Statistical Inference – Basic Concepts

Introduction to Statistical Inference

Statistical inference is a fundamental area of statistics concerned with drawing conclusions about population parameters based on data collected from a sample. It involves using probability theory to make generalizations or predictions about a population from which the sample is drawn.

• Statistics is the branch of mathematics dealing with the collection, analysis, interpretation, and presentation of data.

• The study of statistics is divided into two main areas:

  1. Descriptive statistics: Summarizes and describes features of a dataset (e.g., means, graphs, plots).

  2. Inferential statistics: Makes predictions or inferences about a population based on sample data.

• The goal of statistical inference is to draw conclusions or make propositions about an unknown parameter using a random sample from the population.

• Common statistical inference problems include:

  1. Point estimation

  2. Interval estimation (confidence intervals)

  3. Hypothesis testing

Key Definitions

• Statistical population: The complete set of statistical units (individuals or items) of interest.

• Random variable : A variable whose possible values are numerical outcomes of a random phenomenon, studied on the population.

• Unknown parameter : A fixed, but unknown, numerical characteristic of the population (e.g., mean , variance ).

• Sample statistics: Functions of the random sample , used to estimate population parameters. Any sample statistic is itself a random variable.

Point Estimation

Definition and Properties

Point estimation involves using sample data to calculate a single value (the point estimate) that serves as a best guess for an unknown population parameter.

• Point estimator : Any sample statistic used to estimate the unknown parameter .

• Point estimate : The observed value of the point estimator, calculated from the actual sample data.

• Standard error: The standard deviation of a point estimator, denoted .

• Sampling distribution: The probability distribution of a sample statistic, describing its probabilistic behavior over repeated samples.

Common Point Estimators and Formulas

Sample Identities and Alternate Formulas

• For the sample variance:

  • Alternate formula:

Example: Calculating Sample Statistics

• Given data: Body weights (in grams) of 10 rats: 27.7, 31.5, 30.9, 26.9, 27.0, 38.1, 32.4, 31.1, 36.7, 28.3

• Sample mean:

• Sample variance:

• Sample standard deviation:

• Sample proportion (weight > 35g):

Interval Estimation – Confidence Intervals

Definition and Interpretation

Interval estimation provides a range of values (an interval) that is likely to contain the true value of an unknown population parameter, with a specified level of confidence.

• A confidence interval for is any interval such that .

• Confidence level : The probability that the interval contains the true parameter value in repeated sampling.

• Observed confidence interval: , where is the sample point estimate and is the margin of error.

Margin of Error and Precision

• The margin of error reflects the precision of the point estimate. A smaller margin of error indicates greater precision.

• Precision can be increased by decreasing the margin of error, often by increasing the sample size.

Interpretation of Confidence Intervals

• Being 95% confident that the population mean is in an interval means that, in repeated sampling, approximately 95% of such intervals will contain the true mean.

• For example, if 100 samples are taken and a 95% confidence interval is constructed for each, about 95 intervals will contain the true mean, and 5 will not.

Constructing Confidence Intervals for the Mean (Normal Distribution, Known Variance)

• If and is known, for a random sample of size :

  • The sampling distribution of the sample mean:

  • A confidence interval for is:

  • is the critical value from the standard normal distribution such that .

Confidence Interval for the Difference of Means (Independent Samples, Known Variances)

• If and , with independent samples of sizes and :

  • The sampling distribution of :

  • A confidence interval for is:

Examples and Applications

• Estimating mean resting heart rate: Given bpm, , bpm, and a 99% confidence level, the confidence interval is: bpm

• Estimating mean recovery time: For , days, days, 95% confidence interval: days

• Difference in mean cholesterol levels: For Diet A (, , ) and Diet B (, , ), 98% confidence interval for :

Summary Table: Confidence Interval Formulas

Key Takeaways

• Point estimation provides a single best guess for a parameter; interval estimation provides a range of plausible values.

• Confidence intervals quantify the uncertainty in estimation and are interpreted in terms of repeated sampling.

• Standard error and margin of error are crucial for understanding the precision of estimates.

Additional info: The notes also include worked examples and alternate formulas for variance, as well as graphical illustrations of confidence intervals and their interpretation in repeated sampling.