CampusLearn
← BIT 205 Statistics for Business

Sampling, Confidence Intervals and Hypothesis Testing

Notes

Learning from representative samples A population is the complete group of interest, while a sample is the subset observed. A sampling frame lists units available for selection and can introduce coverage bias if important groups are missing. Simple random sampling gives each unit an equal selection chance; stratified sampling selects within meaningful groups to improve coverage or precision. Larger samples reduce random sampling error but do not automatically remove selection bias. Distinguish a population parameter, such as the true mean waiting time, from a sample statistic used to estimate it. Estimation and evidence A confidence interval combines an estimate with a margin of error based on sampling variability. A 95 percent confidence procedure captures the fixed population parameter in about 95 percent of repeated samples under its assumptions. Hypothesis testing specifies a null claim and an alternative, then evaluates evidence using a test statistic and p-value. The p-value is the probability, assuming the null model, of results at least as extreme as observed. It is not the probability that the null hypothesis is true. Set a significance level before analysis and consider practical importance alongside statistical significance. Practical example A Kisumu county hospital randomly samples 100 comparable patient visits and finds a mean wait of 42 minutes with sample standard deviation 10 minutes. The standard error is 10 divided by the square root of 100 = 1 minute. A large-sample approximate 95 percent confidence interval is 42 plus or minus 1.96 times 1, giving 40.04 to 43.96 minutes. Testing a null mean of 40 gives an approximate standardised statistic of 2 and a two-sided p-value near 0.046. At five percent significance, reject the null under the model, but separately assess whether two minutes warrants operational investment.

Quiz

1. Why might a large sample still give a misleading population estimate?

2. What does a p-value measure under the null model?

3. What is the standard error for standard deviation 10 and sample size 100?

Sign in to submit and securely grade your quiz.