Statistics Concepts: Sampling Bias, Question Design, and Basic Terminology

Vocabulary flashcards covering key terms from the notes on sampling bias, survey design, and basic statistical terminology.

Variable

A characteristic that can take on different values across individuals; can be numerical (quantitative) or categorical (qualitative).

Population

The entire group of interest from which a sample is drawn.

Sample

A subset of the population selected for a study.

Statistic

A numerical summary computed from a sample.

Parameter

A numerical summary that describes a population.

• Population distribution

distribution of all values in the entire population.

Sampling distribution

distribution of a sample statistic from many samples.

• Standard normal distribution

• normal distribution with mean 0 and standard deviation 1.

• Student’s t-distribution

• distribution used when the population standard deviation is unknown.

• Central Limit Theorem

• says sample means become approximately normal for large sample sizes.

• Point estimate

• a single value used to estimate a population parameter.

• Confidence interval

• a range of values likely to contain the true population parameter.

• Significance level (\alpha)

• probability of making a Type I error or the risk of being wrong

• Confidence level

• the percent of confidence that the interval contains the true parameter.

• Critical value

• cutoff value that separates likely from unlikely results.

• Margin of Error

• amount added and subtracted from the estimate.

• Null hypothesis (H_0)

• statement of no change or no difference, the base statement you are tying to reject or fail to reject

• Alternative hypothesis (H_a)

• statement that there is a change or difference.

• Test statistic

• value calculated from sample data used in hypothesis testing. z score or t score

• P-value

• probability of getting results as extreme as the sample results if the null hypothesis is true.

• Type I error

• rejecting a true null hypothesis.

• Type II error —

not rejecting a false null hypothesis.