Junior Statistician Qualification Examination study plan

Compute and interpret mean, median, mode, quartiles, variance, standard deviation, and coefficient of variation for raw and grouped data, and state which measure suits skewed versus symmetric data.

Construct and label frequency tables, cumulative frequency curves, histograms, box plots, and stem-and-leaf displays, then read shape, spread, and outliers back off each display.

Detect and explain misleading graph practices such as truncated axes, unequal class widths, and 3D pie distortion, and redraw one flawed chart correctly.

Produce a one-page descriptive summary of a real dataset you download yourself, reporting at least six summary statistics and two graphs with captions.

Apply the addition and multiplication rules, conditional probability, and Bayes' theorem to solve at least 15 word problems without looking at solutions first.

Distinguish discrete from continuous random variables and compute expectation and variance for binomial, Poisson, hypergeometric, uniform, normal, and exponential models.

Standardize normal variables with z-scores and compute tail, interval, and inverse-normal probabilities using tables and software, checking both against each other.

State the central limit theorem precisely and simulate sampling distributions in software to show the approach to normality as sample size grows.

Derive and compare the method-of-moments and maximum-likelihood estimators for the binomial and exponential parameters, showing the likelihood steps explicitly.

Explain unbiasedness, consistency, efficiency, and sufficiency, and evaluate a given estimator against each criterion.

Construct confidence intervals for a mean, a proportion, a difference of means, and a variance, and state the assumptions behind each.

Determine the sample size needed for a target margin of error in mean and proportion estimation, and interpret what changing confidence level does to that size.

Frame a research question as null and alternative hypotheses, choose the correct test statistic, and state rejection regions for one- and two-tailed tests.

Distinguish Type I and Type II errors, define power, and compute power or required sample size for a one-sample mean test.

Run one-sample and two-sample t-tests, paired t-tests, and z-tests for proportions by hand and in software, and reconcile the two results.

Interpret p-values correctly, including what a p-value does not tell you, and explain the practical difference between statistical and substantive significance.

Fit simple linear regression by least squares, compute slope, intercept, residuals, and standard errors, and interpret each coefficient in context.

Assess model fit with R-squared, residual plots, and a test on the slope, and identify violations such as nonlinearity and nonconstant variance.

Compute and interpret Pearson and Spearman correlation coefficients, and explain how correlation differs from causation and from regression slope.

Build and interpret a multiple regression with two or three predictors, including partial coefficients and multicollinearity checks.

Compare simple random, stratified, cluster, and systematic sampling on cost, bias risk, and precision, and select an appropriate design for three described scenarios.

Design a completely randomized experiment and a randomized block design for stated research questions, specifying treatments, blocks, replication, and randomization procedure.

Explain the role of randomization, control, and blocking in reducing bias and variance, and identify confounders in a described study.

Compute and interpret a one-way analysis of variance, including the F statistic, degrees of freedom, and post-hoc comparison logic.

Run and interpret chi-square goodness-of-fit and independence tests, verifying expected counts and applying the continuity or exact-test correction when appropriate.

Apply the sign test, Wilcoxon signed-rank test, and Mann-Whitney U test, and justify choosing a nonparametric method over its parametric counterpart.

Construct and interpret contingency tables with row, column, and total percentages, and compute measures of association for ordinal data.

Identify when Fisher's exact test is required instead of a chi-square test and explain the reason.

Decompose a time series into trend, seasonal, cyclical, and irregular components, and compute a simple moving average and seasonal index from a short series.

Compute and interpret Laspeyres and Paasche price indices, and explain chain linking and substitution bias.

Clean a messy dataset in software by handling missing values, recoding types, and detecting duplicates, and document every transformation applied.

Complete two full-length timed mock exams under exam conditions and review every wrong answer to its underlying concept.