Sampling Techniques

Systematic Sampling

Definition: In systematic random sampling a random starting point is chosen and then every nth individual in selected for the study, where n is the sampling interval. It is used when sampling a fixed percentage of the population.

Steps: Define the population, choose your sample size, assign number to cases, calculate the interval, select the first unit, select your sample

Example:Step One: Preston High School Population- 1100

Step Two: Sample Size - 100

Step Three: Every student in school will be assigned a number from 1 - 1100

Step Four: Calculate the interval: 1100/100 = 11

Step Five: Select the first unit - a student between 1-11 will be chosen e.g. the 5th student, then the 16th student

Step Six: Select the whole sample: 100 students

Advantages: Gets rid of human bias, Highly representative

Limitations: It can only be carried if a complete list is available, list may be formatted, time and money

Longitudinal Study and Cross-sectional study

A longitudinal study is an observational research method in which data is gathered for the same subjects repeatedly over a period of time. These research projects can last years even decades. Also longitudinal studies are mainly observational studies but can also be done as experiments.Longitudinal studies are common in medicine, psychology and sociology, where they allow researchers to study changes over time.

Cross-sectional study is a method of collecting data from different groups of people at a specific point of time, to approximate the prevalence of the outcome of interest for a specific population

Cross-sectional studies are often used in developmental psychology, but this method is also utilized in many other areas including social science and education.

An example of a longitudinal studyis analyzing and studying the way a person’s behavior or opinion changes on a specific topic.

An example in medicine of this would be studying a person with alzheimer's disease

Advantages: The advantages of longitudinal studies are

- it shows pattern of a variable over a long time

-you produce qualitative and quantitative data making research more accurate

Disadvantages: The main disadvantage is its very time consuming.

Also it is really expensive and lastly not many people approve or wanna do it.

While Cross-sectional studies are the complete opposite.

Cross-sectional studies

  • Pros
  • Inexpensive and fast - often obtained using self-report surveys
  • They allow different variables - Researchers can collect data on some different variables to see how differences in sex, age, educational status, and income might correlate with the critical variable of interest.
  • Good for descriptive analyses
  • Can estimate prevalence of outcome of interest because sample is usually taken from the whole population
  • Cons
  • Hard to find specific participants
  • Hard to make conclusion
  • Non-responders
  • Only a snapshot: the situation may provide differing results if another time-frame had been chosen

Summary of Questionnaire Question Types

Closed questions

  • Closed questions invite a short focused answer, answers to closed questions can often (but not always) be either right or wrong.
  • Can be answered with a ‘yes’ or ‘no’
  • Can require that a choice is made from a list of possible answers
  • Identify a certain piece of information

Leading Questions

  • A question that suggests a answer that the questionnaire desires
  • Yes & no type of questions

Loaded Questions:

  • A question that contains a controversial or unjustified assumption
  • Starts a conversation

Open Questions:

  • Open questions allow for much longer responses and therefore potentially more creativity and information.
  • There are lots of different types of open question; some are more closed than others!

Disadvantages and advantages to closed questions:

Advantages:

  • Easier and quicker for people to answer
  • The answers of different respondents are easier to compare
  • People's answers are easier to analyze

Disadvantages:

  • They can evoke ideas that the respondent would not otherwise have
  • Respondent with no opinion or no prior knowledge may not answer
  • Giving the wrong answer is possible and often probable
  • Becomes confusing if many reponse choice are offered

Disadvantages and advantages to open questions:

Advantages

  • Allow for many different answers
  • Allow you to understand the data points and logic that allowed the respondent to form their answer

Disadvantages

  • If the group is big it can take a lot time
  • Not practical for large groups

Advantages And Disadvantages of Leading Questions

Advantages:

  • Help you get the answer you want
  • Directs people to the path you wanna talk about
  • Good if you want confirmation on something

Disadvantages:

  • Can render your data unusable
  • Opens to questioning things

Cluster Sampling: Divide a population into groups called clusters and randomly choose groups to analyze.

Ex: Analyzing the population of spain by breaking the country down into groups called clusters and analyzing randomized clusters.

Destructive sampling: Method in which the sample is destroyed or permanently altered in the process of random sampling

Ex: testing the breaking strength of lightbulbs by putting a measured force on the bulbs till they crack.

Stratified Sample

Definition: Stratified sampling is a probability sampling technique wherein the researcher divides the entire population into different subgroups or strata, then randomly selects the final subjects proportionally from the different strata (or researcher simply divides the population into groups called strata, from then on, probability samples are drawn from each group).

Example 1 (Proportionate Stratified Sampling): Four strata with population sizes of 200, 400, 600, and 800. If you choose a sampling fraction of ½, this means you must randomly sample 100, 200, 300, and 400 subjects from each stratum respectively. The same sampling fraction is used for each stratum regardless of the differences in population size of the strata

Example 2 (Disproportionate Stratified Sampling): The different strata do not have the same sampling fractions. Four strata contain 200, 400, 600, and 800 people, you may choose to have different sampling fractions for each stratum. First stratum with 200 people has a sampling fraction of ½, resulting in 100 people selected for the sample, while the last stratum with 800 people has a sampling fraction of ¼, resulting in 200 people selected for the sample.

Advantages:

  • Reduces selection bias
  • Ensures each subgroup within the population receives proper representation within the sample

Disadvantages:

  • Cannot be used in every study
  • A challenge is accurately sorting each member of the population into a single stratum

The sorting process can become difficult

Voluntary Response Sampling

-Only includes people who want to volunteer- SELF SELECTED

-Typically get ‘like minded people’ (strong opinions) making the data set biased

ADV.

  • Not time consuming
  • Minimal effort
  • Easy & fast
  • More useful when you want to pinpoint a certain subgroup to survey within a population

DISADV.

  • Not trustworthy
  • The sample is likely to be comprised of strongly opinionated people
  • Cannot be generalized

Examples:

  1. Television viewer polls
  • When programs like American Idol ask viewers to call in and vote for their favourite singer, this is an example of voluntary response sampling
  • Only those who want to call in and be part of the sample will contribute (not everyone watching must participate)
  1. A radio host survey
  • Asks his listeners to visit his website and respond to an online survey
  • People who take the time to complete it tend to have similarly strong opinions compared to the rest of the population, thus making it bias

Simple Random Sampling

-Each member of subset has an equal probability of being chosen

- Include people whether or not they want to volunteer

- Used to avoid unwanted effects because of equality

ADV.

  • Random samples are usually fairly representative since they do not favour certain members
  • Reduce potential for human bias

DISADV.

  • Diverse opinions and data
  • Can be costly
  • Time consuming

Multi-Stage Sampling

  • Multi-Stage Samplingdivides large populations into stages to make the sampling process more practical.

Advantages

  1. Simplification
  • Avoids random sampling from a population that is larger than the researchers resources can handle.
  • As long as the groups have low between-group variance, this form of sampling is a legitimate way to simplify the population
  1. Flexibility
  • Researchers can break down groups and subgroups into smaller groups until the desired type or size of group is reached.
  • No restrictions on how to divide the population into groups.

Disadvantages

  1. Arbitrariness
  • The flexibility of multi-stage sampling has a lack of restrictions on the decision making processes involved in choosing groups.
  • There will always be questions as to whether the chosen groups were optimal.

2. Lost Data

  • Cuts out portions of the population from the study, the study's findings can never be 100% representative of the population.
  • No way to know if the demographics cut from the study could have provided any useful information.

Examples:

Evaluating Spending Patterns of Households

  • Choose provinces using probability sampling.
  • Choose districts within each province using probability sampling.
  • Choose households from each district using random or systematic sampling methods.

Evaluating Acre Usage with Farms

  • Examine acre usage in provinces.
  • Examine acre usage in regions.
  • Examine acre usage in towns/cities.
  • Examine acre usage on individual farms.

Convenience Sampling

  • Type of non-probability sampling method where the sample is taken from a group of people easy to contact or to reach.
  • Researchers select the research sample based on ease and proximity to the researcher. This is different from random sampling.

Advantages

Cost and Time efficiency

  • Few rules governing how the sample should be collected.
  • Cost and time required to carry out a convenience sample are small in comparison to probability sampling techniques. This enables you to achieve fast and inexpensive samples.

Simplicity

  • Gathers useful data and information that would not have been possible using probability sampling techniques.
  • Helpful for pilot studies and for hypothesis generation

Disadvantages

Generalized Sampling

  • Since the sample is not representative of the population, the results of the study cannot speak for the entire population.
  • This undermines your ability to make generalisations from your sample to the population you are studying.

Bias

  • It is not rare that the results from a study that uses a convenience sample differ significantly with the results from the entire population.

Examples:

  • One of the most common examples of convenience sampling is using student volunteers as subjects for the research

Clinical Surveys

  • Using subjects that are selected from a clinic, a medical study group, or an institution that is easily accessible to the researcher.

Questionnaire Question Types:

Information question, checklist question, ranking question, and rating question

Information Question: Collecting information from the respondents other than personal opinions (i.e. Who, What, Where, and When?)

(e.g. what time did you attend our restaurant?)

Checklist Question: A series of yes/no questions

(e.g. check all of the following that apply…)

Ranking Question: Ranking of comparable items

(e.g. Please rank the following ice cream flavours:

_Chocolate Chip

_Caramel Swirl

_Cookies and Cream

_Rocky Road

_Neapolitan

_Vanilla

Rating Question: Respondents assess the question on a one-dimensional scale

(e.g. how satisfied were you with your food?  Very satisfied, somewhat satisfied, neutral, somewhat dissatisfied, very dissatisfied)