Hypothesis Testing Flashcards
Core Steps of Hypothesis Testing
- State your hypotheses:
H₀: the default assumption (e.g., "the average price = 3500") H₁: the alternative (e.g., "the average price ≠ 3500")
- Choose a test depending on:
Type of data (numeric/categorical) Number of variables (1 or 2) Sample size
- Run the test in SPSS
- Check the p-valueIf p < 0.05, reject H₀ (you have strong evidence)If p > 0.05, fail to reject H₀ (not enough evidence)
One-sample T-test
Compare a sample mean to a known value
Eg. Is the average diamond price > $3500?
Paired-samples T-test
Compare two variables for the same group
Is the average length of diamonds different from their width?
Independent-samples T-test
Compare means between two groups
Eg. Are lab-grown diamonds heavier than natural ones?
Chi-Square Test
Check association between two categories
Is diamond color associated with type (natural/lab-grown)?
Two-sided (≠)
You just want to check if it’s different (higher OR lower).
One-sided (> or <)
You want to check in a specific direction (just higher or just lower).
What does a p-value tell you?
The probability that your results happened by chance. If p < 0.05, we reject the null hypothesis.
What are H₀ and H₁ in hypothesis testing?
H₀ is the null hypothesis (no effect), H₁ is the alternative hypothesis (there is an effect).
When do you use a one-sample T-test?
When comparing a sample mean to a known value (e.g., is average price = $3500?).
When do you use an independent samples T-test?
To compare the means of two different groups (e.g., lab-grown vs natural diamonds).
What is the difference between a one-sided and two-sided test?
A one-sided test looks for a difference in one direction (greater or less), while a two-sided test checks for any difference (≠).
What type of test should you use to check if two categorical variables are related?
Chi-Square Test.
What does it mean if your p-value is 0.03?
There’s only a 3% chance the result is due to randomness. Reject H₀ with 95% confidence.
What kind of error is it if you reject H₀ when it’s actually true?
Type I Error (false positive).
What kind of error is it if you fail to reject H₀ when it’s false?
Type II Error (false negative).
Kolmogorov–Smirnov Test
Check if a variable follows a distribution
What test is used to compare the means across more than two groups?
One-Way ANOVA (Analysis of Variance)
What is the null hypothesis in an ANOVA test?
All group means are equal.
What does a significant result in ANOVA tell you?
At least one group is different, but not which one—you need further post-hoc tests to know more.
What is the SPSS path for running a One-Way ANOVA?
Analyze → Compare Means → One-Way ANOVA
When should you use correlation analysis?
When examining the relationship between two numeric (interval/ratio) variables.
What does the correlation coefficient (r) indicate?
The strength and direction of a linear relationship:
r ≈ 1 → Strong positive
r ≈ -1 → Strong negative
r ≈ 0 → Weak/No correlation
What SPSS path do you follow to run a correlation analysis?
Analyze → Correlate → Bivariate
