What is statistical testing?
A method to determine if observed data patterns are due to chance or reflect a real effect.
What is the null hypothesis (H₀)?
The assumption that there is no difference or effect.
What is the alternative hypothesis (H₁)?
The assumption that there is a difference or effect.
What does a small p-value mean?
It provides strong evidence against the null hypothesis.
What is the t-statistic?
A measure of the size of difference between group means relative to data variation.
When should you use a Student’s t-test?
When comparing means of two groups with equal variances.
When should you use Welch’s t-test?
When comparing means of two groups with unequal variances.
When should you use One-way ANOVA?
To compare means across three or more groups.
What does Tukey’s HSD test do?
It identifies which group pairs differ after an ANOVA shows significance.
When should you use a Chi-squared test?
To test association between two categorical variables.
Which test is safer when variances are unequal?
Welch’s t-test.
Which test compares means from multiple groups?
One-way ANOVA.
What test should you use for non-normal or skewed data?
A non-parametric test like Kruskal–Wallis.
How can statistical testing help in your FPA role?
It supports data-driven decisions and validates trends.
What test compares damage rates for different bottle types?
Welch’s t-test or Chi-squared test.
What test checks if sales differ by customer education?
One-way ANOVA followed by Tukey’s HSD.
What test can reveal if leavers differ across departments?
Chi-squared test.
What helps check if variance assumptions hold?
Comparing standard deviations or using Levene’s test.
Why visualise data before testing?
To understand distribution, spot outliers, and choose the correct test.
