Statistics
Symbol Name Purpose
μ Population Mean Represents the average score of all observations in the
population, used to describe the central tendency.
X̄ Sample Mean Represents the average score of all observations in the sample,
used to estimate the population mean.
X Score Denotes an individual data point in the dataset, which is used to
compute summary statistics.
σ Population Standard Measures the spread or dispersion of scores in the population,
Deviation showing how much each score varies from the population mean.
s Sample Standard Measures the spread or dispersion of scores in the sample, used
Deviation to estimate the population standard deviation.
n Number of Scores in a Represents the total number of observations in the sample, used
Sample in calculating sample-based statistics.
N Number of Scores in a Represents the total number of observations in the population,
Population used in calculating population-based statistics.
r Sample Correlation Quantifies the strength and direction of the relationship between
two variables in the sample.
ρ (rho) Population Correlation Quantifies the strength and direction of the relationship between
two variables in the population.
Descriptive Statistics
Descriptive statistics are a way to summarise or describe data from samples and populations.
These summaries can be divided into two main categories:
1. Measures of Central Tendency: A single representative value of a data set
2. Measures of Variability: A single value describing the spread or dispersion of data around the centre.
Measures of Central Tendency
Sample Mean
The symbol for the sample mean is 𝑋, pronounced "X-bar."
The formula for the mean is:
∑𝑋
𝑋= 𝑛
Where:
● ∑: Sigma, the sum of.
● ∑X: The sum of all the scores in the distribution.
● n: The total number of observations.
Population Mean
The symbol for the population mean is μ, pronounced "mu."
The formula for the population mean is:
μ = ΣX / N
Where:
● ΣX: The sum of all the scores in the population.
● N: The total number of observations in the population.
Example:
Given the data: 6, 11, 15, 24, 37,
The calculation is:
X̄ = (6 + 11 + 15 + 24 + 37) / 5
X̄ = 93 / 5
X̄ = 18.6
Median
The median is the middle value in an ordered data set. It divides the distribution into two equal halves.
● If the number of data points is odd, the median is the middle score.
● If the number of data points is even, the median is the average of the two middle scores.
Example 1
Data: 42, 46, 50, 54, 58
The median is 50 because it is the middle value.
Example 2
Data: 9, 11, 13, 15, 17, 19, 21, 23
The median is calculated as the average of 15 and 17:
Median = (15 + 17) / 2 = 16
Mode
The mode is the most frequently occurring value(s) in a distribution. A dataset can have one mode
(unimodal), more than one mode (bimodal or multimodal), or no mode at all.
Example
Data: 2, 5, 9, 9, 9, 15, 18, 24
The mode is 9 because it appears most frequently.
Skewness
Skewness refers to the shape of distribution of the data values:
● Positively skewed distribution: A.K.A. right-skewed as most scores are clustered at the lower end,
with the mean greater than the median and mode.
● Negatively skewed distribution: A.K.A. left-skewed as most scores are clustered at the higher end,
with the mean less than the median and mode.
● Normal distribution: The mean, median, and mode are the same, the distribution is symmetric, and
the kurtosis is low to zero.
● Kurtosis: The tailedness of the distribution. High kurtosis = heavy tails (more outliers)
Measures of Variability
Range
The range measures the spread of data by calculating the difference between the highest and lowest scores.
Outliers make this useless.
Formula: Range = Highest score - Lowest score
Example Data: 3, 6, 15, 37, 59, 70
Range = 70 - 3 = 67
Standard Deviation
The standard deviation measures the average distance of each score from the mean, providing insight into
how much the scores vary.
The formula for the sample standard deviation (s) is:
s = √(Σ(X - X̄)² / (n - 1))
Where:
● X = individual scores
● X̄ = sample mean
● n = number of scores in the sample
Example
Data: 45, 35, 40, 50, 30
1. Calculate the mean:
X̄ = (45 + 35 + 40 + 50 + 30) / 5 = 40
2. Compute deviations from the mean and square them:
(45 - 40)² = 25, (35 - 40)² = 25, (40 - 40)² = 0, (50 - 40)² = 100, (30 - 40)² = 100
3. Sum the squared deviations:
Σ(X - X̄)² = 25 + 25 + 0 + 100 + 100 = 250
4. Divide by n - 1 and take the square root:
s = √(250 / (5 - 1)) = √(250 / 4) = √62.5 ≈ 7.91
Population Standard Deviation
The formula for the population standard deviation is:
σ = √(Σ(X - μ)² / N)
Where:
● σ = population standard deviation
● Σ(X - μ)² = sum of the squared differences between each data point and the population mean
● μ = population mean
● N = total number of observations in the population
Variance
Variance is the average of the squared deviations from the mean. It is closely related to standard deviation
but does not take the square root.
Formula:
Variance (s²) = Σ(X - X̄)² / (n - 1)
Example Using the data above, the variance is:
s² = 250 / 4 = 62.5
Practice Exercises
For the dataset 6, 11, 17, 23, 31, 46, 79, 82, 96, 114, 136
1.1 Calculate the mean, median, and mode.
1.2 Determine the range.
1.3 Compute the standard deviation.
1.4 Find the variance.
For the dataset 5, 7, 9, 11, 12, 12, 15, 20, 23, 25
2.1 Calculate the mean, median, and mode.
2.2 Determine the range.
2.3 Compute the standard deviation.
2.4 Find the variance.
Inferential Statistics
Understanding Inferential Statistics
Inferential statistics refers to a set of methods that allow researchers to make conclusions or generalizations
about a population based on data collected from a sample. These techniques provide probabilities to
determine whether observed differences or relationships are due to random chance or represent true
population characteristics.
Properties of a Normal Distribution
A normal distribution, often visualized as a bell curve, is a fundamental concept in inferential statistics. It has
the following characteristics:
● Symmetry: The left and right sides of the curve are mirror images of each other = no skewness.
● Equality of Measures: The mean, median, and mode all share the same value.
● Bell Shape: The curve is highest at the mean and tapers off symmetrically on both sides.
● Asymptotic Tails: They only reach the horizontal axis at infinity.
Hypothesis Testing and Statistical Tests
In hypothesis testing, researchers make probability-based statements about population properties using
sample data. Absolute certainty is unattainable; instead, inferences are made with a specific level of
confidence. This process involves formulating and testing hypotheses.
Types of Hypotheses
Null Hypothesis (H₀)
The null hypothesis states that there is no effect or difference in the population. It serves as the default or
starting assumption in hypothesis testing.
Example: The difference between two population means is zero:
H₀: μ₁ = μ₂
Reasoning: While proving something to be true is challenging, disproving it through evidence is feasible. For
instance, the statement "Everyone has ten fingers" can be challenged by finding one person with eleven
fingers.
Alternative Hypothesis (H₁)
The alternative hypothesis asserts the existence of an effect or difference. It contradicts the null hypothesis.
Example: The means of two populations are not equal:
H₁: μ₁ ≠ μ₂
Directional Hypothesis (One-Tailed Hypothesis)
A directional hypothesis predicts the specific direction of the relationship between variables, stating whether
one variable will increase or decrease as the other variable changes. For example, "Students who study for
longer periods will score higher on the test," which suggests a positive direction.
Non-Directional Hypothesis (Two-Tailed Hypothesis)
A non-directional hypothesis does not specify a direction, but rather it states that there is a difference or
relationship between variables, without predicting whether it will be positive or negative. For example,
"There is a difference in test scores between students who study for long periods and those who study for
short periods," which simply suggests a difference exists, regardless of direction.
Example: Productivity in Structural Engineering
A group of mechanical engineers was assigned a project to build a mechanically operated telescope. The
engineers were divided into two groups:
● Experimental Group: Received additional training in project management.
● Control Group: Followed traditional engineering methods.
The experimental group demonstrated higher productivity. The researcher seeks to determine if the increase
in productivity can be attributed to the project management training (independent variable).
Key Question: Can we conclude that the observed difference in productivity is statistically significant and not
due to random variation?
One-Tailed vs. Two-Tailed Tests
One-Tailed Test
A one-tailed test evaluates whether a sample mean is significantly higher or lower than the population mean,
but not both.
Example: Testing if the experimental group outperformed the control group.
Two-Tailed Test
A two-tailed test checks for differences in both directions, testing whether a sample mean is either
significantly higher or lower.
More common than one-tailed tests due to the following reasons:
● Researchers often do not have prior knowledge of the direction of the effect (exploratory studies).
● Researchers may prefer flexibility to account for unexpected results.
Example: Hypothesis Testing in Practice
Adventure Program and Self-Concept
A researcher examines whether participating in adventure programs improves self-concept. The self-concept
scores for a group of boys are recorded before and after the program:
Boys Score Before Score After
A 33 36
B 30 31
C 40 37
D 27 36
E 18 24
Formulating Hypotheses:
H₀: The adventure program has no effect on self-concept (H₀: μ_before = μ_after).
H₁: The adventure program improves self-concept (H₁: μ_before < μ_after).
Attitudes and Relationships
Donn Byrne and Barbara Blaylock (1963) investigated whether people with similar attitudes are more likely to
form relationships. They examined whether political attitudes of husbands and wives align.
Formulating Hypotheses:
H₀: Husbands and wives do not share similar political attitudes (H₀: No correlation).
H₁: Husbands and wives share similar political attitudes (H₁: Positive correlation).
Understanding Statistical Techniques
Correlational Analysis
Definition: Correlational analysis is a statistical method used to examine the relationship between two
continuous variables. It helps determine whether changes in one variable are systematically associated with
changes in another.
Key concepts include:
● Covariance: If changes in Variable 1 are associated with changes in Variable 2, they are said to be
covariant.
● Question of Interest: Is there a systematic relationship between these two variables?
Graphic Representation: Scatterplots
Scatterplots are visual tools used to illustrate the relationship between two variables:
● The X-axis represents Variable 1.
● The Y-axis represents Variable 2.
● Each data point on the scatter plot corresponds to a pair of values from the dataset.
Types of Relationships in Scatter Plots:
● No Relationship: Dots appear randomly with no discernible pattern.
● Positive Relationship: High scores on Variable 1 are associated with high scores on Variable 2, and
low scores on Variable 1 are associated with low scores on Variable 2.
● Negative Relationship: High scores on Variable 1 are associated with low scores on Variable 2, and
vice versa.
● Curvilinear Relationship: Initially, increases in Variable 1 are associated with increases in Variable 2
up to a certain point, after which increases in Variable 1 are associated with decreases in Variable 2.
Numerical Description of Relationships: Correlation Coefficient (r)
The correlation coefficient (r) quantifies the strength and direction of the relationship between two variables.
Formula for r:
r = (n Σ(XY) - (ΣX)(ΣY)) / √[(n Σ(X²) - (ΣX)²)(n Σ(Y²) - (ΣY)²)] OR r = Σ(X-𝑋)(Y-𝑌) / √Σ(X-𝑋)² Σ(Y-𝑌)²
Where:
● N: Number of observations
● X: Values of the first variable
● Y: Values of the second variable
● Σ: Summation symbol
Components of the Formula:
● XY: Product of corresponding X and Y values
● ΣX, ΣY: Sum of all X and Y values
● ΣX², ΣY²: Sum of squared values for X and Y
Interpreting the Correlation Coefficient
The interpretation of r involves four aspects:
➔ Direction:
◆ Positive (+): Both variables increase or decrease together.
◆ Negative (-): One variable increases while the other decreases.
➔ Size (Magnitude):
Guidelines for interpreting r:
◆ < 0.20: Slight correlation, almost negligible relationship
◆ 0.20–0.40: Low correlation, definite but small relationship
◆ 0.40–0.70: Moderate correlation, substantial relationship
◆ 0.70–0.90: High correlation, marked relationship
◆ 0.90: Very high correlation, very dependable relationship
➔ Shared Variance:
The coefficient of determination (r²) indicates the proportion of variance shared between the two
variables. The % of variation in y that is attributed to x.
Formula:
r² = r × r × 100
This converts shared variance into a percentage.
➔ Significance:
Significance testing evaluates whether the observed relationship is likely due to chance.
Example: Study Hours and Test Scores
Scenario: A researcher investigates the relationship between the number of study hours and test scores
among ten first-year psychology students.
Student Study Hours Test Score X² Y² XY
(X) (Y)
1 10 21 100 441 210
2 12 15 144 225 180
3 19 35 361 1225 665
4 9 13 81 169 117
5 18 10 324 100 180
6 21 12 441 144 252
7 16 9 256 81 144
8 2 16 4 256 32
9 6 20 36 400 120
10 14 17 196 289 238
ΣX = 127, ΣY = 168, ΣX² = 1943, ΣY² = 3327, ΣXY = 2138
Step 1: Calculate r:
r = (10(2138) - (127)(168)) / √[(10(1943) - (127)²)(10(3327) - (168)²)]
Substituting values:
r = (21380 - 21336) / √[(19430 - 16129)(33270 - 28224)]
r = 44 / √[3301 * 5046]
r = 44 / √16656846
r = 44 / 4081.28 ≈ 0.01
Step 2: Interpret r:
● Direction: Positive relationship (+)
● Magnitude: Almost negligible (r = 0.01)
● Shared Variance:
r² = (0.01)² = 0.0001
Converting to percentage: 0.0001 × 100 = 0.01%
This means only 0.01% of the variance in test scores can be explained by study hours.
● Significance: Answered through hypothesis testing
Understanding the Confidence Interval
A confidence interval (CI) represents the range within which we are reasonably certain that the population
parameter (e.g., mean) lies, based on the sample data. The confidence level indicates how confident we are
that the interval contains the true population parameter.
● For example, a 95% confidence level means we are 95% confident that the true population
parameter lies within the calculated range of values.
● The remaining 5% (alpha = 0.05) represents the probability of making a Type 1 error, where the true
population parameter lies outside the confidence interval.
Formula for Confidence Interval
Confidence Interval = Sample Statistic ± (Zα/2 × (σ / √n))
Where:
● Sample Statistic: The point estimate (e.g., sample mean).
● Zα/2: The critical Z-value or t-value corresponding to the alpha level and confidence level.
● σ: The population standard deviation (or sample standard deviation if unknown).
● n: The sample size.
Alpha Levels and Confidence Levels
The alpha level (α) is the probability that the true population parameter falls outside the confidence interval.
It is related to the confidence level as follows:
Alpha (α) Confidence Level Zα/2 (Critical Z-Value)
0.10 90% Confidence ±1.645
0.05 95% Confidence ±1.960
0.01 99% Confidence ±2.576
0.001 99.9% Confidence ±3.291
How Alpha and Confidence Work
● Alpha is split between the two tails of the normal distribution (e.g., for α = 0.05, each tail gets 0.025).
● A lower alpha results in a wider confidence interval, meaning more certainty but less precision.
● A higher alpha results in a narrower confidence interval, meaning less certainty but more precision.
Example of 95% Confidence Interval
Step-by-Step:
Given:
1. CI = 50 ± (1.960 × (10 / √25))
● Sample Mean (X̄) = 50 2. CI = 50 ± (1.960 × 2)
● Standard Deviation (σ) = 10 3. CI = 50 ± 3.92
● Sample Size (n) = 25 4. CI = (46.08, 53.92)
● Zα/2 = 1.960 for 95% confidence
Interpretation: With 95% confidence, the true population mean lies between 46.08 and 53.92.
T-Tests (Test of Difference)
Introduction to T-Tests
T-tests are statistical methods used to compare the means of a sample and a population or between two
groups to determine whether differences are statistically significant. They are particularly useful when the
population standard deviation (σ\ lowercase sigma) is unknown and the sample standard deviation (s) is
used as an estimate.
Key Features of T-Tests
● Purpose:
T-tests are used to determine if there is a significant difference between:
○ A sample mean and a population mean (one-sample t-test).
○ The means of two independent groups (independent t-test).
○ The means of two related groups (paired t-test).
● When to Use:
○ The population standard deviation (σ\ lowercase sigma) is unknown.
○ The sample standard deviation (s) is used as an estimate.
○ The sample data is normally distributed or the sample size is sufficiently large (Central Limit
Theorem).
The 5 Conditions of a Statistical Test:
1. Random Sampling
● Definition: The data should be collected randomly from the population, ensuring that each member
of the population has an equal chance of being included.
● Why it’s important: Random sampling helps reduce bias and ensures that the sample is
representative of the population, making the results generalizable.
2. Independence
● Definition: The observations should be independent of each other, meaning the value of one
observation should not influence the value of another.
● Why it’s important: Most statistical tests assume that the observations are independent, and
violating this assumption can lead to incorrect conclusions.
3. Normality
● Definition: The data should ideally follow a normal distribution, or the sampling distribution of the
test statistic should approximate normality, especially for small sample sizes.
● Why it’s important: Many statistical tests (e.g., t-tests) assume normality in the data. If this condition
is violated, non-parametric tests might be more appropriate.
4. Homogeneity of Variance
● Definition: The variance within each group being compared should be roughly equal. This is often
tested using Levene's test or other similar methods.
● Why it’s important: If the variances of the groups are significantly different, the results of tests like
the t-test or ANOVA may not be reliable.
5. Scale of Measurement
● Definition: The data should be measured on an appropriate scale, such as nominal, ordinal, or
interval/ratio. The choice of statistical test depends on the type of data (e.g., categorical or
continuous).
○ Nominal: Categories without a specific order (e.g., gender, race).
○ Ordinal: Categories with a meaningful order but not necessarily equal spacing (e.g., rankings,
educational levels).
○ Interval/Ratio: Numeric data where intervals are meaningful, and ratio data also has an
absolute zero (e.g., height, weight, temperature).
● Why it’s important: The scale of measurement dictates which statistical methods are appropriate. For
example, a parametric test like the t-test requires interval or ratio scale data, while non-parametric
tests may be used for ordinal or nominal data.
One-Sample T-Test Example
Scenario
A researcher investigates whether contemporary music influences adolescent risk-taking behavior. The
population mean risk-taking score is μ = 40, and the researcher collects data from a sample of 10
adolescents. The sample scores are:
35, 49, 63, 20, 18, 19, 7, 12, 31, 24
Steps to Conduct the One-Sample T-Test
Step 1: Calculate the Sample Mean (X̄)
The formula for the sample mean is:
X̄ = ΣX / n
Substitute values:
X̄ = (35 + 49 + 63 + 20 + 18 + 19 + 7 + 12 + 31 + 24) / 10
X̄ = 278 / 10
X̄ = 27.8
Step 2: Calculate the Sample Standard Deviation (s)
The formula for the sample standard deviation is:
s = √(Σ(X - X̄)² / (n - 1))
Subtract the mean (27.8) from each score (X):
X - X̄ = [35 - 27.8, 49 - 27.8, …, 24 - 27.8]
Results: 7.2, 21.2, 35.2, -7.8, -9.8, -8.8, -20.8, -15.8, 3.2, -3.8
Square these deviations:
(X - X̄)² = [51.84, 449.44, 1239.04, 60.84, 96.04, 77.44, 432.64, 249.64, 10.24, 14.44]
Compute the sum of squared deviations:
Σ(X - X̄)² = 2681.6
Divide by n - 1:
s = √(2681.6 / (10 - 1)) = √(2681.6 / 9) = √297.96 ≈ 17.26
Step 3: Calculate the Standard Error of the Mean (SE)
The formula for SE is:
SE = s / √n
Substitute values:
SE = 17.26 / √10 = 17.26 / 3.16 ≈ 5.46
Step 4: Calculate the Observed t-Value (tₒᵦs)
The formula for tₒᵦs is:
tₒᵦs = (X̄ - μ) / SE
Substitute values:
tₒᵦs = (27.8 - 40) / 5.46
tₒᵦs = (-12.2) / 5.46 ≈ -2.234
Step 5: Determine the Critical t-Value (t ᵣᵢ )
Using a t-distribution table:
Degrees of freedom (df) = n - 1 = 10 - 1 = 9
Significance level (α) = 0.05, two-tailed test
t ᵣᵢ = ±2.262
Step 6: Decision Rule
If |tₒᵦs| ≥ t ᵣᵢ , reject H₀.
Otherwise, fail to reject H₀.
Here:
|tₒᵦs| = 2.234 and t ᵣᵢ = ±2.262
Since 2.234 < 2.262, we fail to reject H₀.
Step 7: Conclusion
The null hypothesis (H₀) states that the mean risk-taking score for adolescents is 40. Since we fail to reject H₀,
the data does not provide sufficient evidence to conclude that contemporary music significantly impacts
adolescent risk-taking behavior.
Summary of One-Sample T-Test
Step Value
Sample Mean (X̄) 27.8
Standard Deviation (s) 17.26
Standard Error (SE) 5.46
Observed t-Value (tₒᵦs) -2.234
Critical t-Value (t ᵣᵢ ) ±2.262
Decision Fail to Reject H₀
Conclusion No significant difference
Two-Sample T-Test (Test of Difference)
Introduction to Two-Sample T-Test
A two-sample t-test is used to compare the means of two independent groups to determine if they are
statistically different from each other. This test assumes that the data for both groups is continuous and
normally distributed, and that the variances of the two groups are equal (homogeneity of variance).
Key Features of Two-Sample T-Tests
Purpose:
To test whether the difference between the means of two groups is statistically significant.
Example: Comparing the health scores of girls and boys.
Requirements:
● Two independent groups (e.g., experimental and control groups).
● One continuous variable (e.g., test scores).
● Random sampling and normally distributed scores.
● Homogeneity of variance: The variance in the two groups should be similar.
Steps to Conduct a Two-Sample T-Test
Step 1: State the Hypotheses
Null Hypothesis (H₀): There is no difference between the population means of the two groups.
H₀: μ₁ = μ₂
Alternative Hypothesis (H₁): There is a difference between the population means of the two groups.
H₁: μ₁ ≠ μ₂
Step 2: Check Design Requirements and Assumptions
● Two independent groups: The same participants cannot be in both groups.
● Random sampling.
● Scores are normally distributed.
● Homogeneity of variance is assumed.
Step 3: Calculate the Observed t-Value (tₒᵦs)
The formula for a two-sample t-test is:
t = (X̄₁ - X̄₂) / √[( (n₁ - 1)s₁² + (n₂ - 1)s₂²) / (n₁ + n₂ - 2) * (1/n₁ + 1/n₂)]
Where:
● X̄₁, X̄₂: Sample means for groups 1 and 2.
● s₁², s₂²: Sample variances for groups 1 and 2.
● n₁, n₂: Sample sizes for groups 1 and 2.
Step 4: Find the Critical t-Value (t ᵣᵢ )
Degrees of freedom (df):
df = n₁ + n₂ - 2 = 8 + 7 - 2 = 13
Significance level (α): 0.05, two-tailed test.
Using a t-table:
t ᵣᵢ = ±2.16
Step 5: Decision Rule
If |tₒᵦs| ≥ t ᵣᵢ , reject H₀.
Otherwise, fail to reject H₀.
Here:
|tₒᵦs| = 0.35 and t ᵣᵢ = ±2.16
Since 0.35 < 2.16, we fail to reject H₀.
Step 6: Conclusion
The null hypothesis (H₀) states that there is no significant difference in health scores between girls and boys.
Since we fail to reject H₀, we conclude that the data does not provide sufficient evidence to suggest a
significant difference between the groups.
Step 7: Effect Size (Eta-Squared)
The formula for eta-squared (η²) is:
η² = t² / (t² + df)
Substitute values:
η² = (0.35)² / ((0.35)² + 13)
η² = 0.1225 / (0.1225 + 13)
η² = 0.1225 / 13.1225 ≈ 0.0093
Convert to a percentage:
η² × 100 = 0.93%
This indicates a very small effect size.
Summary of Two-Sample T-Test
Step Value
Sample Means (X̄₁, X̄₂) 24.63, 23.43
Sample Variances (s₁², s₂²) 74.27, 11.61
Pooled Variance (sₚ²) 45.22
Standard Error (SE) 3.48
Observed t-Value (tₒᵦs) 0.35
Critical t-Value (t ᵣᵢ ) ±2.16
Decision Fail to Reject H₀
Conclusion No significant difference
1. Alcohol and Tobacco Consumption
Region Alcohol Tobacco
North 6.47 4.03
Yorkshire 6.13 3.76
Northeast 6.19 3.77
East Midlands 4.89 3.34
West Midlands 5.63 3.47
East Anglia 4.52 2.92
Southeast 5.89 3.20
Southwest 4.79 2.71
Wales 5.27 3.53
Scotland 6.08 4.51
Northern Ireland 4.02 4.56
1.1 Relationship between Alcohol and Tobacco Consumption
To determine the relationship, calculate the correlation coefficient (r). This will quantify the strength and
direction of the relationship.
1.2 Interpret the Correlation Coefficient
● r > 0: Positive correlation (as alcohol consumption increases, tobacco consumption tends to
increase).
● r < 0: Negative correlation (as alcohol consumption increases, tobacco consumption tends to
decrease).
● r = 0: No correlation.
2. Gym Attendance and Satisfaction with Life
Participant Gym Attendance (X) Satisfaction with Life (Y)
1 21 10
2 21 16
3 19 8
4 21 17
5 38 19
6 39 30
7 19 8
8 21 17
9 26 23
10 19 16
2.1 Calculate the Correlation Coefficient (r)
Use the formula:
r = (N Σ(XY) - (ΣX)(ΣY)) / √[(N Σ(X²) - (ΣX)²) (N Σ(Y²) - (ΣY)²)]
2.2 Interpret the Correlation Coefficient
● Direction: Positive (+++) or Negative (---) relationship.
● Size: Use guidelines for r interpretation:
○ Slight/negligible (< 0.20)
○ Low (0.20–0.40)
○ Moderate (0.40–0.70)
○ High (0.70–0.90)
○ Very High (> 0.90)
3. IQ Test Hypothesis
Person IQ
1 110
2 95
3 82
4 120
5 135
6 78
7 140
8 138
Hypothesis Test (α = 0.05):
● Null Hypothesis (H₀): The sample mean does not differ significantly from the population mean (μ =
100).
● Alternative Hypothesis (H₁): The sample mean differs significantly from the population mean (μ ≠
100).
Steps:
1. Calculate the sample mean (X̄).
2. Compute the standard deviation (s).
3. Calculate the t-value using:
t = (X̄ - μ) / (s / √n)
4. Compare tₒᵦs with t ᵣᵢ .
4. Loneliness and Age Correlation
Correlation Coefficient: r = 0.22
Interpretation:
● Direction: Positive correlation (+++). As age increases, loneliness tends to increase slightly.
● Size: Low correlation (definite but small relationship).
5. Lecturer Ratings
Lecturer First-Year Students (X) Final-Year Students (Y)
1 44 58
2 39 47
3 36 18
4 35 22
5 33 31
6 29 38
7 22 38
5.1 Calculate the Correlation Coefficient (r):
Use the same formula as in Question 2.
Interpretation:
● Direction: Positive or negative.
● Strength: Evaluate r based on guidelines for correlation size.
6. Group Comparison: Psychology Test Scores
Group Scores
Group A 23, 26, 35, 14, 19, 17, 30, 15
Group B 15, 17, 2, 6, 29, 12, 40, 17
Hypothesis Test (α = 0.01):
● Null Hypothesis (H₀): There is no significant difference between Group A and Group B.
● Alternative Hypothesis (H₁): There is a significant difference between Group A and Group B.
Steps:
1. Calculate the mean and variance for each group.
2. Compute the pooled variance (sₚ²):
sₚ² = [(n₁ - 1)s₁² + (n₂ - 1)s₂²] / (n₁ + n₂ - 2)
3. Calculate the standard error (SE):
SE = √(sₚ² * [1/n₁ + 1/n₂])
4. Compute tₒᵦs:
tₒᵦs = (X̄₁ - X̄₂) / SE
5. Compare tₒᵦs with t ᵣᵢ .
Type 1 Error (False Positive)
● Incorrectly rejecting a true null hypothesis.
● Concluding that there is an effect or difference when none actually exists.
● Alpha level is set too low and the sample mean incorrectly falls in the critical region.
Type 2 Error (False Negative)
● Failing to reject a false null hypothesis.
● Conclude that there is no effect or difference when one actually exists.
● Occurs when the alpha level is set too high and the sample mean does not fall in the critical region.
Parametric Tests
● Statistical tests.
● Assume the data follows a specific distribution, typically normal.
● Data measured on an interval or ratio scale.
● Assume that the variances of the groups being compared are equal (homogeneity of variance).
● Common parametric tests include the t-test and ANOVA.
Non-Parametric Tests
● Statistical tests.
● Any distribution can be used (“distribution-free” test); do not assume a specific distribution.
● Ordinal and nominal scales used.
● More flexible for data that doesn’t meet the assumptions of normality, when the data is not normally
distributed.
Statistics
Inferential
Descriptive
Measures of
Central Tendency Parametric Tests
Nonparametric Tests
Measures of
Variability
Correlation and T-Tests
Mean, Median, and Mode
Range, Variance, and
Standard deviation