Probability and Statistics: TExES Mathematics 4-8 115
TExES Mathematics 4-8 (115) covers data displays and distributions, probability models, compound events, sampling, inference, experiments, regression and correlation.
- Prepare to choose appropriate graphs and statistics, check probability assumptions, evaluate samples and distinguish association from causation.
- The official framework places these topics in Competencies 012 through 014.
On this page12 sections
- Framework scope for probability and statistics
- Organize and display data
- Describe center, spread and shape
- Probability as a model
- Compound events and counting
- Distributions and probability models
- Sampling, experiments and inference
- Bivariate data, correlation and regression
- Original worked example: school survey
- Common errors and teaching responses
- Instruction and assessment connections
- Prepare for TExES 115
Framework scope for probability and statistics
The TExES Mathematics 4-8 (115) framework places Probability and Statistics in Domain IV, approximately 16 percent. Competency 012 addresses graphical and numerical techniques for exploring data, characterizing patterns and describing departures. Competency 013 covers probability theory and models. Competency 014 connects probability, sampling and statistical inference. Use these exact objectives to guide preparation; the domain is broader than calculating a mean or applying one probability formula.
Data and probability questions often depend on the design and representation. A graph can reveal shape but can also mislead through its scale. A sample can support an inference only if the selection process and context justify it. A probability model needs assumptions about outcomes and events. Candidates should explain what the analysis permits and what it does not establish.
The teaching competencies also matter. A teacher should help learners reason from data, use simulations, evaluate claims and identify misconceptions. Practice interpreting student work and choosing questions that reveal understanding. A correct calculation may still answer the wrong question if the variable, sample or event was misunderstood.
Organize and display data
Competency 012 includes organizing and displaying data in formats such as tables, frequency distributions, stem-and-leaf plots, box-and-whisker plots, histograms and pie charts. Choose a display based on variable type and purpose. A histogram shows a numerical distribution grouped into intervals; a bar chart compares categories; a box plot summarizes quartiles and potential outliers. A display should have clear labels, units and a scale that supports fair comparison.
A stem-and-leaf plot preserves individual values while showing how they cluster. A histogram emphasizes the overall shape but groups values. A box plot makes median, quartiles and spread visible, but does not show every observation. These displays answer different questions. A candidate should not choose a graph only because it looks familiar; ask what features the audience needs to see.
Check scales and categories. A vertical axis that begins at a nonzero value can exaggerate small differences in a bar chart. Unequal interval widths in a histogram can distort frequency comparisons if bar area is not handled appropriately. A pie chart is useful for parts of a whole when categories are mutually exclusive and sum to the total; it is not ideal for showing change over time. Label any graph so a reader knows the units and sample.
Describe center, spread and shape
Competency 012 names center, spread, shape and skewness. Mean, median and mode summarize center in different ways. The mean uses every numerical value and is sensitive to extremes. The median is the middle ordered value and is more resistant to outliers. The mode identifies a most frequent value or category. Choose a measure that fits the distribution and question.
Consider the values 2, 3, 3, 4 and 18. The mean is 6, while the median is 3. The high value shifts the mean, so the median may better describe a typical observation if the large value is unusual. That does not mean the median is always best. The mean may be useful when all values contribute to a total or when the distribution is fairly symmetric.
Spread can be described by range, interquartile range and other measures. The range uses maximum minus minimum and is sensitive to extremes. The interquartile range spans the middle half of ordered data. Shape includes symmetry, skewness, clusters, gaps and outliers. A dot plot or histogram can show features that a single average conceals. Always connect summary statistics to a display and context.
Probability as a model
Competency 013 includes probability through data collection, experiments and simulations; simple and compound events; probability models; sample spaces; permutations and combinations; geometric probability; and binomial, geometric and normal distributions. A probability describes a model for uncertainty. For equally likely outcomes, P(event) is favorable outcomes divided by total outcomes. If outcomes are not equally likely, counting alone is not sufficient.
For a fair six-sided die, the probability of rolling an even number is 3/6, or 1/2. A simulation can approximate the long-run frequency by rolling many times, but one short run can differ from the theoretical value. Explain the difference between theoretical probability and experimental relative frequency. A simulation's usefulness depends on whether it models the relevant outcomes and assumptions.
A sample space lists possible outcomes. For two coin tosses, the outcomes are HH, HT, TH and TT. Exactly one head occurs in HT and TH, so the probability is 2/4 = 1/2 under a fair independent-toss model. An organized tree diagram can make compound outcomes visible. Without a systematic list, learners may omit outcomes or treat distinct orders as identical when order matters.
Compound events and counting
For independent events, the probability that both occur is the product of their probabilities. If a fair coin is tossed twice, the probability of two heads is 1/2 times 1/2 = 1/4. If events are dependent, the second probability can change based on the first. Always identify whether the process includes replacement or otherwise affects the next outcome.
A bag holds 3 red and 2 blue tiles. Drawing two without replacement, the probability of red then blue is 3/5 times 2/4 = 3/10. With replacement, it would be 3/5 times 2/5 = 6/25. The wording changes the model. A tree diagram can show the conditional probabilities after each first draw.
Permutations count arrangements when order matters; combinations count selections when order does not. Choosing a president and secretary from a group assigns distinct roles, so changing order creates a different outcome. Selecting two students for an undifferentiated team does not create a new selection when their order is switched. Define the experiment in words before using a formula. Geometric probability compares favorable area with total area when the model supports a uniform selection assumption.
Distributions and probability models
The framework includes binomial, geometric and normal distributions. A binomial model concerns a fixed number of trials, two outcomes per trial, a constant probability of success and independent trials. A geometric model counts trials until a first success under suitable conditions. A normal model is continuous and symmetric around its center in the ideal distribution. Identify the conditions before using a named distribution.
A binomial example might be counting how many successes occur in a fixed set of independent trials with constant success probability. A geometric example asks how many attempts until the first success. The distinction is the quantity being counted. Do not apply the binomial distribution to trials with changing probabilities or dependence without a justified model.
A normal distribution can model measurements or scores under conditions where the shape is approximately bell-shaped. Standard scores describe position relative to mean and standard deviation. A normal model does not mean every dataset is normal. Inspect data and context. Use a probability model to answer a question only when its assumptions are appropriate.
Sampling, experiments and inference
Competency 014 includes designing, conducting, analyzing and interpreting statistical experiments. A random sample gives members of a population a known chance of selection under the sampling procedure. A convenience sample may overrepresent a subgroup and limit generalization. A larger sample often reduces sampling variability, but size alone does not fix bias. How the sample was drawn matters.
A population parameter describes the full group; a sample statistic summarizes the observed sample. Repeated random samples can produce different statistics. Confidence intervals express uncertainty in an estimate under a specified method. The framework calls for understanding the relationship between sample size and confidence intervals; in general, larger samples can support narrower intervals under comparable conditions, but the design and variability matter.
Experiments can investigate cause and effect when subjects are assigned and other conditions are controlled appropriately. Observational data can reveal association but often cannot rule out confounding. Random assignment and random sampling answer different questions: assignment supports causal comparison within an experiment, while sampling concerns how results generalize to a population. Do not treat the terms as interchangeable.
Bivariate data, correlation and regression
Competency 014 names scatterplots, regression lines, correlation coefficients and residual analysis for exploring bivariate data and making or evaluating predictions. A scatterplot shows paired values and can reveal direction, form, strength, clusters and outliers. A correlation coefficient summarizes linear association, but does not establish causation and can be affected by outliers.
A regression line can be used to predict within the range of data when a linear model is appropriate. Extrapolation far beyond observed values is risky. Residuals are differences between observed and predicted values. A pattern in residuals may indicate that a linear model misses curvature or another structure. Always consider the context and assumptions before treating a prediction as reliable.
For example, students who spend more time practicing may also score higher, but a positive association does not prove that practice time alone caused the difference. Prior knowledge, instruction and access could also matter. A scatterplot can describe the relationship; an experiment or better design would be needed to evaluate causal claims. This distinction is central to statistical reasoning.
Original worked example: school survey
A school surveys 40 students about their preferred after-school activity. Twenty prefer sports, 12 prefer art and 8 prefer reading. The category proportions are 20/40 = 1/2, 12/40 = 3/10 and 8/40 = 1/5. They sum to 1, so a pie chart could represent the parts of this sample. A bar chart may be easier for comparing category counts directly.
The survey method determines what can be inferred. If students were randomly sampled from the school, the responses may support an estimate of school preferences, with sampling uncertainty. If the survey was given only to students attending sports practice, it would likely overrepresent sports preferences. The same arithmetic does not repair a biased sample. Ask who was invited, who responded and how the sample was selected.
A candidate should avoid claiming that exactly half of all students prefer sports based only on the observed sample. The defensible statement is that half of the surveyed students selected sports. Broader inference depends on design and context. This example combines proportions, graphs, sampling and cautious communication.
Common errors and teaching responses
A student may report the mean as the only meaningful center, even with strong skew or an outlier. Compare mean and median using an actual dataset and ask which best answers the question. Another may select a pie chart for a time trend. Ask what each category represents and whether the goal is to compare groups or show change.
Students can also assume a larger sample eliminates all bias, confuse random assignment with random sampling, or infer causation from correlation. Use counterexamples and diagrams to show the difference. Ask what population is represented, how participants were selected and what alternative explanations remain. These are instructional questions as well as statistical content.
In probability, a common error is assuming replacement or independence without reading the setup. Draw a tree and write conditional probabilities at each branch. In counting, clarify whether order matters before using permutations or combinations. The teacher should prompt students to define the experiment and list outcomes before applying a shortcut.
Instruction and assessment connections
Competencies 017 and 018 connect learning, instructional planning, tools and mathematical discourse. Students can collect data, create displays, simulate events and critique claims. The teacher should set an objective and choose technology or manipulatives that support the reasoning. A spreadsheet can organize observations, but students still need to interpret distributions and explain conclusions.
Competency 019 addresses formative and summative assessment, worthwhile tasks, misconceptions, reliability, validity and using results to modify instruction. A short exit question can reveal whether students confuse correlation and causation. A task that asks students to select a graph and justify it can assess understanding better than a vocabulary match alone. Use errors to decide whether the next lesson needs a sample-space model, a data display or a discussion of sampling.
Prepare for TExES 115
Study competencies 012 through 014 and practice moving from data to display, summary, model and inference. Identify the variable, population, sample, event and assumptions. Calculate carefully, then state what the result means and what conclusion is justified. For a classroom scenario, identify the student misconception and choose an instructional response that makes the reasoning visible.
Pearson's domain percentages are approximate. Official samples illustrate how competencies may be assessed but do not replace the framework. The examples here are original practice and are not Pearson questions. Explain why distractors are tempting and how the official competency supports the best response. This builds transferable statistical judgment instead of memorizing isolated formulas.
Common questions
Which TExES 115 competencies cover statistics?
Competencies 012 through 014 cover data displays, probability, sampling and statistical inference.
Does correlation prove causation?
No. Correlation describes association. Causal claims require an appropriate design and evidence.
When should I use a median instead of a mean?
A median can better describe center when a distribution is skewed or contains influential outliers.
What is the difference between permutations and combinations?
Permutations count arrangements when order matters; combinations count selections when order does not.