Syllabus

PS2204: Statistical Methods For Psychological Research

Statistics and Psychology: Relevance of Statistics in Psychological Research;

Descriptive Statistics: Graphical representation of data, measures of central

Inferential Statistics: Hypothesis testing; null and alternate hypothesis;

Non-Parametric Statistics: Difference between parametric and non-

Books
➢ Garret, H.E., Woodworth, R.S. Statistics in psychology and education. Bombay:
Vakils Feffer & Simons Ltd (2005).
➢ Mohanty, B. & Misra, S. (2016). Statistics for behavioral and social sciences.
NewDelhi: Sage Publications India.
➢ Mangal, S. K. (2012. Statistics in psychology and education, NewDelhi: PHI.
 MEANING OF STATISTICS
❖ Statistics is a science which provides tools for analysis and
interpretation to be used on raw data collected for the
purpose of decision making in various fields of scientific
inquiry.
❖ It involves four important terms—population, sample,
parameter and statistics.
❖ It deals with the collection, classification and tabulation of
numerical facts as the basis for explanation, description and
comparison of phenomena.
 NATURE OF STATISTICS
❖ Observe, record and enumerate facts relating to a social
phenomenon.
❖ Organise, classify and analyse numerical facts.
❖ Provides the basis for explanation, description and
comparison of different phenomena.
❖ Helps interpretation, prediction and decision-making about
a scientific inquiry.
❖ Facilitates the accomplishment of the ultimate objectives of
scientific enquiry.
 AIMS AND APPLICATIONS OF
STATISTICS AS A SCIENCE
➢ Designing scientific experiments and minimising experimental errors.
➢ Drawing a representative sample and fixing its size.
➢ Summarising or describing the data collected.
➢ Systematic arrangement, mathematical analysis and interpretation of the observed
data.
➢ Comparing individuals or groups of individuals in various ways.
➢ Determining whether certain aspects of behaviour are related.
➢ Predicting future behaviour from current information.
➢ Exploring the cause-and-effect relationships between two or more properties or
events.
➢ Assessing the probability of the results occurring by chance.
➢ Estimating the probability of errors in the inference.
➢ Estimating the reliability and validity of a test and the variations of a property and its
causes in a population.
➢ Application in psychological problems, educational problems, scientific research,
employment surveys, market research, industrial or organisational development, etc.
 CLASSIFICATION OF STATISTICAL
PROCEDURES
➢ Descriptive Statistics
Statistics that summarize the major characteristics of an array
of scores (Baron, 2002).
➢ Sampling or Inferential Statistics
Statistical procedures used in the drawing of inferences about
the properties of populations from sample data.
➢ Prediction Statistics
Statistical procedures used in predicting future behaviour
from current information.
FUNCTIONS (OR USES) OF STATISTICS
➢ Collection of data
➢ Enumeration
➢ Sampling design
➢ Methods of Sampling
➢ Classification of data
➢ Tabulation of data
➢ Measurement
 LIMITATIONS OF STATISTICS
❖Statistics do not study qualitative phenomenon.
❖Statistics do not study individuals.
❖Statistical laws are not exact.
❖Statistics cannot be applied indiscriminately.
❖Statistical relation does not necessarily mean a causal
relationship.
❖Statistics are liable to be misused.
MISUSE (OR ABUSES) OF STATISTICS
Misuse of statistics can involve the use of:
✓Extremely small or biased samples
✓ Unexpected comparisons
✓ Misleading graphs and presentations
 DESCRIPTIVE STATISTICS
• Descriptive statistics deals with how to organize, summarize and simplify the data that
have been observed, gathered and analyzed.
• Descriptive statistics is vital to carry out further data analysis with the help of
inferential statistics. It is mainly used to describe and organize the data.
• Descriptive statistics include:
- Classification
- Tabulation
- Graphical and diagrammatic presentation
- Measures of central tendency- Mean, Median, Mode
- Measures of dispersion- Variance, Standard Deviation
 INFERENTIAL STATISTICS
• It deals with generalizing the results of observation from a sample to the larger population
from which the sample has been drawn.
• Inferential statistics refers to the mathematical methods based on probability theory and helps
in reasoning and inferring the characteristic features of the sample drawn from the larger
population.
• It helps in arriving at a meaningful inference, and testing of hypothesis and points out the
various errors of hypothesis testing.
• Inferential statistics can be used to draw inferences about the population based on the data
collected from its representative sample.
• It not only helps in the generalization of a particular result to the population from which the
sample was drawn but also helps with probabilities.
• It can also be effectively used to make predictions and estimations about population
parameters based on sample statistics.
• Two types of procedures are used in inferential statistics, viz., estimation and hypothesis
testing.
 Estimation/Prediction
• It refers to estimating the probability of a phenomenon. This is accomplished by the
results the researcher obtained from the sample he had drawn from the population.
Since the sample drawn is representative of the population, the results can also be
generalized to the larger population.
• It is more an approximation and thus is bound to have fluctuations and these
fluctuations are due to either:
1. Chance factors: One of the problems faced by researchers is to know if the
inference drawn by them from the data is due to chance or real.
2. Sampling error: This occurs when a selected sample is really not representative
of the population. Sampling error can occur when the selected sample may not
have the salient characteristics of the population to the relevant research.
SCALES OR LEVELS OF MEASUREMENT
❖Nominal/Classificatory
❖Ordinal/Ranking
❖Interval
❖Ratio
 SCALES OF MEASUREMENT
Nominal Scale:
•Variables that can be categorized under nominal scale are
necessarily qualitative and exclusive in nature.
•For example, color of hair, religion, gender, and so on.
•Nominal implies 'name’, the meaning of the term 'nominal' in Latin.
•Numbers can be used under nominal scale by assigning different
numbers to different categories of variables.
•For example, about gender, males can be assigned 1 and females can be assigned 2.
Ordinal Scale:
•When items are classified according to good or bad, more or less, high and
low, and so on, in regard to a characteristic, the scale is termed an ordinal
scale and the categories have an ordered relationship to each other.
•Ordinal scales measure only the degrees of difference, and such scales are
used in the measurement of attitude, opinion, etc.
•The meaning of the term 'ordinal' is 'order' in Latin and thus the categories
can be ranked.
•For example, a student with 1st rank may have obtained 75 marks, the
student with second rank may have obtained 65 marks and a student with
third rank may have obtained 64 marks.
Interval Scale:
• Interval scales have certain similarity to ordinal scale but differs from the latter,
in that the distance between one subject and another will be equal in interval
scale though there is no absolute zero in this scale.
• An example of such scale is the thermometer where there is equal distance
between 98.4 and 99.4 and 99.4 to 100.4 but there is no 'zero' point.
• Interval scales possess some of the properties of ordinal scale, as for instance,
the categories under interval scale are exclusive and they can also be ranked.
• They provide degrees of difference between any two categories and the
difference between any two points on a scale will be equal.
• Most scales used to measure psychological entities fall under interval scale as
there is no absolute zero. For example, there cannot be a zero Intelligence
Quotient (IQ) or attitude.
Ratio Scale:
• This scale possesses all the properties of an interval scale, and in addition, it
has a zero point which differentiates it from the interval scale
• This zero indicates the absence of a particular characteristic or property.
• In this scale, the different points are of equidistant.
• For example, if participants are asked about their age, the difference
between any two given years in age will be the same. Further, 'zero' age
determines absence of age or birth. Thus, a person who is 80 years old is
double the age than 40 years old.
• Ratio scale can be used for quantity of purchase, share figures and so on
• Ratio scale incorporates the properties of all the scales, nominal, ordinal and
interval and hence numerous descriptive calculations can be carried out for
variables that can be measured.
 Properties Of Scales Of Measurement
Scales Properties
Exclusive Arrangement of Distance is True or real
Categories ccategories in an equal between zero
order adjacent
categories

Nominal *
Ordinal * *
Interval * * *
Ratio * * * *
VARIABLES AND THEIR CLASSIFICATION
Any property or characteristic of some event,
object or person that may have different values
at different times depending on the conditions
(Pagano, 1994)
➢Dependent and Independent Variables
➢Continuous and Discrete (Discontinuous)
Variables
• Variables can be classified as discrete or
continuous.
➢Discrete variables (such as class size) consist of
indivisible categories. They can only be in whole
numbers.
➢Continuous variables (such as time or weight) are
infinitely divisible into whatever units a researcher
may choose. For example, time can be measured
to the nearest minute, second, half-second, etc.