IGNOUASSIGNMENTS.

IN
ignouassignments.in

ASSIGNMENT SOLUTIONS GUIDE (2021-22)

MPC-006: STATISTICS IN PSYCHOLOGY

Disclaimer/Special Note: These are just the sample of the Answers/Solutions to some of the Questions
given in the Assignments. These Sample Answers/Solutions are prepared by Private
Teacher/Tutors/Authors for the help and guidance of the student to get an idea of how he/she can
answer the Questions given the Assignments. We do not claim 100% accuracy of these sample
answers as these are based on the knowledge and capability of Private Teacher/Tutor. Sample
answers may be seen as the Guide/Help for the reference to prepare the answers of the Questions
given in the assignment. As these solutions and answers are prepared by the private teacher/tutor so

IN
the chances of error or mistake cannot be denied. Any Omission or Error is highly regretted though
every care has been taken while preparing these Sample Answers/Solutions. Please consult your own

S.
Teacher/Tutor before you prepare a Particular Answer and for up-to-date and exact information, data
and solution. Student should must read and refer the official study material provided by the

76 50 NT
university.

SECTION A
98 80 E
Answer the following question in about 1000 words (wherever applicable) each
82 26 NM
Q1. Describe the meaning of inferential statistics and focus on hypothesis testing.
Ans. Organising and summarising data is only one step in the process of analysing the data. In any
scientific investigation either the entire population or a sample is considered for the study.
In most of the scientific investigations a sample, a small portion of the population under
79 91 IG

41
investigation, is used for the study. On the basis of the information contained in the sample we try to
draw conclusions about the population. This process is known as statistical inference.
98 S

Statistical inference is widely applicable in behavioural sciences, especially in psychology. For

example, before the Lok Sabha or Vidhan Sabha election process starts or just before the declaration of
AS

election results print media and electronic media conduct exit poll to predict the election result. In this
process all voters are not included in the survey, only a portion of voters i.e. sample is included to
infer about the population. This is called inferential statistics. Inferential statistics deals with drawing
U

of conclusions about large group of individuals ( population) on the basis of observation of a few
participants from among them orvabout the events which are yet to occur on the basis of past events.
O

It provides toolsvto compute the probabilities of future behaviour of the subjects. Inferential statistics
is the mathematics and logic of how this generalisation fromvsample to population can be made.
N

There are two types of inferential procedures: (1) Estimation, (2) Hypothesis testing.
IG

Estimation
In estimation, inference is made about the population characteristics on the basis of what is
discovered about the sample. There may be sampling variations because ofvchance fluctuations,
variations in sampling techniques, and other sampling errors.VEstimation about population
characteristics may be influenced by such factors.
Therefore, in estimation the important point is that to what extent our estimate is close to the true
value.
Characteristics of Good Estimator: A good statistical estimator should have the following
characteristics, (i) Unbiased (ii) Consistent (iii) Accuracy . These are beingbdealt with in detail below.
i) Unbiased
An unbiased estimator is one in which, if we were to obtain an infinite number of random samples of
a certain size, the mean of the statistic would be equal to the parameter. The sample mean, ( x ) is an

1
IGNOUASSIGNMENTS.IN
ignouassignments.in

unbiased estimate of population mean (μ) because if we look at possible random samples of size N
from a population, then mean of the sample would be equal to μ. ii) Consistent
A consistent estimator is one that as the sample size increased, the probability that estimate has a
value close to the parameter also increased. Because it is a consistent estimator, a sample mean based
on 20 scores has a greater probability of being closer to (μ) than does a sample mean based upon only
5 scores ii) Accuracy
The sample mean is an unbiased and consistent estimator of population mean (μ). But we should not
over look the fact that an estimate is just a rough or approximate calculation. It is unlikely in any
estimate that ( x ) will be exactly equal to population mean (μ). Whether or not x is a good estimate of
(μ) depends upon the representative ness of sample, the sample size, and the variability of scores in
the ppopulation.
• Point Estimation: We have indicated that x obtained from a sample is an unbiased and
consistent estimator of the population mean (μ). Thus, if an investigator obtains Adjustment

IN
Score from 100 students and wanted to estimate the value of (μ) for the population from
which these scores were selected, researcher would use the value of x as an estimate of
population mean (μ). If the obtained value of x were 45.0 then this value would be used as

S.
estimate of population mean (μ).
This form of estimate of population parameters from sample statistic is called point

76 50 NT
estimation. Point estimation is estimating the value of a parameter as a single point, for
example, population mean (μ) = 45.0 from the value of the statistic x = 45.0
• Interval Estimation: A point estimate of the population mean (μ) almost is assured of being
98 80 E
in error, the estimate from the sample will not equal to the exact value of the parameter. To
gain confidence about the accuracy of this estimate we may also construct an interval of
82 26 NM
scores that is expected to include the value of the population mean. Such intervals are called
confidence interval. A confidence interval is a range of scores that is expected to contain the
value of (μ). The lower and upper scores that determine the interval are called confidence
79 91 IG

41
limits. A level of confidence can be attached to this estimate so that, the researcher can be 95%
or 99% confidence level that encompasses the population mean.
HYPOTHESIS TESTING
98 S

Inferential statistics is closely tied to the logic of hypothesis testing. In hypothesis testing we have a
AS

particular value in mind. We hypothesize that this value characterise the population of observations.
The question is whether that hypothesis is reasonable in the light of the evidence from the sample. In
estimation no particular population value need be stated. Rather, the question is , what is the
population value. For example, Hypothesis testing is one of the important areas of statistical analyses.
U

Sometimes hypothesis testing is referred to as statistical decision-making process. In day-to-day

O

situations we are required to take decisions about the population on the basis of sample information.
Statement of Hypothesis
N

A statistical hypothesis is defined as a statement, which may or may not be true about the population
parameter or about the probability distribution of the parameter that we wish to validate on the basis
IG

of sample information.
Most times, experiments are performed with random samples instead of the entire population and
inferences drawn from the observed results are then generalised over to the entire population.
But before drawing inferences about the population it should be always kept in mind that the
observed results might have come due to chance factor. In order to have an accurate or more precise
inference, the chance factor should be ruled out.
The probability of chance occurrence of the observed results is examined by the null hypothesis (H0).
Null hypothesis is a statement of no differences. The other way to state null hypothesis is that the two
samples came from the same population. Here, we assume that population is normally distributed
and both the groups have equal means and standard deviations.

2
IGNOUASSIGNMENTS.IN
ignouassignments.in

Since the null hypothesis is a testable proposition, there is counter proposition to it known as
alternative hypothesis and denoted by H1. In contrast to null hypothesis, the alternative hypothesis
(H1) proposes that
i) the two samples belong to two different populations,
ii) their means are estimates of two different parametric means of the respective population, and
iii) there is a significant difference between their sample means.
The alternative hypothesis (H1) is not directly tested statistically; rather its acceptance or rejection is
determined by the rejection or retention of the null hypothesis. The probability ‘p’ of the null
hypothesis being correct is assessed by a statistical test. If probability ‘p’ is too low, H0 is rejected and
H1 is accepted. It is inferred that the observed difference is significant. If probability ‘p’ is high, H0 is
accepted and it is inferred that the difference is due to the chance factor and not due to the variable
factor.
Level of Significance

IN
The level of significance (p<.05 ) is that probability of chance occurrence of observed results up to and
below which the probability ‘p’ of the null hypothesis being correct is considered too low and the
results of the experiment are considered significant (p ≤).

S.
On the other hand, if p exceeds , the null hypothesis (H0) cannot be rejected because the probability of
it being correct is considered quite high and in such case, observed results are not considered

76 50 NT
significant (p > ). The selection of level of significance depends on the choice of the researcher.
Generally level of significance is taken to be 5% or 1%, i.e., = .05 or = .01). If null hypothesis is rejected
at .05 level, it means that the results are considered significant so long as the probability ‘p’ of getting
98 80 E
it by mere chance of random sampling works out to be 0.05 or less (p< .05). In other words, the results
are considered significant if out of 100 such trials only 5 or less number of the times the observed
82 26 NM
results may arise from the accidental choice in the particular sample by random sampling.
One-tail and Two-tail Test
Depending upon the statement in alternative hypothesis (H1), either a one-tail or two- tail test is
79 91 IG

41
chosen for knowing the statistical significance. A one-tail test is a directional test. It is formulated to
find the significance of both the magnitude and the direction (algebraic sign) of the observed
difference between two statistics. Thus, in two-tailed tests researcher is interested in testing whether
98 S

one sample mean is significantly higher (alternatively lower) than the other sample mean.
AS

Q2. The scores obtained by three groups of employees on emotional Intelligence scale are given
below. Compute one way ANOVA for the same.
U
O
N
IG

Ans. Analysis of Variance Results

F-statistic value = 4.24621
P-value = 0.02492

3
IGNOUASSIGNMENTS.IN
ignouassignments.in

IN
S.
76 50 NT
98 80 E
82 26 NM
79 91 IG

41
Q3. Elucidate the concept of normal distribution and normal curve (with the help of diagram) and
describe the characteristics of Normal Probability Curve.
Ans. Concept of Normal Distribution
98 S

Carefully look at the following hypothetical frequency distribution, which a teacher has obtained
AS

after examining 150 students of class IX on a Mathematics achievement test.

U
O
N
IG

The concentration of maximum frequencies (f = 30) lies near a central value of distribution and
frequencies gradually tapper off symmetrically on both the sides of this value.

4
IGNOUASSIGNMENTS.IN
ignouassignments.in

Concept of Normal Curve

Now, suppose if we draw a frequency polygone with the help of above distribution, we will have a
curve.

IN
S.
76 50 NT
98 80 E
The shape of the curve is just like a ‘Bell’ and is symmetrical on both the sides.
If you compute the values of Mean, Median and Mode, you will find that these three are
82 26 NM
approximately the same (M = 52; Md = 52 and Mo = 52)
This Bell-shaped curve technically known as Normal Probability Curve or simply Normal Curve and
the corresponding frequency distribution of scores, having just the same values of all three measures
of central tendency (Mean, Median and Mode) is known as Normal Distribution.
79 91 IG

41
Many variables in the physical (e.g. height, weight, temperature etc.) biological (e.g. age, longevity,
blood sugar level and behavioural (e.g. Intelligence; Achievement; Adjustment; Anxiety; Socio-
98 S

Economic-Status etc.) sciences are normally distributed in the nature. This normal curve has a great
significance in mental measurement. Hence to measure such behavioural aspects, the Normal
AS

Probability Curve in simple terms Normal Curve worked as reference curve and the unit of
measurement is described as σ (Sigma).
Theoretical Base of the Normal Probability Curve
U

The normal probability curve is based upon the law of Probability (the various games of chance)
discovered by French Mathematician Abraham Demoiver (1667-1754). In the eighteenth century, he
O

developed its mathematical equation and graphical representation also.

N

The law of probability and the normal curve that illust-rates it are based upon the law of chance or
the probable occurrence of certain events. When anybody of observations conforms to this
IG

mathematical form, it can be represented by a bell shaped curve with definite characteristics.
The characteristics of the normal probability curve are:
1) The Normal Curve is Symmetrical: The normal probability curve is symmetrical around it’s
vertical axis called ordinate. The symmetry about the ordinate at the central point of the curve
implies that the size, shape and slope of the curve on one side of the curve is identical to that
of the other. In other words, the left and right halves to the middle central point are mirror
images, as shown in the figure given here.
2) The Normal Curve is Unimodel: Since there is only one maximum point in the curve, thus
the normal probability curve is unimodel, i.e. it has only one mode.
3) The Maximum Ordinate occurs at the Center: The maximum height of the ordinate always
occur at the central point of the curve, that is the mid-point. In the unit normal curve it is
equal to 0.3989.

5
IGNOUASSIGNMENTS.IN
ignouassignments.in

4) The Normal Curve is Asymptotic to the X Axis: The normal probability curve approaches
the horizontal axis asymptotically; i.e. the curve continues to decrease in height on both ends
away from the middle point (the maximum ordinate point); but it never touches the
horizontal axis. Therefore, its ends extend from minus infinity (- ∞) to plus infinity (+ ∞).
5) The Height of the Curve declines Symmetrically: In the normal probability curve the height
declines symmetrically in either direction from the maximum point.
6) The Points of Influx occur at point ±1 Standard Deviation (± 1 σ): The normal curve changes
its direction from convex to concave at a point recognised as point of influx. If we draw the
perpendiculars from these two points of influx of the curve to the horizontal X axis; touch at a
distance one standard deviation unit from above and below the mean (the central point).
7) The Total Percentage of Area of the Normal Curve within Two Points of Influxation is
fixed: Approximately 68.26% area of the curve lies within the limits of ± 1 standard deviation
(± 1 σ) unit from the mean.

IN
8) The Total Area under Normal Curve may be also considered 100 Percent Probability: The
total area under the normal curve may be considered to approach 100 percent probability;
interpreted in terms of standard deviations.

S.
9) The Normal Curve is Bilateral: The 50% area of the curve lies to the left side of the maximum
central ordinate and 50% of the area lies to the right side. Hence the curve is bilateral.

76 50 NT
10) The Normal Curve is a mathematical model in behavioural Sciences Specially in Mental
Measurement: This curve is used as a measurement scale. The measurement unit of this scale
is ± 1σ (the unit standard deviation).
‘ 98 80 E
Q4. Describe setting up of level of significance with a focus on its steps.
82 26 NM
Ans. Ordinarily, we draw only a single sample from its parent population. However, our problem
becomes one of determining how we can infer or estimate the mean of the population (Mpop) on the
basis of the sample mean (M). Thus, the degree to which a sample mean (M) represents its parameter
79 91 IG

41
is an index of the “Significance” or Trustworthiness of the computed sample mean.
When we draw a sample from the population, the observed statistics or estimate that is the mean of
the sample obtained, may be some time large or small to the mean of the population (Mpop). The
98 S

difference may have arisen “by chance” due to the differences in the composition of our sample, or
AS

due to its selection method or the procedure followed in the sample selection. The gap between the
two measures sample mean (M) and population mean (Mpop), if is low and negligible the sample
mean is considered to be trustworthy and we can forecast or estimate the population mean (Mpop)
successfully.
U

Therefore, a sample mean (M) is statistically trustworthy or significant to forecast the mean of the
O

population (Mpop), depending upon the probability that the difference between the two measures i.e.
Mpop and M could have been arisen “by chance”.
N

And the confidence level to which this forecast has been made is known as level of confidence or level
of significance.
IG

In simpler terms, the level of significance or level of confidence is a degree to which we accept or
reject or predict a happening or incidence with confidence.
There are a number of levels of confidence or levels of significance e.g. 100%, 99%, 95%, 90% ..........
50% etc. In psychology and other behavioural sciences, generally, we consider only two levels of
significance viz. the 99% level of significance or level of confidence and 95% level of significance a
level of confidence.
The amount 99% and 95% confidence is also termed as 0.01 and 0.05 level of confidence. The 0.01 level
means, if we repeatedly draw a sample or conduct an experiment 100 times, only on one occasion, the
obtained sample mean or results will fallout side the limits Mpop ± 2.58 S.E.
Here the term S.E. means the standard error exists in the estimate or sample statistics.
Similarly, 0.05 level means, if repeatedly draw a sample or conduct an experiment 100 times, only on
five occasions the obtained sample mean will fall outside the limits Mpop ± 1.96 S.E.

6
IGNOUASSIGNMENTS.IN
ignouassignments.in

The value 1.96 and 2.58 have been taken from the ‘t’ distribution or ‘t’ table (P...). Keeping large size
sample in view.
The 0.01 level is more rigorous and higher in terms of standard, as compared to the 0.05 level and
would require a high level of accuracy and precision. Hence, if an obtained value (on the basis of a
sample or an experiment) is significant at 0.01 level, it is automatically significant at 0.05 level but the
reverse is not always true.

Q5. Compute Spearman’s rho for the following data:

IN
S.
76 50 NT
98 80 E
82 26 NM
79 91 IG

41
98 S
AS
U
O
N
IG

7
IGNOUASSIGNMENTS.IN
ignouassignments.in

IN
S.
76 50 NT
98 80 E
82 26 NM
79 91 IG

41
98 S
AS
U
O
N

Q6. Elucidate the steps involved in drawing a scatter diagram.

IG

Ans. Step 1. Plotting the Axes

Draw the x and y axis on the graph and plot one variable on x-axis and another on y-axis.
(Although, correlation analyses do not restrict you from plotting any variable on any axis, plot the
causal variable on x-axis in case of implicitly assumed cause-effect relationship.)
Also note that correlation does not necessarily imply causality.
Step 2. Range of Values
Decide the range of values depending on your data.
Begin from higher or lower value than zero.
Conventionally, the scatterplot is square.
So, plot x and y values about the same length.
Step 3. Identify the pairs of values
Identify the pairs of values.
A pair of value is obtained from a data.

8
IGNOUASSIGNMENTS.IN
ignouassignments.in

A pair of values is created by taking a one value on first variable and corresponding value on second
variable.
Step 4. Plotting the graph
Now, locate these pairs in the graph.
Find an intersection point of x and y in the graph for each pair.
Mark it by a clear dot (or any symbol you like for example, star).
Then take second pair and so on.
The scatterplot shown below is based on the data given in table 1. (Refer to Figure 1).

IN
S.
76 50 NT
98 80 E
The graph shown above is scatterplot representing the relationship between intelligence and the
scores on reasoning task. We have plotted intelligence on x-axis because it is a cause of the
82 26 NM
performance on the reasoning task. The scores on reasoning have started from 100 instead of zero
simply because the smallest score on intelligence is 104 which is far away from zero. We have also
started the range of reasoning scores from 10 since the lowest score on reasoning is 12. Then we have
79 91 IG

41
plotted the pair of scores. For example, subject A has score of 104 on intelligence and 12 on reasoning
so we get x,y pair of 104,12. We have plotted this pair on the point of intersection between these two
scores in the graph by a dot. This is the lowest dot at the left side of the graph. You can try to practice
98 S

the scatter by using the data given in the practice.

AS

Q7. With the help of Mann Whitney U test find if significant difference exists between the scores
obtained on perceived parental behaviour obtained by male and female adolescents.
U
O
N
IG

Ans.

Result Details

9
IGNOUASSIGNMENTS.IN
ignouassignments.in

Sample 1
Sum of ranks: 84
Mean of ranks: 9.33
Expected sum of ranks: 90
Expected mean of ranks: 10
U-value: 51
Expected U-value: 45
Sample 2
Sum of ranks: 106
Mean of ranks: 10.6
Expected sum of ranks: 100
Expected mean of ranks: 10
U-value: 39

IN
Expected U-value: 45
Sample 1 & 2 Combined
Sum of ranks: 190

S.
Mean of ranks: 10
Standard Deviation: 12.2474

76 50 NT
Result 1 - U-value
The U-value is 39. The critical value of U at p < .05 is 20. Therefore, the result is not significant at p <
.05.
Result 2 - Z-ratio 98 80 E
The Z-Score is 0.44907. The p-value is .65272. The result is not significant at p < .05.
82 26 NM
Q8. Compute Chi-square for the following data:
79 91 IG

41
98 S
AS
U

Ans. The formula for chi-square (X2 ) is:

(X2) = ∑[(fo-fe)2/fe]
O

In which
N

Fo = frequency of occurrence of observed or experimentally determined facts.

Fe = expected frequency of occurrence.
IG

Chi-square Value: 1.2

Degrees of Freedom: 2
P value: 0.548811636094

SECTION C
Answer the following in about 50 words each
Q9. Frequency distribution
Ans. The arrangement of data in groups according to similarities is known as classification. A
classification is a summary of the frequency of individual scores or ranges of scores for a variable. In
the simplest form of a distribution, we will have such value of variable as well as the number of
persons who have had each value.

10
IGNOUASSIGNMENTS.IN
ignouassignments.in

Once data are collected, it should be arranged in a format from which they would be able to draw
some conclusions. Thus by classifying data, the investigators move a step ahead in regard to making a
decision.’
A much clear picture of the information of score emerges when the raw data are organised as a
frequency distribution. Frequency distribution shows the number of cases following within a given
class interval or range of scores. A frequency distribution is a table that shows each score as obtained
by a group of individuals and how frequently each score occurred.
Frequency Distribution can be with Ungrouped Data and Grouped Data
i) An ungrouped frequency distribution may be constructed by listing all score values
either from highest to lowest or lowest to highest and placing a tally mark (/) besides each
scores every times it occurs. The frequency of occurrence of each score is denoted by ‘f’.
ii) Grouped frequency distribution: If there is a wide range of score value in the data, then it
is difficult to get a clear picture of such series of data. In this case grouped frequency

IN
distribution should be constructed to have a clear picture of the data. A group frequency
distribution is a table that organises data into classes.
It shows the number of observations from the data set that fall into each of the class.

S.
Construction of frequency distribution
To prepare a frequency distribution it is essential to determine the following:

76 50 NT
1) The range of the given data =, the difference between the highest and lowest scores.
2) The number of class intervals = There is no hard and fast rules regarding the number of
classes into which data should be grouped. If there are very few scores it is useless to have a
98 80 E
large number of class-intervals. Ordinarily, the number of classes should be between 5 to 30.
3) Limits of each class interval = Another factor used in determining the number of classes is the
82 26 NM
size/ width or range of the class which is known as ‘class interval’ and is denoted by ‘i’.
Class interval should be of uniform width resulting in the same-size classes of frequency distribution.
The width of the class should be a whole number and conveniently divisible by 2, 3, 5, 10, or 20.
79 91 IG

41
Q10. Measures of central tendency
Ans. It is the middle point of a distribution. Tabulated data provides the data in a systematic order
98 S

and enhances their understanding. Generally, in any distribution values of the variables tend to
AS

cluster around a central value of the distribution. This tendency of the distribution is known as
central tendency and measures devised to consider this tendency is know as measures of central
tendency. A measure of central tendency is useful if it represents accurately the distribution of scores
on which it is based. A good measure of central tendency must possess the following characteristics:
U

It should be clearly defined- The definition of a measure of central tendency should be clear and
O

unambiguous so that it leads to one and only one information.

It should be readily comprehensible and easy to compute.
N

It should be based on all observations- A good measure of central tendency should be based on all the
values of the distribution of scores.
IG

It should be amenable for further mathematical treatment.

It should be least affected by the fluctuation of sampling.
In Statistics there are three most commonly used measures of central tendency.
These are:
• Arithmetic Mean: The arithmetic mean is most popular and widely used measure of central
tendency. Whenever we refer to the average of data, it means we are talking about its
arithmetic mean. This is obtained by dividing the sum of the values of the variable by the
number of values. It is also a useful measure for further statistics and comparisons among
different data sets. One of the major limitations of arithmetic mean is that it cannot be
computed for open-ended class-intervals.
• Median: Median is the middle most value in a data distribution. It divides the distribution
into two equal parts so that exactly one half of the observations is below and one half is above

11
IGNOUASSIGNMENTS.IN
ignouassignments.in

that point. Since median clearly denotes the position of an observation in an array, it is also
called a position average. Thus, more technically, median of an array of numbers arranged in
order of their magnitude is either the middle value or the arithmetic mean of the two middle
values. It is not affected by extreme values in the distribution.
• Mode: Mode is the value in a distribution that corresponds to the maximum concentration of
frequencies. It may be regarded as the most typical of a series value. In more simple words,
mode is the point in the distribution comprising maximum frequencies therein.

Q11. Phi coefficient

Ans. The Pearson’s correlation between one dichotomous variable and another continuous variable is
called as point-biserial correlation. When both the variables are dichotomous, then the Pearson’s
correlation calculated is called as Phi Coefficient (φ ).
For example, let us say that you have to compute correlation between gender and ownership of the

IN
property. The gender takes two levels, male and female. The ownership of property can be measured
as either the person owns a property and the person do not own property. Now you have both the
variables measured as dichotomous variables. Now if you compute the Pearson’s correlation between

S.
these two variables is called as Phi Coefficient (φ ). Both the variables take value of either of 0 or one.

76 50 NT
98 80 E
82 26 NM
79 91 IG

41
98 S
AS

The value of φ coefficient is found to be – .465.

The relationship is negative, is function of the way we have assigned the number 0 and 1 to each of
U

the variable. If we assign 0 to females and 1 to males, then we will get the same value of correlation
O

with positive sign. Nevertheless, this does not mean that sign of the relationship cannot be
interpreted. Once these numbers have been assigned, then we can interpret the sign. Male is 0 and
N

female is 1; whereas 0 = no ownership and 1 is ownership.

The negative relation can be interpreted as follows: as we move from male to female we move
IG

negatively from no ownership to ownership. Meaning that male have more ownership than females.
We can also calculate the proportion of variance shared by these two variables.
That is r2 = φ2 = – .4652 = 0.216 percent.

Q12. Partial correlation

Ans. Two variables, A and B, are closely related. The correlation between them is partialled out, or
controlled for the influence of one or more variables is called as partial correlation. So when it is
assumed that some other variable is influencing the correlation between A and B, then the influence
of this variable(s) is partialled out for both A and B. Hence it can be considered as a correlation
between two sets of residuals. Here we discuss a simple case of correlation between A and B is
partialled out for C. This can be represented as AB C. r which is read as correlation between A and B
partialled out for C. the correlation between A and B can be partialled out for more variables as well.

12
IGNOUASSIGNMENTS.IN
ignouassignments.in

For example, the researcher is interested in computing the correlation between anxiety and academic
achievement controlled from intelligence. Then correlation between academic achievement (A) and
anxiety (B) will be controlled for Intelligence (C). This can be represented as: Academic
Achievement(A) Anxiety (B) . Intelligence (C) r . To calculate the partial correlation (rP ) we will need
a data on all three variables. The computational formula is as follows:

Q13. Adjusted r
Ans. The Pearson’s correlation coefficient (r) calculated on the sample is not an unbiased estimate of
population coefficient (ñ). When the number of observations (sample size) are small the sample

IN
correlation is a biased estimate of population correlation. In order to reduce this bias, the calculated
correlation coefficient is adjusted. This is called as adjusted correlation coefficient (radj).

S.
76 50 NT
98 80 E
82 26 NM
79 91 IG

41
98 S
AS
U
O
N

Q14. Nonparametric statistics

IG

Ans. Non-parametric statistics covers techniques that do not rely on data belonging to any particular
distribution. These include (i) distribution free methods (ii) nonstructural models. Distribution free
means its interpretation does not depend on any parametrized distributions. It deals with statistics
based on the ranks of observations and not necessarily on scores obtained by interval or ratio scales.
Non-parametric statistics is defined to be a function on a sample that has no dependency on a
parameter. The interpretation does not depend on the population fitting any parametrized
distributions. Statistics based on the ranks of observations are one example of such statistics and these
play a central role in many non-parametric approaches.
Non-parametric techniques do not assume that the structure of a model is fixed. Typically, the model
grows in size to accommodate the complexity of the data. In these techniques, individual variables are
typically assumed to belong to parametric distributions, and assumptions about the types of
connections among variables are also made.

13
IGNOUASSIGNMENTS.IN
ignouassignments.in

Non-parametric methods are widely used for studying populations that are based on rank order
(such as movie reviews receiving one to four stars). The use of non-parametric methods may be
necessary when data have a ranking but no clear numerical interpretation. For instance when we try
to assess preferences of the individuals, (e.g. I prefer Red more than White colour etc.), we use non
parametic methods. Also, when our data is based on measurement by ordinal scale, we use non-
parametric statistics.
As non-parametric methods make fewer assumptions, their applicability is much wider than those of
parametric methods. Another justification for the use of non-parametric methods is its simplicity. In
certain cases, even when the use of parametric methods is justified, non-parametric methods may be
easier to use. Due to the simplicity and greater robustness, non-parametric methods are seen by some
statisticians as leaving less room for improper use and misunderstanding.
A statistic refers to the characteristics of a sample, such as the average score known as the mean. A
parameter, on the other hand, refers to the characteristic of a population such as the average of a

IN
whole population. A statistic can be employed for either descriptive or inferential purposes and one
can use either of the two types of statistical tests, viz., parametric Tests and non-parametric Tests
(assumption free test).

S.
The distinction employed between parametric and non-parametric test is primarily based on the level
of measurement represented by the data that are being analysed. As a general rule, inferential

76 50 NT
statistical tests that evaluate categorical / nominal data and ordinal rank order data are categorized as
non-parametric tests, while those tests that evaluate interval data or ratio data are categorized as
parametric tests.
98 80 E
Q15. Interval and ratio scales of measurement
82 26 NM
Ans. In statistics, there are four data measurement scales: nominal, ordinal, interval and ratio. These
are simply ways to sub-categorize different types of data. This topic is usually discussed in the
context of academic teaching and less often in the “real world.” If you are brushing up on this
79 91 IG

with these terms.

Interval
41
concept for a statistics test, thank a psychologist researcher named Stanley Stevens for coming up
98 S

Interval scales are numeric scales in which we know both the order and the exact differences between
AS

the values. The classic example of an interval scale is Celsius temperature because the difference
between each value is the same. For example, the difference between 60 and 50 degrees is a
measurable 10 degrees, as is the difference between 80 and 70 degrees.
Interval scales are nice because the realm of statistical analysis on these data sets opens up. For
U

example, central tendency can be measured by mode, median, or mean; standard deviation can also be
O

calculated.
Like the others, you can remember the key points of an “interval scale” pretty easily. “Interval” itself
N

means “space in between,” which is the important thing to remember–interval scales not only tell us
about order, but also about the value between each item.
IG

Here’s the problem with interval scales: they don’t have a “true zero.” For example, there is no such
thing as “no temperature,” at least not with celsius. In the case of interval scales, zero doesn’t mean
the absence of value, but is actually another number used on the scale, like 0 degrees
celsius. Negative numbers also have meaning. Without a true zero, it is impossible to compute
ratios. With interval data, we can add and subtract, but cannot multiply or divide.
Confused? Ok, consider this: 10 degrees C + 10 degrees C = 20 degrees C. No problem there. 20
degrees C is not twice as hot as 10 degrees C, however, because there is no such thing as “no
temperature” when it comes to the Celsius scale. When converted to Fahrenheit, it’s clear: 10C=50F
and 20C=68F, which is clearly not twice as hot. I hope that makes sense. Bottom line, interval scales
are great, but we cannot calculate ratios, which brings us to our last measurement scale…
Ratio

14
IGNOUASSIGNMENTS.IN
ignouassignments.in

Ratio scales are the ultimate nirvana when it comes to data measurement scales because they tell us
about the order, they tell us the exact value between units, AND they also have an absolute zero–
which allows for a wide range of both descriptive and inferential statistics to be applied. At the risk
of repeating myself, everything above about interval data applies to ratio scales, plus ratio scales have
a clear definition of zero. Good examples of ratio variables include height, weight, and duration.
Ratio scales provide a wealth of possibilities when it comes to statistical analysis. These variables can
be meaningfully added, subtracted, multiplied, divided (ratios). Central tendency can be measured by
mode, median, or mean; measures of dispersion, such as standard deviation and coefficient of
variation can also be calculated from ratio scales.

Q16. Measuring skewness

Ans. There are two methods to study the skewness in a distribution.
i) Observation Method: There is a simple method of detecting the directions of skewness

IN
by the inspection of frequency polygon prepared on the basis of the scores obtained
regarding a trait of the population or a sample drawn from a population.
Looking at the tails of the frequency polygon of the distribution obtained, if longer tail of

S.
the curve is towards the higher value or upper side or right side to the centre or mean,
the skewness is positive. If the longer tail is towards the lower values or lower side or left

76 50 NT
to the mean, the skewness is negative.
ii) Statistical Method: To know the skewness in the distribution we may also use the
statistical method. For the purpose we use measures of central tendency, specifically
98 80 E
mean and median values and use the following formula.
82 26 NM
Another measure of skewness based on percentile values is as under
79 91 IG

41
98 S

Here, it is to be kept in mind that the above two measures are not mathematically
AS

equivalent. A normal curve has the value of SK = 0. Deviations from normality can be
negative and positively direction leading to negatively skewed and positively skewed
distributions respectively.
U

Q17. Standard error

O

Ans. It has been established that the variability of the sample medians is about 25 per cent greater
than the variability of means in a normally distributed population. Hence the standard error of a
N

median can be estimated by using the formulas:

IG

Q18. Two-way ANOVA

Ans. The two-way ANOVA compares the mean differences between groups that have been split on
two independent variables (called factors). The primary purpose of a two-way ANOVA is to

15
IGNOUASSIGNMENTS.IN
ignouassignments.in

understand if there is an interaction between the two independent variables on the dependent
variable. For example, you could use a two-way ANOVA to understand whether there is an
interaction between gender and educational level on test anxiety amongst university students, where
gender (males/females) and education level (undergraduate/postgraduate) are your independent
variables, and test anxiety is your dependent variable. Alternately, you may want to determine
whether there is an interaction between physical activity level and gender on blood cholesterol
concentration in children, where physical activity (low/moderate/high) and gender (male/female) are
your independent variables, and cholesterol concentration is your dependent variable.
The interaction term in a two-way ANOVA informs you whether the effect of one of your
independent variables on the dependent variable is the same for all values of your other independent
variable (and vice versa). For example, is the effect of gender (male/female) on test anxiety influenced
by educational level (undergraduate/postgraduate)? Additionally, if a statistically significant
interaction is found, you need to determine whether there are any "simple main effects", and if there

IN
are, what these effects are (we discuss this later in our guide).
In this "quick start" guide, we show you how to carry out a two-way ANOVA using SPSS Statistics, as
well as interpret and report the results from this test. However, before we introduce you to this

S.
procedure, you need to understand the different assumptions that your data must meet in order for a
two-way ANOVA to give you a valid result.

76 50 NT
98 80 E
82 26 NM
79 91 IG

41
98 S
AS
U
O
N
IG

16