Define your Research Aims.2. Identify the Population and Sample Size.3. Decide how to Collect the Data.

- Carry out Pilot Survey.

4. Present the Data.5. Analyse the Data.6. Interpret the Results.

Page 20: Sample Surveys

Solution

(a) The question does not allow for all possible sports. While it may not be possible to include all types of sport, it is possible to cater for everybody if an ‘Other’ alternative is included.

QUESTION 1

1. What is your favourite type of sport?(i) Tennis(ii) Rugby(iii) Athletics(iv) Other

Page 21: Sample Surveys

Q UESTION 2.

(a) There are gaps between 1km and 5km and also between 10km and 20km.

2. How far would you travel to see a competitive sports fixture?(i) Less than 1km(ii) 1 - 10 km(iii) Greater than 10km but less than 20km(iv) 20 km or more

Page 22: Sample Surveys

QUESTION 3.

(a) This question needs to be split into two questions.3. Do you participate in sport?(i) Yes(ii) No

4. Do you watch sport on TV?(i) Yes(ii) No