Statistics Notes for Dissertation Preparation
WHAT IS MEAN
The mean is the arithmetic average of a set of scores. It is obtained by adding all the
scores together and dividing the total by the number of scores. The mean is one of
the most commonly used measures of central tendency in statistics.
The mean helps researchers understand the general performance or average level of
a group. However, it is sensitive to extreme scores or outliers. A very high or very
low score can affect the mean significantly.
WHAT IS MEDIAN
The median is the middle score in a distribution when all scores are arranged in
ascending or descending order. It divides the data into two equal halves.
The median is useful when the data contain extreme scores or are not normally
distributed. Unlike the mean, the median is not greatly affected by outliers and
therefore often represents the center of skewed data more accurately.
STANDARD DEVIATION (SD)
Standard Deviation is a measure of dispersion that shows how much the scores
deviate from the mean. It indicates the spread or variability of data in a distribution.
A low SD indicates that scores are close to the mean, while a high SD indicates
greater variability among scores. SD is important in psychological research because
it helps describe consistency and variation in participant responses.
STANDARD ERROR OF MEAN (SEM)
The Standard Error of Mean refers to the standard deviation of the sampling
distribution of the mean. It indicates how accurately the sample mean represents
the population mean.
A smaller SEM suggests that the sample mean is a more accurate estimate of the
population mean. SEM decreases as sample size increases and is commonly used in
inferential statistics and confidence intervals.
KURTOSIS
Kurtosis refers to the degree of peakedness or flatness of a distribution compared to
a normal distribution. It helps describe the shape of the data distribution.
A high kurtosis value indicates a sharply peaked distribution with more extreme
scores, while low kurtosis indicates a flatter distribution with fewer extreme values.
Kurtosis is used to examine normality before applying statistical tests.
SKEWNESS
Skewness refers to the asymmetry of a distribution. It indicates whether scores are
distributed evenly around the mean or shifted more toward one side.
Positive skewness occurs when the tail extends toward the right side, while negative
skewness occurs when the tail extends toward the left side. A skewness value close
to zero indicates a symmetrical or normal distribution.
NORMAL PROBABILITY CURVE (NPC)
The Normal Probability Curve is a symmetrical, bell-shaped curve in which most
scores cluster around the mean and fewer scores occur toward the extremes. In a
perfectly normal distribution, the mean, median, and mode are equal and located at
the center of the curve.
The Normal Probability Curve is important because many statistical tests assume
that data are normally distributed. Approximately 68% of scores fall within ±1
standard deviation, 95% within ±2 standard deviations, and 99.7% within ±3
standard deviations from the mean. Normal distribution helps researchers apply
parametric statistical tests accurately.
RELIABILITY
Reliability refers to the consistency, stability, and dependability of a measuring
instrument. A reliable test produces similar results when administered repeatedly
under similar conditions. If a psychological test gives inconsistent results, it cannot
be considered scientifically useful.
Important types of reliability include:
- Test-retest reliability
- Split-half reliability
- Internal consistency reliability
- Inter-rater reliability
Reliability is important because inconsistent measurement reduces the accuracy
and trustworthiness of research findings.
VALIDITY
Validity refers to the extent to which a test measures what it is intended to measure.
A valid test accurately assesses the construct or behaviour it claims to measure.
Important types of validity include:
- Face validity
- Content validity
- Construct validity
- Criterion validity
A test may be reliable without being valid, but a valid test is generally expected to be
reliable as well.
NORMALITY
Normality refers to the extent to which data follow a normal distribution or bell-
shaped curve. Many parametric statistical tests assume that the data are
approximately normal.
Normality is commonly assessed using skewness, kurtosis, histograms, Q-Q plots,
and statistical tests such as the Shapiro-Wilk test or Kolmogorov-Smirnov test.
HOMOGENEITY
Homogeneity, also called homogeneity of variance, refers to the equality of
variances among groups being compared in a study. It means that the spread of
scores should be approximately similar across groups.
Homogeneity is an important assumption for parametric tests such as ANOVA and
independent sample t-tests. It is commonly tested using Levene’s Test.
HYPOTHESIS
A hypothesis is a tentative statement or prediction about the relationship between
variables. It is formulated before conducting research and is tested statistically
using collected data.
The Null Hypothesis (H₀) states that there is no significant relationship or difference
between variables. The Direct or Alternative Hypothesis (H₁) states that a
significant relationship or difference exists.
VARIABLE
A variable is any characteristic, trait, or condition that can change or take different
values among individuals or situations.
The two most important variables are the Independent Variable (IV) and Dependent
Variable (DV). The independent variable influences change, while the dependent
variable is the outcome being measured.
T-TEST
A t-test is a parametric statistical test used to determine whether there is a
significant difference between the means of two groups.
The significance of the result is determined using the probability value (p-value). If
the p-value is less than .05, the difference is generally considered statistically
significant.
USES OF T-TEST
The t-test is used when researchers want to compare two groups or two conditions.
Examples include:
- Comparing anxiety levels between males and females
- Comparing pre-test and post-test scores
- Comparing treatment and control groups
CORRELATION
Correlation is a statistical technique used to determine the degree and direction of
relationship between two variables.
A positive correlation indicates that both variables increase together, while a
negative correlation indicates that one variable increases as the other decreases.
TYPES OF CORRELATION
The three main types of correlation are:
- Positive correlation
- Negative correlation
- Zero correlation
Correlation may also be weak, moderate, or strong depending on the correlation
coefficient.
SPEARMAN CORRELATION
Spearman Rank-Order Correlation is a non-parametric statistical technique used to
measure the relationship between ranked or ordinal variables.
It is used when data are ordinal, non-normal, ranked, or contain outliers.
PEARSON CORRELATION
Pearson Product-Moment Correlation is a parametric statistical technique used to
measure the degree and direction of linear relationship between two continuous
variables.
It is used when data are continuous, normally distributed, and meet parametric
assumptions.
WHEN SPEARMAN AND PEARSON ARE USED
Pearson correlation is used for continuous and normally distributed data.
Spearman correlation is used for ordinal, ranked, skewed, or non-normal data.
OUTLIERS
Outliers are extreme scores or observations that differ greatly from the rest of the
data.
Outliers can strongly affect statistical results such as the mean, standard deviation,
correlation, and regression.
DATA TRANSFORMATION
Data transformation refers to the mathematical modification of data to improve
normality, reduce skewness, or satisfy statistical assumptions.
Common transformations include logarithmic transformation, square root
transformation, and inverse transformation.
LEVELS OF MEASUREMENT
Levels of measurement refer to the classification of variables based on their
characteristics.
The four main levels are:
- Nominal
- Ordinal
- Interval
- Ratio
EXPLORATORY ANALYSIS
Exploratory analysis refers to statistical procedures used to discover patterns or
underlying structures in data without starting with a fixed theoretical model.
Exploratory Factor Analysis (EFA) is commonly used during early stages of test
construction and scale development.
CONFIRMATORY ANALYSIS
Confirmatory analysis refers to statistical procedures used to test whether collected
data fit a previously established theory or model.
Confirmatory Factor Analysis (CFA) is commonly used in scale validation and
psychometric research.
MISSING DATA
Missing data refers to the absence of responses or values for certain variables in a
dataset.
Researchers may handle missing data by deleting incomplete cases, replacing
missing values, or using statistical estimation techniques.
ANOVA
ANOVA, or Analysis of Variance, is a parametric statistical technique used to
determine whether there are significant differences between the means of groups.
ANOVA compares variance between groups with variance within groups using the
F-ratio.
ONE-WAY ANOVA
One-Way ANOVA is used when there is one independent variable with three or more
groups or levels.
It examines whether group means differ significantly on a dependent variable.
TWO-WAY ANOVA
Two-Way ANOVA is used when there are two independent variables.
It examines both the individual effects and interaction effects of variables on a
dependent variable.
THREE-WAY ANOVA
Three-Way ANOVA is used when a study contains three independent variables.
It examines the main effects and interaction effects among multiple variables.
USES OF ANOVA
ANOVA is widely used to compare group means and identify significant differences
among groups.
It is commonly used in psychology, education, medicine, and social science research.
REGRESSION
Regression is a statistical technique used to examine relationships between
variables and predict the value of a dependent variable based on one or more
independent variables.
Regression is commonly used for prediction, forecasting, and identifying important
predictors in research.