Word | Definition |
Population | The group about which we want to learn something |
Parameter | A characteristic of the population |
Sample | A subset of the population from which we collect data |
Statistic | A number calculated from sample data |
Simple random sample | A sample in which every individual in the population has the same chance of being selected as any other individual |
Sampling frame | A comprehensive list of individuals from which the sample will be drawn |
Sampling error | The sample to sample variation that we would expect to obtain if we selected multiple samples from the population |
Bias | A distorted view of the population that results from poor sampling design |
Stratified random sample | Sampling technique: First divide population into two or more groups before taking random sample (e.g. male and females) |
Benefits of stratified random sample | Benefits of this technique is that it leads to more precise estimates by reducing sample variability |
Cluster sampling | Clusters, or natural groups in populations are selected that are identical on the characteristics we are interesting in exploring. We then take a random sample of the clusters. |
Benefit of cluster sampling | The benefit of this technique is to save time and money. |
Systematic sampling | Every 10th or nth person are selected from a list of individuals in the population. |
[BLANK] is used to estimate [BLANK - 2 words] | [Statistics] is used to estimate [population parameters] |
Overall size of [BLANK] is more important than the overall size of the [BLANK] | Overall size of [sample] is more important than the overall size of the [population] |
Social desirability bias | When people adjust their responses to survey questions to avoid "looking bad" or to make themselves "look good" in the eyes of the person conducting the survey |
The [BLANK] in which you ask survey questions may lead to different responses | The [order] in which you ask survey questions may lead to different responses |
Survey questions must be [BLANK] and [BLANK] | Survey questions must be [concise] and [clear] |
Avoid [BLANK] questions that are worded to "lead" the respondent towards a particular response | Avoid ["leading"] questions that are worded to "lead" the respondent towards a particular response |
Voluntary response bias | Occurs when respondents are choosing you rather than you choosing them. They are not a random sample of the underlying population. |
What is the problem with voluntary response bias? | People who are usually responding are more strongly opinionated (usually negative) than the general population. |
Nonresponse bias | Common bias. Very hard to avoid. Occurs when respondents refuse to participate. |
What is the problem with nonresponse bias? | People who refuse to respond may have a different opinion than those who did. |