Concepts involving confidence interval and hypothesis testing (population mean and proportion)

Concepts

Population Sample
Mean 𝜇 or Parameter 𝑥̅ or Statistic
∑(𝑥𝑖 − 𝜇)2 ∑(𝑥𝑖 − 𝑥̅ )2
Standard Deviation 𝜎=√ 𝑆=√
𝑁 𝑛
Proportion 𝑝 𝑝̂
Size 𝑁 𝑛
Statistical Hypothesis

One Tailed Left Two Tailed One Tailed Right

Null Hypothesis 𝐻0 : 𝜇 = 𝑥 𝑜𝑟 𝐻0 : 𝜇 ≥ 𝑥 𝑜𝑟 𝐻0 : 𝜇 ≤ 𝑥
Alternative Hypothesis 𝐻1 : 𝜇 < 𝑥 𝐻1 : 𝜇 ≠ 𝑥 𝐻1 : 𝜇 > 𝑥
Level of Significance
𝛼 𝛼
Confidence Level 𝛼 𝑧 𝑜𝑟 𝑇𝑤𝑜 𝑇𝑎𝑖𝑙𝑒𝑑 𝐿𝑒𝑓𝑡 𝑜𝑟 𝑅𝑖𝑔ℎ𝑡 𝑇𝑎𝑖𝑙𝑒𝑑
2 2
90% 10% 5% ±1.645 ±1.28
95% 5% 2.5% ±1.96 ±1.645
98% 2% 1% ±2.326 ±1.96
99% 1% 0.5% ±2.576 ±2.326
Test Statistic

t - test z - test
Criteria 𝑛 < 30 𝑛 ≥ 30
𝑥̅ − 𝜇 𝑥̅ − 𝜇 𝑥̅ − 𝜇
Formula 𝑡= 𝑠 𝑧 = 𝑠 𝑜𝑟 𝑧 = 𝜎
√𝑛 √𝑛 √𝑛
Confidence
Interval of 𝑆 𝑆 𝜎 𝜎
𝑥̅ − 𝑡𝛼 ( ) < 𝜇 < 𝑥̅ + 𝑡𝛼 ( ) 𝑥̅ − 𝑧𝛼 ( ) < 𝜇 < 𝑥̅ + 𝑧𝛼 ( )
Population 2 √𝑛 2 √𝑛 2 √𝑛 2 √𝑛
Parameter
𝑆 𝜎
Margin of error 𝐸 = 𝑡𝛼 ( ) 𝐸 = 𝑧𝛼 ( )
√𝑛 2 2 √𝑛
Computing for the length of the confidence interval

t - test z - test
Length of the 𝑆 𝜎
confidence 𝐿 = 2 [𝑡𝛼 ( )] 𝐿 = 2 [𝑧𝛼 ( )]
interval 2 √𝑛 2 √𝑛
Hypothesis Testing on population mean and proportion

Steps Population Mean / Parameter Population Proportion

𝜇 = 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛
𝑝 = 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛
𝑥̅ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑚𝑒𝑎𝑛
Identify the given 𝑝̂ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛
𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒
𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒
𝑆 = 𝑆𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝐷𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
𝐻0 : 𝜇 = 𝐻0 : 𝑝 =
𝐻0 : 𝜇 ≥ 𝐻0 : 𝑝 ≥
𝐻0 : 𝜇 ≤ 𝐻0 : 𝑝 ≤
Formulate the
𝑎𝑛𝑑 𝑎𝑛𝑑
Hypothesis
𝐻1 : 𝜇 ≠ 𝐻1 : 𝑝 ≠
𝐻1 : 𝜇 > 𝐻1 : 𝑝 >
𝐻1 : 𝜇 < 𝐻1 : 𝑝 <
Select the correct t - test z - test
z - test
test statistic 𝑛 < 30 𝑛 ≥ 30
Identify the
appropriate rejection Depends on the level of significance Depends on the level of significance
region
t - test z - test 𝑝̂ − 𝑝
Compute the test 𝑥̅ − 𝜇 𝑥̅ − 𝜇 𝑧=
𝑡= 𝑠 𝑧= 𝜎
statistic score √𝑝(1 − 𝑝)
√𝑛 √𝑛 𝑛
Decide whether to 𝐹𝑎𝑖𝑙 𝑡𝑜 𝑟𝑒𝑗𝑒𝑐𝑡 𝑡ℎ𝑒 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠 𝐹𝑎𝑖𝑙 𝑡𝑜 𝑟𝑒𝑗𝑒𝑐𝑡 𝑡ℎ𝑒 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠
reject or fail to reject 𝑜𝑟 𝑜𝑟
the null hypothesis 𝑅𝑒𝑗𝑒𝑐𝑡 𝑡ℎ𝑒 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠 𝑅𝑒𝑗𝑒𝑐𝑡 𝑡ℎ𝑒 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠
Draw a conclusion Depends on the word problem Depends on the word problem
Concepts involving Bivariate Data and Scatter Plot

Bivariate Data

- data that involves two variables where one of the variable determine the value of the other variable

Scatter Plot

- graph that shows how each point is scattered

- trend line, correlation between the variables

Form, Trend, and Direction on a Scatter Plot

- Form (shape), linear (the trend line is straight) or nonlinear (the trend line curved)

- Trend (direction), is the data positive (trend line increases) or negative (trend line decreases)

- Strength (variation), is the variables association strong (least scattered in the trend line) or weak (more
scattered in the trend line)
Constructing a Scatter Plot

Example Scatter Plot

50
45
45
40
Y - Axis (Dependent Variable)

40
35
35
30
30
25
25
20
20
15
15
10
10
5
5
0
0 1 2 3 4 5 6 7 8 9 10
X - Axis (Independent Variable)

Concepts involving Pearson Product Coefficient

r value Description
r =1 Perfect Positive Relationship
0.75 ≤ r < 1.00 Very High Positive Relationship
0.50 ≤ r < 0.75 Moderately High Positive Relationship
0.25 ≤ r < 0.50 Moderately Low Positive Relationship
0.00 < r < 0.25 Very Low Positive Relationship
r =0 Zero or No Relationship
r = -1 Perfect Negative Relationship
-1.00 < r ≤ -0.75 Very High Negative Relationship
-0.75 < r ≤ -0.50 Moderately High Negative Relationship
-0.50 < r ≤ -0.25 Moderately Low Negative Relationship
-0.25 < r < 0.00 Very Low Negative Relationship
2
Name 𝑥 𝑦 𝑥 𝑦2 𝑥𝑦
1 𝑥1 𝑦1 (𝑥1 )2 (𝑦1 )2 𝑥𝑦1
n 𝑥𝑛 𝑦𝑛 (𝑥𝑛 )2 (𝑦𝑛 )2 𝑥𝑦𝑛
𝑛 𝑛 𝑛 𝑛 𝑛
2 2
Summation ∑𝑥 ∑𝑦 ∑𝑥 ∑𝑦 ∑ 𝑥𝑦
𝑖=1 𝑖=1 𝑖=1 𝑖=1 𝑖=1

Pearson Correlation Coefficient

𝑛(∑ 𝑥𝑦) − (∑ 𝑥)(∑ 𝑦)
𝑟=
√[𝑛 ∑ 𝑥 2 − (∑ 𝑥)2 ][∑ 𝑦 2 − (∑ 𝑦)2 ]