MKB2705 Chap.10 Chi-Square, t-Tests and Correlation
Chi-Square, t-Tests and Correlation
Method selection begins with the research contrast, variable roles and design rather than a remembered menu. Chi-square addresses association between categorical variables by comparing observed cell counts with counts expected under independence. Inspect the full table, directed percentages and expected counts before testing. A significant statistic does not show which cells matter or whether the pattern is important.
Report group distributions, percentage-point differences and an association measure such as Cramér's V where appropriate. Sparse cells may require a meaningful category combination, an exact method or a descriptive conclusion; merging only inconvenient categories is not defensible. A t-test compares means under a selected structure.
Independent groups require independent observations and a quantitative outcome with a mean that answers the question. Welch's form protects against unequal variances without requiring equal group sizes. A paired t-test analyses within-pair differences and therefore needs correctly matched observations.
Report the mean difference in original units, confidence interval, group summaries and a standardised effect only when it helps interpretation. Correlation summarises the direction and strength of a linear association between two quantitative variables on cases with valid paired data. Always inspect the scatterplot. Curvature, clusters, restricted range and influential observations can make one coefficient misleading.
Pearson correlation is unchanged by swapping variables and does not establish which variable causes the other. A high value can arise from a common cause, selection or shared measurement. The chapter's independent examples use a categorical access-by-period table for chi-square, separate day and evening summaries for a Welch comparison, and paired access and renewal-intention scores for correlation.
Each analysis starts with a valid-base and assumption audit, performs transparent arithmetic or software checks, and ends with a bounded decision statement. Across all three methods, the result noun matters: distribution difference for chi-square, mean difference for a t-test and linear association for correlation. The method name cannot substitute for magnitude, units or business consequence.
Reproduce SPSS output from controlled syntax, reconcile sample sizes with the data ledger and investigate any unexpected base change. This chapter teaches standard inferential canon aligned to the official sequence and report requirement. All values, worked models and practice prompts are independently authored.
What this chapter covers
- 01
Decision focus
- 02
Evidence control
- 03
Error control
- 04
Claim boundary
- 05
Decision use
AskSia-authored practice weighting (not an official mark scheme): Original worked model: chi-square, t-tests and correlation
- +1State the management or evidence question, population and decision use before naming a method.
- +1Choose and defend the relevant design, measure, sample or analysis, preserving the correct valid base.
- +1Report the result or planned output with magnitude, uncertainty and a precise evidence noun.
- +1State the main limitation and a conditional decision or follow-up that does not exceed the evidence.
Key terms
- chi-square test
- A key concept in Chi-Square, t-Tests and Correlation: define it in the population, context and decision for this study rather than relying on a label alone.
- Welch t-test
- A control term used to keep chi-square, t-tests and correlation technically and conceptually traceable across the project.
- Pearson correlation
- A boundary or diagnostic that should appear beside the relevant result, not only in a generic limitations paragraph.
Chi-Square, t-Tests and Correlation FAQ
How does chi-square, t-tests and correlation support MKB2705 assessment?
It supplies a specific research decision, evidence control and claim boundary that can support the proposal, class-test reasoning, SPSS report or reflection. Apply it to your own project and current Moodle task rather than copying the worked model.
What is the most common chi-square, t-tests and correlation mistake?
The common failure is letting a convenient method, software output or confident phrase replace the decision question and represented evidence. Keep population, construct, valid base and design visible.
Can AI complete this chi-square, t-tests and correlation work?
No. Follow the current task-specific rule. Use only permitted support, verify every source and number, author submitted prose yourself and complete the required declaration. Quizzes say AI should not be used.
Assessment move
Create a selector with variable roles, design, valid base, effect noun and assumptions. Practise one original case for each method. For chi-square, hand-check an expected count, inspect directed percentages and identify the cells driving the pattern. For a t-test, decide independent versus paired before calculating, report group summaries and express the difference in original units.
For correlation, inspect the scatterplot for curvature, clusters, range restriction and influential cases before reading the coefficient. Reconcile every SPSS sample size with the data ledger. Write three final sentences using the correct nouns: categorical distribution difference, mean difference and linear association. Each sentence must include magnitude, uncertainty or strength, population and the main boundary.
Confirm the current task's required procedure and keep all practice numbers independent.
Working through Chi-Square, t-Tests and Correlation in MKB2705? Sia is AskSia’s AI Marketing tutor — ask any MKB2705 Chi-Square, t-Tests and Correlation question and get a clear, step-by-step explanation grounded in how MKB2705 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.
