ExamPass EngineeringExamPass Engineering Start free
FE Environmental · Knowledge area 12 of 15

Probability and Statistics on the FE Environmental exam

Probability and Statistics accounts for 4 of the 110 questions — 3.6% of your exam. It is one of the lighter areas, which makes it a good place to secure quick marks rather than a place to spend weeks.

Questions4
Share of exam3.6%
Rank by weight12/15
In our bank14

What Probability and Statistics covers

On the FE Environmental exam this area covers measures of central tendency and dispersion, probability rules, conditional probability, discrete and continuous distributions, confidence intervals, hypothesis testing, and linear regression.

What the questions look like: A mean or standard deviation from a small data set, a probability from the normal or binomial distribution, or reading a confidence interval off the Handbook tables.

Worth knowing cold: Know which distribution a problem is describing before you reach for a formula. Most errors here are choosing the wrong model, not arithmetic.

3 free Probability and Statistics practice problems

These come from our FE Environmental bank, written to the same specification as the exam. Try each one before opening the solution.

Problem 1

An environmental consulting firm conducts RCRA groundwater detection monitoring at an active industrial hazardous waste landfill to determine whether down-gradient compliance wells exhibit statistically significant evidence of contamination above up-gradient background levels. Statistical hypothesis testing is structured as: Null hypothesis $H_0: \mu_{\text{down}} = \mu_{\text{background}}$ (no release), versus Alternative hypothesis $H_1: \mu_{\text{down}} > \mu_{\text{background}}$ (contamination present). Under US EPA Unified Statistical Guidance for Groundwater and NCEES principles, select the TWO true statements regarding this statistical testing program.

  1. AA Type I error (false positive) occurs if the statistical test concludes that groundwater contamination is present when the facility has not actually released any contaminants
  2. BA Type II error (false negative) occurs when a clean monitoring well is falsely declared contaminated, triggering unnecessary corrective action
  3. CWhen background monitoring data follows a normal distribution, an Upper Tolerance Limit (UTL = X̄ + k·s) or prediction limit can establish a compliant threshold above which a down-gradient value indicates statistical contamination
  4. DSetting an extremely small significance level (such as α = 0.0001) always maximizes the statistical power (1 - β) to detect real contaminant leaks early
Show the solution

Statistical analysis of groundwater monitoring data at waste facilities requires balancing environmental protection against false facility alarms under US EPA 40 CFR Part 264 Subpart F regulations. Step 1: Definition of statistical errors: A Type I error (probability $\alpha$) is a false positive—rejecting $H_0$ when $H_0$ is true (falsely alleging a leak when none occurred, Statement A). A Type II error (probability $\beta$) is a false negative—failing to reject $H_0$ when $H_1$ is true (failing to detect an actual leak; Statement B is incorrect because it confuses Type I and Type II errors). Step 2: Threshold estimation: In detection monitoring, an Upper Tolerance Limit (UTL) or Upper Prediction Limit (UPL) calculated from up-gradient background data as $\bar{X} + k \cdot s$ defines an upper boundary that contains a specified coverage percentage of the population with confidence $(1 - \alpha)$; values above this threshold trigger verification retesting or assessment monitoring (Statement C). Statement D is false because reducing $\alpha$ directly increases $\beta$, which decreases statistical power ($1 - \beta$) and causes small releases to be missed.

Problem 2

An environmental engineer is establishing a groundwater detection monitoring statistical program for a municipal solid waste landfill under EPA RCRA Subtitle D regulations (40 CFR § 258.53). The program evaluates background versus downgradient groundwater monitoring well samples for evidence of statistical contamination. Which of the following statements regarding hypothesis testing, statistical error rates, and compliance testing methodologies are CORRECT? (Select all that apply.)

  1. AUnder EPA Subtitle D guidance, the facility-wide false positive rate (Type I error rate, α) for individual well-constituent comparisons must be strictly controlled (e.g., individual comparison α ≥ 0.01 and annual facility-wide α ≤ 0.05) to prevent falsely concluding that an unpermitted release has occurred.
  2. BWhen groundwater background monitoring records contain more than 50% non-detects (censored data), standard parametric analysis of variance (ANOVA) assuming an underlying normal distribution is preferred over non-parametric tolerance limits.
  3. CIncreasing the sample size n from 4 to 16 quarterly background samples decreases the statistical power of the test to detect an actual release (Type II error increases).
  4. DA Type II error (β) occurs if the engineer fails to reject the null hypothesis of compliance when the groundwater downgradient of the landfill is actually contaminated, posing an unmitigated environmental and public health hazard.
Show the solution

1. EVALUATION OF STATEMENT A (TRUE): EPA RCRA Subtitle D regulations (40 CFR § 258.53(g)) require statistical testing to maintain a controlled site-wide false positive rate (FWFPR, typically $\alpha \le 0.05$) while keeping individual test significance levels $\alpha \ge 0.01$ to balance detection sensitivity against excessive false alarms. 2. EVALUATION OF STATEMENT B (FALSE): Under the EPA Unified Guidance, when datasets contain more than 15%–50% censored values (non-detects), parametric ANOVA is invalid due to severe violation of distributional assumptions. Non-parametric tolerance intervals or prediction limits must be applied. 3. EVALUATION OF STATEMENT C (FALSE): Increasing sample size from $n = 4$ to $n = 16$ reduces standard error of the mean, increasing statistical power ($1 - \beta$) and decreasing Type II error ($\beta$). 4. EVALUATION OF STATEMENT D (TRUE): In environmental compliance testing, the null hypothesis $H_0$ is compliance. A Type II error ($\beta$, false negative) occurs when $H_0$ is not rejected despite actual groundwater contamination, allowing hazardous contaminant plumes to migrate undetected.

Problem 3

A spectrophotometric laboratory calibration curve for nitrate-nitrogen (NO3⁻-N) in environmental water samples is developed using ordinary least squares (OLS) linear regression of absorbance (y) versus standard concentration (x): y = β₀ + β₁·x. Which TWO of the following statements regarding ordinary least squares (OLS) regression line properties and statistical residual diagnostics are mathematically and methodologically TRUE?

  1. AThe algebraic sum of the vertical residuals around the least squares regression line must identically equal zero: Σ(yi - ŷi) = 0 for any model containing an intercept term.
  2. BA high coefficient of determination (R² > 0.99) guarantees that the underlying physical relationship between absorbance and concentration is strictly linear without curvature.
  3. CThe least squares regression line strictly passes through the point of sample means (centroid): (x̄, ȳ).
  4. DA high Pearson correlation coefficient (r > 0.99) confirms that the regression residuals are homoscedastic across all concentration ranges.
Show the solution

1. OLS MATHEMATICAL PROPERTIES: - Statement A is TRUE: By setting the partial derivative of the sum of squared errors with respect to the intercept $\beta_0$ to zero: $$\frac{\partial \sum e_i^2}{\partial \beta_0} = -2 \sum (y_i - \beta_0 - \beta_1 x_i) = 0 \implies \sum (y_i - \hat{y}_i) = 0$$ The algebraic sum of vertical residuals around the least-squares line is always identically zero for any linear model with an intercept. - Statement C is TRUE: Because $\sum (y_i - \beta_0 - \beta_1 x_i) = 0$, dividing by $n$ gives: $$\bar{y} - \beta_0 - \beta_1 \bar{x} = 0 \implies \bar{y} = \beta_0 + \beta_1 \bar{x}$$ Therefore, the point of means (centroid $(\bar{x}, \bar{y})$) always lies exactly on the regression line. 2. EVALUATION OF FALSE STATEMENTS: - Statement B is FALSE: Anscombe's quartet and calibration curves with saturation plateauing demonstrate that high $R^2$ values ($> 0.99$) can occur even when the true relationship is distinctly non-linear or polynomial. Residual plotting is mandatory to verify linearity. - Statement D is FALSE: Correlation measures the strength of linear association, not variance uniformity. Residual variance may increase systematically with concentration (heteroscedasticity) despite $r > 0.99$, violating the constant variance assumption of standard OLS.

Find out where you actually stand

A free 20-question diagnostic across every FE Environmental knowledge area, scored in the real exam interface. You get a projected score and the areas costing you the most — so you know whether Probability and Statistics is where your time should go at all.

Start the free Environmental diagnostic

Retaking the FE Environmental exam?

Copy the scores from your NCEES diagnostic report and see whether Probability and Statistics is where your next attempt gains the most points, or whether another area deserves the time first.

Analyze my diagnostic report

Other FE Environmental knowledge areas

Probability and Statistics on other FE exams

The same knowledge area is weighted differently on each exam, and the questions differ with it.