91Ó°ÊÓ

The sample proportion is a way to express the fraction of a sample that contextually represents a particular attribute. In any given group, or sample size, it displays the proportion of observations that match a specific category. For example, in the context of the orange tabby cats exercise, if 90% of orange tabby cats are male, then the sample proportion (p) can be defined as 0.9.
The concept of sample proportion is particularly important in statistics because it helps in making inferences about the larger population based on a smaller, manageable sample. When repeatedly taking random samples of a given size, these sample proportions form a distribution. Managing and understanding these distributions leads to more robust statistical conclusions.
This understanding is crucial when determining how often a sample proportion will differ from the actual population proportion—especially in sampling scenarios such as polling or quality control tests.

A normal distribution is a key concept in statistics characterized by a bell-shaped curve that is symmetric around the mean. When we talk about sample proportions, we are often checking if their distribution approximates a normal distribution.
In the orange tabby cats context, whether the distribution of sample proportions is normal depends on sample size. The rule of thumb for this approximation is that both the expressions \(np\) and \(n(1-p)\) should be greater than or equal to 10. With the sample proportion given as \(p = 0.9\):

• For a sample size of 140: \(np = 126\) and \(n(1-p) = 14\), both meet the requirement.
• For a sample size of 280, \(np = 252\) and \(n(1-p) = 28\), these also meet the requirement.

This means as the sample size increases, the distribution of the sample proportion becomes approximately normal, making it easier to apply further statistical techniques.

The standard error (SE) in statistics measures how much variability there is in a sample statistic, like the sample proportion, compared to the population parameter. It essentially tells us how much the sample proportion \(\hat{p}\) is expected to vary from the actual population proportion \(p\).
The formula to calculate standard error is \(SE = \sqrt{\frac{p(1-p)}{n}}\). This formula shows that the standard error decreases with larger sample sizes. If you multiply your sample size by four, the standard error is halved because you are effectively increasing the accuracy of your estimate. In the exercise, this mathematical property is highlighted to be true, reducing uncertainty and increasing confidence in the estimates.
Understanding standard error is central for hypothesis tests and constructing confidence intervals because it quantifies the precision of the sample proportion compared to the actual population proportion.

Skewness is a statistic that tells us about the symmetry—or lack thereof—of the distribution of data. A distribution is skewed if it is not symmetrical. Understanding skewness is crucial when determining whether distribution of our sample proportions fits a certain shape.
In the context of the exercise on orange tabby cats, if the number of sample proportion results is low, the distribution could be skewed. As observed in statement (a), where the sample size of 30 does not hold up the normality condition \(np \geq 10\) and \(n(1-p) \geq 10\), the results show a right-skewed distribution due to the small number of non-male tabbies (3).
A normal distribution has a skewness of zero, indicating that it is perfectly symmetrical. When skewness is not zero, interpretations regarding probabilities and statistics differ, which is why it is always good to check the skewness when analyzing samples.