Summary of Introduction to Fundamental Statistical Concepts
Introduction to Fundamental Statistical Concepts
Introduction
Statistics is both a set of numbers used to describe data and a field of study that teaches how to collect, summarise, analyse, and draw conclusions from data. This guide focuses on the two main branches: Descriptive Statistics and Inferential Statistics. You will learn definitions, methods, practical examples, and when to use each approach.
Overview: Two Main Types
| Type | Purpose | Typical tools | Example question |
|---|---|---|---|
| Descriptive Statistics | Summarise and present observed data | Mean, median, mode, range, standard deviation, graphs | What is the average test score in this class? |
| Inferential Statistics | Make conclusions about a population from a sample | Hypothesis tests, confidence intervals, regression, ANOVA | Does a new teaching method improve scores in the whole university? |
Descriptive Statistics
Descriptive statistics reduce large datasets into understandable summaries.
Definition: Descriptive statistics are techniques for organising, summarising, and presenting data so that patterns and characteristics become clear.
Key measures
- Central tendency: describe a typical value
- Mean (average): sum of observations divided by count. Example: For scores $95$, $90$, $80$, $85$, $95$, $100$ the mean is $$\text{mean} = \frac{95 + 90 + 80 + 85 + 95 + 100}{6} = \frac{545}{6} = 90.833\ldots$$
- Median: middle value when data are ordered. For ordered data $80$, $85$, $90$, $95$, $95$, $100$ the median is the average of the two middle values: $$\text{median} = \frac{90 + 95}{2} = 92.5$$
- Mode: most frequent value. Example: mode = $95$.
- Spread (variability): range, variance, standard deviation
- Range: difference between maximum and minimum. Example: range = $100 - 80 = 20$.
- Standard deviation: typical distance from the mean (compute from variance).
- Shape: skewness, kurtosis — describe asymmetry and tail behaviour.
Presenting data
- Use tables, histograms, boxplots, bar charts, and pie charts to visualise distributions and categorical counts.
- Label axes and include units.
Inferential Statistics
Inferential statistics let you draw conclusions about a larger population using a subset (sample) of data.
Definition: Inferential statistics are methods that use sample data to make probabilistic statements about a population and to test hypotheses.
Key concepts
-
Population vs Sample
- Population: the complete set of individuals or items you want to study. Example: all students at a university.
- Sample: a subset of the population used to estimate population characteristics.
-
Parameter vs Statistic
- Parameter: a numerical value describing a population (e.g., population mean $\mu$).
- Statistic: a numerical value computed from a sample (e.g., sample mean $\bar{x}$).
Definition: A random variable is a variable whose value depends on the outcome of a random process.
- Types of random variables
- Discrete random variable: takes specific values, usually integers. Example: number of books a student borrows $0$, $1$, $2$, $3$.
- Continuous random variable: takes any value in an interval. Example: student height in metres.
Common inferential tools
- Confidence intervals: give a range that likely contains the true population parameter. Example: a 95% confidence interval for a mean might be $(4.3,;5.1)$ meaning we are 95% confident the population mean lies between $4.3$ and $5.1$.
- Hypothesis testing: formal procedure to decide whether a claimed effect is supported by data. Key outputs: test statistic (e.g., $t$-value) and p-value. If $p$ is small, the observed result is unlikely under the null hypothesis.
- Regression analysis: models relationship
Sign up for the full summaryAlready have an account? Sign in
Descriptive and Inferential Statistics
Klíčové pojmy: Statistics has two branches: descriptive (summarise data) and inferential (generalise from samples)., Mean $\bar{x}$ is computed as $\frac{\sum x_i}{n}$ and summarises central tendency., Median is the middle value of ordered data; for even $n$ take the average of the two middle values., Mode is the most frequent observation; range is max minus min., Use standard deviation to quantify typical deviation from the mean., Confidence interval provides a range likely to contain a population parameter; common form: $\bar{x} \pm z\,SE$., Hypothesis tests use a test statistic and p-value to assess evidence against a null hypothesis., Regression models linear relationships: $Y = \beta_0 + \beta_1 X + \varepsilon$; interpret coefficients carefully (correlation vs causation)., ANOVA compares means across three or more groups to detect differences., Distinguish parameter (population) from statistic (sample)., Random variables: discrete take specific values, continuous take any value in an interval., Visualisation (histograms, boxplots) is essential for understanding distributions.