IBM SPSS Statistics Training Course

Participants can identify and correct common data quality issues before analysis.

• Frequency tables used to identify invalid codes and unexpected categories
• Descriptive summaries used to detect impossible values and extreme observations
• Missing-data patterns reviewed using frequencies, charts and case listings
• Duplicate records identified through case identifiers and sorting procedures
• Validation rules applied to dates, ranges and cross-field relationships
• Data cleaning decisions documented in syntax comments and analysis notes

Participants can create analysis-ready variables using transparent SPSS transformations.

• Recode into Different Variables preserves original source-data values
• Compute Variable creates scores, ratios, flags and derived measures
• Conditional transformations controlled through IF and DO IF statements
• Date and time functions calculate durations, periods and reporting intervals
• String functions standardise text categories and extract coded values
• Visual Binning converts continuous measures into defined reporting bands

Participants can prepare the correct analysis population from multiple SPSS data files.

• Sort Cases establishes matching order before merging related datasets
• Add Variables merges fields using a unique participant identifier
• Add Cases appends records with aligned variable definitions
• Select Cases filters populations using explicit inclusion criteria
• Split File produces subgroup output without creating separate datasets
• Weight Cases applies survey weights and explains weighted sample sizes

Participants can summarise variables and assess distributions before selecting statistical tests.

• Frequencies reports counts, percentages, modes and distribution summaries
• Descriptives calculates mean, standard deviation, range and z-scores
• Explore examines medians, quartiles, outliers and normality diagnostics
• Skewness and kurtosis interpreted alongside histograms and Q-Q plots
• Boxplots compare distributions across groups and identify unusual cases
• Central tendency measures matched to nominal, ordinal and scale variables

Participants can produce clear SPSS tables and charts for technical and management audiences.

• Chart Builder creates bar charts, histograms, boxplots and scatterplots
• Chart titles, axes and data labels edited for clear interpretation
• Custom Tables summarise categories, percentages and subgroup comparisons
• Pivot table formatting controls decimal places, labels and displayed statistics
• Output Viewer folders organise results by question, method and audience
• Export procedures create Word, Excel, PowerPoint and PDF deliverables

Participants can write, run and annotate syntax for repeatable SPSS analysis tasks.

• Paste buttons generate syntax from menu-based analysis procedures
• GET FILE and SAVE OUTFILE commands manage reproducible file paths
• Variable labels and value labels assigned through syntax commands
• Comments document assumptions, source files and transformation decisions
• Syntax selections rerun specific procedures without repeating completed steps
• OUTPUT MODIFY commands standardise selected output table formatting

Participants can select appropriate statistical tests from a structured decision process.

• Research questions translated into null and alternative hypotheses
• Independent, dependent, categorical and scale variables distinguished accurately
• Significance level, p-value and confidence interval interpreted together
• Type I and Type II errors related to decision risk
• Statistical power, sample size and effect size considered jointly
• Test-selection matrix matches questions, designs and measurement levels

Participants can conduct and interpret one-sample, independent and paired-samples t-tests.

• One-Sample T Test compares a sample mean with target values
• Independent-Samples T Test compares means across two separate groups
• Paired-Samples T Test assesses before-and-after measurement differences
• Levene's test informs interpretation of equal-variance t-test results
• Cohen's d quantifies practical importance of mean differences
• Confidence intervals communicate plausible ranges for estimated differences

Participants can compare three or more group means and identify meaningful differences.

• One-Way ANOVA tests mean differences across three or more groups
• Homogeneity of variance assessed using Levene's test and plots
• Welch ANOVA used when equal-variance assumptions are not met
• Tukey HSD identifies pairs of groups with significant differences
• Eta squared reports the proportion of variance explained
• Estimated marginal means support clear group-comparison reporting

Participants can apply non-parametric tests when parametric assumptions are unsuitable.

• Mann-Whitney U compares independent groups using ranked observations
• Wilcoxon signed-rank test evaluates paired ordinal or skewed measurements
• Kruskal-Wallis test compares three or more independent ranked groups
• Friedman test assesses repeated measurements across related conditions
• Median and rank summaries support non-parametric result interpretation
• Exact significance options considered for small sample analyses

Participants can test and report relationships between categorical variables.

• Crosstabs display observed counts, row percentages and column percentages
• Pearson chi-square tests association between two categorical variables
• Expected cell counts checked before accepting chi-square test results
• Fisher's exact test handles sparse two-by-two contingency tables
• Phi and Cramer's V measure strength of categorical association
• Odds ratios and relative risks support binary outcome interpretation

Participants can assess and communicate the direction and strength of variable relationships.

• Pearson correlation measures linear association between scale variables
• Spearman's rho assesses monotonic relationships using ranked observations
• Scatterplots reveal form, direction, outliers and possible nonlinearity
• Correlation coefficients interpreted with sample size and confidence intervals
• Partial correlation controls for specified confounding variables
• Correlation findings separated clearly from causal claims and conclusions

Participants can build and interpret multiple linear regression models for continuous outcomes.

• Linear Regression specifies continuous outcomes and predictor variables
• Enter, hierarchical and stepwise methods compared for model construction
• Unstandardised and standardised coefficients interpreted within model context
• R squared and adjusted R squared assess model explanatory value
• Dummy coding represents categorical predictors within regression equations
• Prediction intervals distinguish individual forecasts from mean-response estimates

Participants can assess regression assumptions and evaluate multi-item survey measures.

• Residual plots assess linearity, normality and constant error variance
• Cook's distance identifies observations with disproportionate model influence
• Tolerance and variance inflation factors identify multicollinearity concerns
• Cronbach's alpha assesses internal consistency of multi-item scales
• Item-total correlations identify weak items within survey measures
• Exploratory factor analysis examines underlying dimensions in questionnaire items

Participants can build, review and present a complete SPSS analysis package addressing a defined business or research question.

• Analysis brief defines decision question, stakeholders, measures and success criteria
• Prepared dataset documents imports, recodes, exclusions and missing-data treatment
• Descriptive outputs profile the sample, outcomes and key data limitations
• Selected tests answer stated questions with assumptions and effect sizes
• Regression or association analysis identifies evidence relevant to the decision
• Findings presentation distinguishes results, interpretation, limitations and recommended actions