91Ó°ÊÓ

The concept of normal distribution is foundational in statistics. It's a continuous probability distribution that is symmetric about the mean, meaning most of the data points cluster around the central peak, tapering off symmetrically on each side. This creates the characteristic bell-shaped curve. Many natural phenomena follow a normal distribution, including traits like height or test scores.

In a normal distribution, the mean, median, and mode are all equal. This makes it easier to draw conclusions about the data. For our water consumption example, the problem states that the daily amount typically follows a normal distribution with a mean of 1.4 liters. This means, before any campaign influence, the average person was expected to drink 1.4 liters per day. The aim of this understanding is to see if our sample after the campaign deviates significantly from this established norm.

• Symmetrical shape: the left side mirrors the right side.
• Mean equals median, which equals mode.
• Most data points lie within three standard deviations from the mean.

The t-distribution often comes into play when dealing with small sample sizes, usually n < 30. It is similar in shape to a normal distribution but has heavier tails. This means there is more probability in the tails of the distribution, providing a safeguard against outliers and variability in small data sets. It's particularly useful for hypothesis testing involving small samples drawn from a normally distributed population.

For the hypothesis test regarding water consumption, since we're working with a sample of 10, we use the t-distribution rather than the normal distribution. This distribution requires a calculation of degrees of freedom, which in most simple cases equals the sample size minus one (n - 1). So, with 10 adults in our sample, we use 9 degrees of freedom.

When performing hypothesis testing with the t-distribution:

• Use for small sample sizes.
• Accounts for extra variability compared to a normal distribution.
• The degrees of freedom play a crucial role in determining the shape of the t-distribution.

The p-value helps us decide whether we can reject the null hypothesis. It's the probability of observing a test statistic as extreme as the one calculated from the sample, assuming the null hypothesis is true. The smaller the p-value, the stronger the evidence against the null hypothesis.

In our water consumption case, once the t-statistic is calculated, finding the p-value involves referencing a t-distribution table or using statistical software. Since this is a one-tailed test, we're interested in the probability that the test statistic is greater than or equal to our calculated value. This tells us the likelihood of our sample mean occurring if the null hypothesis is correct.

• A p-value lower than the significance level indicates evidence against the null hypothesis.
• P-value is crucial for interpreting statistical significance.
• Always compare the p-value with the pre-determined significance level (like 0.01).

Statistical significance in hypothesis testing tells us whether the result of our test provides convincing evidence against the null hypothesis. It's determined by the p-value and the significance level. If the p-value is less than or equal to the chosen significance level, the result is statistically significant.

In our exercise, the significance level is set at 0.01. This stringent threshold means we require very strong evidence to reject the null hypothesis. If the calculated p-value is below 0.01, we can conclude that the health campaign has significantly increased daily water consumption among the sample group.

This concept is fundamental in decision-making:

• Do not confuse statistical significance with practical significance.
• Be cautious not to reject the null hypothesis too readily.
• Higher confidence levels (lower significance levels) require more substantial evidence.

Understanding statistical significance helps in evaluating the reliability of the results from hypothesis tests.