Errors in Sampling
Terms
undefined, object
copy deck
- Non sampling errors
- Not related to the act of selecting a sample form the population. They include processing errors, response errors, and non response.
- Stratified random sample
- This sampling technique divides the population into strata or groups. An SRS is chosen form each separate group. The SRS's are combined to form the full sample.
- Sampling frame
- a list of individuals from which we will pick our sample.
- Convenience sample
- chooses the individuals that are easiest to reach. Does not represent the entire population so this is biased.
- Cluster sampling
- A sampling technique where the entire population is divided into groups or clusters.
- Processing error
- An example is entering incorrect data.
- Simple Random Sampling-SRS
- Basic sampling technique where we select a group of subject for study from a larger population. Each individual is chosen entirely by change.
- Parameter
- A number that describes the population. We don't know its value in practice.
- Random sampling error
- Deviation between the sample statistic and the population parameter caused by chance in selecting a random sample.
- Margin of error
- Tells us how close the sample statistic lies to the population parameter.
- Response error
- This occurs when a subject gives an incorrect response.
- Ordinal Data
- Categorical data organized in groups. For example: Classes- Freshman, sophomore, junior, senior. Data is summarized using percentages.
- Systematic sample
- Every kth term is included in the sample.
- Statistic
- A number that describes a sample. The value is known. It is used to estimate the parameter.
- Variability
- Describes how spread out the values of the sample statistic are when we take mean samples. Large variability means that the result of sampling is not repeatable.
- Interval data
- Continuous data that is ordered with a constant scale. It does not have a natural zero. For example, year and temperature.
- Voluntary Response Sample
- A sample that consists of people who choose themselves by responding. They often over represent people with strong opinions.
- Sampling Errors
- Caused by the act of taking a sample. The error can be found in the sampling frame or with the sample variability.
- Confidence statement
- Has two parts: margin of error and level of confidence.
- Ratio data
- Continuous data with a natural zero and constant scale. Examples include height, weight, age, and length. This uses a natural scale.
- Undercoverage
- An Occurs when some groups in the population are left out of the process of choosing a sample.
- Nominal Data
- Categorical data in which objects fall into unordered categories. These types of data are summarized using percentages.
- Non response
- The failure to obtain data from an individual.
- Biased
- Systematically favors certain outcomes. Consistent, repeated deviation of the sample statistic from the population parameter in the same direction when we take many samples.