Scribd
Upload
5 views4 pages

Statistical Tests Overview Guide

The document outlines various statistical tests used for hypothesis testing, including the One-Sample Z-Test, One-Sample T-Test, One-Way ANOVA, and others. Each test is associated with specific conditions regarding population variance, sample size, and the nature of the data being analyzed. The document also describes the null and alternative hypotheses for each test, emphasizing their applications in comparing means and proportions.

Uploaded by

kamikuroichi
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views4 pages

Statistical Tests Overview Guide

The document outlines various statistical tests used for hypothesis testing, including the One-Sample Z-Test, One-Sample T-Test, One-Way ANOVA, and others. Each test is associated with specific conditions regarding population variance, sample size, and the nature of the data being analyzed. The document also describes the null and alternative hypotheses for each test, emphasizing their applications in comparing means and proportions.

Uploaded by

kamikuroichi
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Used when:

One-Sample Z-Test • Population variance is known


• The sample size is large (n > 30)

One-Sample Z-Test (Z-Score)

One-Sample Z-Test (Z-Value) 𝑃𝑃(𝑍𝑍)


Two-Tailed: 2 ∗ (1 − 𝑍𝑍𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣 )
One-Sample Z-Test (P-Value) Right Tailed: (1 − 𝑍𝑍𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣 )
Left Tailed: 𝑍𝑍𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣𝑣
If p < α: Reject H₀ (evidence supports H₁)
If p ≥ α: Fail to reject H₀ (no evidence to support H₁)

Used when:
One-Sample T-Test • Population variance is unknown
• The sample size is small (n < 30)

Degrees of Freedom 𝑑𝑑𝑑𝑑 = 𝑛𝑛 − 1

Used when:
One-Way ANOVA Test • Comparing means across 3 or more groups
• Testing for differences in group means
𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉 𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏𝑏 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔
𝐹𝐹 =
𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉𝑉 𝑤𝑤𝑤𝑤𝑤𝑤ℎ𝑖𝑖𝑖𝑖 𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔𝑔

Used when:
• Testing proportions (e.g., defect rate)
One-Sample Proportion Test
• Comparing sample proportion to a known
population proportion
𝑝𝑝̂ − 𝑝𝑝
𝑧𝑧 =
𝑝𝑝𝑝𝑝
�
𝑛𝑛
𝑞𝑞 = 1 – 𝑝𝑝
# 𝑜𝑜𝑜𝑜 𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑𝑑
𝑝𝑝̂ =
# 𝑜𝑜𝑜𝑜 𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠
Used when:
• The sample size is large (n ≥ 30)
Two-Sample Z-Test • Tests the difference between two
population’s means, while knowing the
population standard deviation or variance

Null Hypothesis 𝜇𝜇1 = 𝜇𝜇2


Alternative Hypothesis 𝜇𝜇1 ≠ 𝜇𝜇2

Used when:
Two Sample Proportion Test • Compare two different populations having
some single characteristic

𝑥𝑥1
𝑝𝑝1 =
𝑛𝑛1
𝑥𝑥2
𝑝𝑝2 =
𝑛𝑛2
𝑥𝑥1 + 𝑥𝑥2
𝑝𝑝 =
𝑛𝑛1 + 𝑛𝑛2
Null Hypothesis 𝑝𝑝1 = 𝑝𝑝2
Alternative Hypothesis 𝑝𝑝1 ≠ 𝑝𝑝2

Used when:
• Comparing the average of two groups
Two-Sample T-Test (Pooled Variance)
• Unknown standard deviation
• expected SDs are EQUAL
Used when:
• Comparing the value of two groups when
Mann Whitney U-Test
you can’t assume normality distribution
• Test is robust (prone) to outliers

Used when:
• Before and After
Paired T-Test
• Pre-Test and Post-Test
• T-Distribution

Used when:
• Before and After
Paired Wilcoxon Sign Rank Test • Pre-Test and Post-Test
• Normality cannot be assumed
• Ranking Method

W = Sum of the two lowest ranks

Used when:
• Comparing the average of two groups
Two Sample T-Test (Welch)
• Unknown Standard Deviation
• Expected SDs to be UNEQUAL

You might also like