Please enable JavaScript.
Coggle requires JavaScript to display documents.
Scale, Reliability, Validity & Sampling - Coggle Diagram
Scale, Reliability, Validity & Sampling
-
-
Theory of Measurement - Use math to combine what we know about reliability and validity, based on classical test theory (also called true score theory).
Random - Mistakes in measurement caused by random, unpredictable factors that affect some results but not others.
Systematic - Mistakes in measurement caused by factors that consistently skew all the results in the same direction.
Sampling Process
Population - Everyone or everything that has the traits you want to study. This could be a person, group, organization, country, object, or anything you want to learn about.
Sampling Frame - A list of people or items from the target population that you can actually reach and select for your study.
Sample - The final step in sampling is picking your sample from the list you have, using a clear method. There are two main types of methods: random (probability) sampling and non-random (non-probability) sampling.
Probability Sampling - A method where every member of the population has a known chance of being chosen for the sample.
Simple Random - Every possible group of a certain size from the population has an equal chance of being chosen. The chance of picking any specific group of n out of N total units is calculated using combinations
Systematic - The list of the population is organized in order, and members are picked at regular steps from that list.
Cluster - If the population is spread out over a large area, it might be hard to randomly sample everyone. In this case, it makes sense to split the population into smaller groups, or “clusters.
Non-Probability - A sampling method where some members of the population have no chance of being chosen, or where you can’t know the exact chances of selection.
Convenience - A method where you choose a sample from the people or items that are easiest to reach or most convenient.
Quota - The population is divided into separate subgroups, and then a non-random sample is taken from each group to meet a specific quota.
Expert - A method where participants are picked non-randomly because they have special knowledge or experience about what’s being studied.
Snowball - technique where you begin with a few people who fit your study criteria and ask them to refer others they know who also qualify.
Statistics - The process of picking a smaller group from a larger population to study, so you can make conclusions about the whole population.
Frequency Distribution - Frequency of answers from different people to the same question can be shown in a graph that counts how often each answer occurs.
Normal Distribution - With many responses, the frequency graph usually forms a bell-shaped curve called a normal distribution, which helps estimate overall traits like the average (mean) or how spread out the responses are (standard deviation).