📌 Quick Reference Guide – Statistics, Hypothesis Testing & R Code

This document serves as a comprehensive guide for quick calculations, statistical

interpretations, hypothesis testing steps (Z-Test & T-Test), and corresponding R code for
execution.

1 Quick Reference Table – Formulas, Interpretation & R Code

1️⃣
Topic Formula / Interpretation R Code
Calculation

Mean (Average) X̄ = ΣX / n Central value of the mean(c(5,10,15))

dataset

Standard Deviation σ = sqrt(Σ (X - X̄ )² / Spread of data sd(c(5,10,15))

(σ) n) (higher = more
spread out)

Variance (σ²) σ² = (Standard Higher variance = var(c(5,10,15))

Deviation)² greater
inconsistency in
data

Probability (Single P(A) = Favorable Likelihood of an choose(4,1)/

Event) Outcomes / Total event occurring choose(52,1)
Outcomes

Binomial Probability P(X = k) = C(n,k) Probability of k dbinom(3,5,0.6)

p^k (1-p)^(n-k) successes in n trials

Expected Value E(X) = n * p Average number of 10 * 0.6

(Binomial Mean) successes in n trials

Z-Score Z = (X - μ) / σ How far X is from pnorm(85,

the mean mean=70, sd=8,
lower.tail=FALSE)

T-Test t = (X̄ - μ) / (s / Used when sample t.test(sample,

sqrt(n)) size < 30 mu=50)

2️⃣Step-by-Step Hypothesis Testing (Z-Test & T-Test)

### **Z-Test (Large Sample, n ≥ 30)**

Step 1: Compute Z-Value

Z = (X̄ - μ) / (σ / sqrt(n))
Step 2: Find Z-Critical Value

For α = 0.05 → Z-critical = ±1.96

For α = 0.01 → Z-critical = ±2.58

Step 3: Compute P-Value

P = 2 × (1 - P(Z < computed Z))

Step 4: Decision
If P < α → Reject H₀
If P > α → Fail to reject H₀

### **T-Test (Small Sample, n < 30)**

Step 1: Compute T-Value

t = (X̄ - μ) / (s / sqrt(n))

Step 2: Find T-Critical Value (from t-table)

Step 3: Compute P-Value

Step 4: Decision
If P < α → Reject H₀
If P > α → Fail to reject H₀

3️⃣Interpretation Based on Hypothesis Type

### **Two-Tailed Test**
- If P < α → Reject H₀ → Significant difference exists.

### **Left-Tailed Test**

- If P < α → Reject H₀ → Sample mean is significantly lower.

### **Right-Tailed Test**

- If P < α → Reject H₀ → Sample mean is significantly higher.

4️⃣Final Interpretation Statement Templates

### **Two-Tailed Test Interpretation**

If P < α (e.g., 0.05):

“It is highly significant that the sample mean is different from the population mean. Since
the P-value is less than 0.05, we reject H₀ and conclude that there is a statistically significant
difference between the sample and population means.”

If P > α:
“There is not enough evidence to conclude a significant difference. Since the P-value is
greater than 0.05, we fail to reject H₀, meaning the sample mean is not significantly different
from the population mean.”

### **Left-Tailed Test Interpretation**

If P < α:

“It is highly significant that the sample mean is lower than the population mean. Since the P-
value is less than 0.05, we reject H₀ and conclude that the sample mean is significantly
lower.”

If P > α:

“There is not enough evidence to conclude that the sample mean is lower. Since the P-value
is greater than 0.05, we fail to reject H₀, meaning the sample mean is not significantly lower
than the population mean.”

### **Right-Tailed Test Interpretation**

If P < α:

“It is highly significant that the sample mean is higher than the population mean. Since the
P-value is less than 0.05, we reject H₀ and conclude that the sample mean is significantly
higher.”

If P > α:

“There is not enough evidence to conclude that the sample mean is higher. Since the P-value
is greater than 0.05, we fail to reject H₀, meaning the sample mean is not significantly higher
than the population mean.”

5️⃣Graph Interpretation for Statistical Tests

### **Normal Distribution Curve Interpretation**

A normal distribution is a symmetric, bell-shaped curve centered around the mean (μ). The
probability density decreases as we move away from the mean.

- **68% of data** falls within 1 standard deviation (σ) of the mean.

- **95% of data** falls within 2 standard deviations (σ) of the mean.

- **99.7% of data** falls within 3 standard deviations (σ) of the mean.

Interpretation Example: If a Z-score is **+2**, it means the value is **2 standard deviations
above the mean**, and the probability of a higher value is approximately **2.5%**.

### **Z-Test and T-Test Graph Interpretation**

In hypothesis testing, we use the standard normal distribution or t-distribution to
determine whether our test statistic falls in the rejection region.

- **Critical region (shaded area in tail(s))**: If the test statistic falls in this area, we reject \
( H_0 \).

- **Non-critical region (center part of the curve)**: If the test statistic falls here, we fail to
reject \( H_0 \).

### **Confidence Interval Interpretation on Graphs**

A confidence interval (CI) is represented as a range on a number line. The wider the
interval, the more uncertainty in the estimate.

- **If the CI includes the hypothesized population mean (μ), we fail to reject \( H_0 \).**

- **If the CI does not include μ, we reject \( H_0 \).**

Example: If a 95% confidence interval for the mean is (72, 78), and μ = 70 is outside this
range, we reject \( H_0 \) and conclude the sample mean is significantly different from 70.

6️⃣Z-Score Lookup Table

This table provides the cumulative probability (area under the normal curve) for different
Z-scores. The values represent the probability that a random variable is **less than or equal
to** the given Z-score.

Z-Score Probability (P-value)

-3.00 0.0013

-2.58 0.0049

-2.33 0.0099

-2.00 0.0228

-1.96 0.0250

-1.64 0.0500

-1.00 0.1587

0.00 0.5000

+1.00 0.8413

+1.64 0.9500

+1.96 0.9750
+2.00 0.9772

+2.33 0.9901

+2.58 0.9951

+3.00 0.9987

7️⃣R Code for Z-Score Calculation

You can calculate Z-scores in R using the following command:

```r
# Define values
X <- 60000 # Value to check
mu <- 50000 # Population mean
sigma <- 5000 # Standard deviation

# Compute Z-Score
z_score <- (X - mu) / sigma
z_score
```

This will return **2**, confirming that 60,000 is 2 standard deviations above the mean.

8️⃣Graph Interpretation
### **Box Plot Interpretation**

A box plot shows the spread of data using quartiles and helps detect outliers.

- **Median (Q2 line):** The middle value of the dataset.

- **Box (IQR = Q3 - Q1):** Contains the middle 50% of the data.

- **Whiskers:** Extend to the minimum and maximum values within 1.5×IQR.

- **Outliers:** Values outside the whiskers.

**R Code to Generate a Box Plot:**

```r
data <- c(10, 20, 22, 25, 30, 35, 40, 50, 100)
boxplot(data, main='Box Plot', col='lightblue')
```

### **Pie Chart Interpretation**

A pie chart represents categorical data as proportional slices.

- **Larger slices indicate higher proportions.**

- **Good for visualizing part-to-whole relationships.**

**R Code to Create a Pie Chart:**

```r
labels <- c('A', 'B', 'C', 'D')
values <- c(40, 30, 20, 10)
pie(values, labels=labels, col=rainbow(4))
```

### **Bar Chart Interpretation**

A bar chart is used to compare values across different categories.

- **Height of bars represents frequency or value.**

- **Good for comparing groups.**

**R Code for a Bar Chart:**

```r
categories <- c('A', 'B', 'C', 'D')
values <- c(10, 20, 30, 40)
barplot(values, names.arg=categories, col='blue', main='Bar Chart')
```

### **Histogram Interpretation**

A histogram displays the distribution of numerical data.

- **Used for detecting skewness and spread.**

- **Higher bars indicate more frequent values.**

**R Code to Generate a Histogram:**

```r
data <- c(10, 12, 15, 18, 22, 25, 30, 35, 40, 50, 55, 60)
hist(data, col='green', main='Histogram', xlab='Values')
```

### **Normal Curve Interpretation**

A normal distribution curve is symmetric around the mean.

- **Bell-shaped curve with most values near the center.**

- **68% of data within 1σ, 95% within 2σ, 99.7% within 3σ.**
**R Code for a Normal Curve:**

```r
x <- seq(-4, 4, length=100)
y <- dnorm(x, mean=0, sd=1)
plot(x, y, type='l', col='red', lwd=2, main='Normal Curve')
```

### **Skewness Interpretation**

Skewness indicates the direction and extent of asymmetry in data.

- **Symmetric Data:** Skewness = 0.

- **Right-Skewed (Positive):** Mean > Median > Mode.

- **Left-Skewed (Negative):** Mean < Median < Mode.

**R Code to Calculate Skewness:**

```r
library(moments)
data <- c(10, 12, 15, 20, 35, 50, 80)
skewness(data)
```

### **Confidence Interval Interpretation**

A confidence interval gives a range where the true population parameter is likely to fall.

- **If the CI includes the hypothesized value, we fail to reject H₀.**

- **If the CI excludes it, we reject H₀.**

**R Code to Compute a Confidence Interval:**

```r
data <- c(50, 52, 53, 54, 55, 56, 58, 60, 62, 64)
t.test(data, conf.level=0.95)
```

### **Z-Score Interpretation with Graph**

A Z-score tells how far a value is from the mean in terms of standard deviations.

- **Z = 0:** Value is exactly at the mean.

- **Z > 0:** Value is above the mean.

- **Z < 0:** Value is below the mean.

**R Code to Plot a Z-Score on a Normal Curve:**

```r
x <- seq(-4, 4, length=100)
y <- dnorm(x)
plot(x, y, type='l', col='blue')
abline(v=2, col='red', lwd=2, lty=2) # Marks Z = 2
```

### **T-Statistic Interpretation with Graph**

A T-distribution is used when the sample size is small (n < 30).

- **T-distribution is wider than the normal curve for small samples.**

- **For large samples, T-distribution approaches normality.**

**R Code to Plot a T-Distribution:**

```r
x <- seq(-4, 4, length=100)
y <- dt(x, df=10)
plot(x, y, type='l', col='blue', lwd=2, main='T-Distribution')
```