91Ó°ÊÓ

Sample bias occurs when the selected sample is not representative of the larger population. This can skew the results or lead to incorrect inferences about the population. When bias is present, certain members of the population may have a higher chance of being included in the sample than others, leading to over- or under-representation. For example, if we only select students from a freshman dormitory, we may miss older students who live off-campus. In the context of the exercise, bias could be introduced if the sample was not randomly chosen and instead focused on specific groups. If only students aged 18 to 20 were selected either intentionally or unintentionally, we might wrongly conclude that these ages represent the entire university's student population. To mitigate sample bias, it's important to use careful sampling methods that give every individual an equal opportunity to be included. This helps ensure our sample is more likely to reflect the population accurately.

Understanding the difference between a population and a sample is key to making accurate statistical inferences.

• A population refers to the complete set of individuals or items that we are interested in studying. In a university setting, the population includes all students enrolled at the institution, regardless of age or year in school.
• A sample, on the other hand, is a subset of this population. We use samples because it is often impractical to collect data from everyone in the population.

In the original exercise, the 50 students represent a sample of the larger population of all students. One must be cautious in over-extending conclusions drawn from a sample to the entire population, especially if the sample does not adequately reflect the diversity and characteristics of the whole group.

Choosing the right sampling method is crucial for achieving a representative sample without bias. Sampling methods dictate how individuals are chosen from the population and thus affect the reliability of statistical inferences. Common sampling methods include:

• Random Sampling: Every individual has an equal chance of being selected, minimizing bias and making the sample more likely to represent the population accurately.
• Stratified Sampling: The population is divided into subgroups (or strata), and samples are taken from each. This can ensure that specific groups are adequately represented in the sample.
• Cluster Sampling: The population is divided into clusters, and whole clusters are randomly selected for analysis. This method is useful when the population is too large and widespread for simple random sampling.

In the context of our scenario, knowing how the sample of 50 students was chosen would help determine if the inferences about the student population are valid. For instance, using stratified sampling could ensure that we are capturing a diverse group across all age ranges and years of study, rather than just those near the age of 18-20.