NORMAL DISTRIBUTION

Q) Define the normal distribution.

A) Normal distribution is a limiting form of the binomial distribution when the number of trails n is
very large and neither p nor q is very small.
Q) Define the normal probability distribution.
A) The normal probability distribution with mean µ and standard deviation σ is given by
𝑥−µ
1 −1/2( )2
f(x) = √2𝜋σ 𝑒 σ

Q) Define normal frequency distribution.

A) If the normal distribution is multiplied by N, it is called normal frequency distribution.
Q) What is standard normal distribution?
A) If the random variable has a normal distribution with mean and variance then the random
𝑋−𝜇
variable z = 𝜎 has a standard normal distribution with mean 0 and variance 1.
Q) How many parameters of normal distribution?
A) There are 2 parameters of normal distribution.
μ, σ2
Q) What is the shape of normal distribution?
A) Normal distribution is bell shaped distribution.
Q) Write down the properties of normal distribution.
A) 1) The normal probability distribution is a continuous distribution that ranges from -ꚙ to
+ꚙ
2) The total area under the curve of normal distribution is equal to one.
3) The normal curve is unimodel.
4) The normal distribution is symmetrical distribution.
Q) Define asymptotic curve.
A) The normal curve gets closer and closer to the X-axis but never touches it, hence it is called
asymptotic curve.
Q) Define reproductive property of normal distribution.
A) If X1 ~N1 (μ1, sd1) and X2~N2(μ2, sd2) has a reproductive property then their sum X1
+X2~N(μ1+μ2, sd1+sd2)
Q) Define normal curve.
A) The graph of normal probability density function is called a normal curve.
Q) Define probability density function.
A) A continuous random variable X is normally distributed If and only if its probability density
function is
𝜇
1 −1/2(𝑥− )2
F(x) = 𝑒 𝜎 for -ꚙ to +ꚙ
𝜎√2𝛱
Q) What are the relationships between mean, median and mode in normal distribution?
A) In normal distribution mean, median and mode are equal
Q) What is the importance of normal distribution?
A) The normal distribution plays an important role in both theoretical as well as in applied
statistics. A number of natural phenomena such as weights, heights etc follow the normal
distribution. It is the foundation of statistical inference.
Q) Define standard normal distribution.
A) if the random variable X has a normal distribution with mean µ and variance σ2 then the random
𝑥−µ
variable 𝑍 = 𝜎 has a standard normal distribution with mean 0 and variance 1
 SAMPLING
Q) Define population.
A) A collection of individuals or objects having some common measureable characteristics is called
population.
Q) Define sample.
A) The selected part of the population is called sample.
Q) Distinguish between target and sampled population.
A) The population about which we want to apply final conclusions of a study is called a target
population.
Sampled population is one from which a sample is actually selected.
Q) What do you mean by sampling?
A) Technique of selecting a true sample from the population to know the characteristics of the
population is called sampling.
Q) Define sample survey and census.
A) The collection of information from a part of the population is called sample survey.
The collection of information from all elements in a population is called taking a census.
Q) Define sampling units.
A) The objects constituting the population are called sampling units.
Q) Distinguish between finite and infinite populations.
A) A population is said to be finite if it consists of a finite or fixed number of elements.
A population is said to be infinite if there is no limit to the number of elements it can contain.
Q) What is the purpose of sampling?
A) The two basics purposes of sampling are (i) to provide sufficient information about the
characteristics of a population, (ii) to find the reliability of the estimates derived from the sample.
Q) What are the advantages of sampling?
A) Following are the main advantages of sampling:
1) Time saving 2) Economic 3) Accuracy 4) Feasibility
Q) What are the limitation of sampling?
A) If the basic facts of each and every unit in the population are needed census become
indispensable. The sample will not meet such a requirement.
Q) Define sampling design.
A) A sampling design is a procedure or plan used to choose the sample from the population.
Q) Define sampling frame.
A) A sampling frame is a complete list of the sampling units.
Q) What do you mean by simple random sampling?
A) It is a procedure of sample selection that allows each elements of the population an equal
chances of being included in the sample, and each possible sample of same size an equal chance
of being selected.
Q) What do you mean by stratified random sampling?
A) It is a probability sampling method in which the population is divided into non-overlapping
groups such that the units within groups are homogenous with respect to some characteristic of
interest, a simple random sample is taken from each group and overall sample is obtained by
combining the sample for all groups.
Q) What do you mean by systematic sampling?
A) Systematic sampling is a procedure in which sample is obtained by selecting one unit at random
from the first k units and thereafter choosing every kth unit.
Q) What do you mean by sampling with replacement?
A) Sampling is said to be with replacement when a sampling unit is drawn, observed, and then
returned to the population before another unit is drawn.
Q) What do you mean by sampling without replacement?
A) Sampling is said to be with replacement when a sampling unit is selected, observed, and not
returned to the population before another unit is drawn.
Q) Define parameter and statistic.
A) A numerical value calculated from the population is called a parameter.
A numerical value calculated from the sample is called a statistic.
Q) Define sampling error.
A) The difference between statistic and the population parameter. E=t – Ɵ
Q) Define non-sampling error.
A) The errors that occur in the collection, recording, and tabulation of the data are called non-
sampling errors.
Q) Distinguish between probability and non-probability sampling.
A) A probability sampling is a process in which the sample is selected in such a way that every
element of a population has a known non-zero probability of being included in the sample.
A non-probability sampling is a procedure in which sample is drawn from the population in such
a way that the probability for including any particular member in the sample is not known.
Q) Define standard error.
A) The standard deviation of the sampling distribution of a statistic is called the standard error of
the statistics.
 ESTIMATION
Q) What is meant by statistical inference?
A) Statistical inference is the art of drawing conclusions about the population from the limited
information contained in the sample.
Q) Define estimation.
A) The procedure of making judgment about a population parameter from a sample statistics is
known as estimation.
Q) What is meant by point estimation?
A) The object of point estimation is to obtain a single number from the sample which will represent
the unknown value of the population parameter.
Q) Define point estimate.
A) An estimate for unknown population parameter expressed by a single value is called a point
estimate.
Q) Define point estimator.
A) A point estimator of the population parameter is a rule or formula that produces a single value
that can be used as an estimate of the unknown population parameter.
Q) What is interval estimation?
A) A range of values used to estimate a population parameter is known as interval estimation.
Q) Define estimator.
A) An estimator is a rule, usually expressed as a formula, used in estimating an unknown
population parameter. For example, sample mean is employed to estimate the population
mean.
Q) Define estimate.
A) An estimate is a specific value derived from the estimator. For example, sample mean is
employed to estimate the population mean.
Q) Define biased estimator.
A) The estimator is said to be biased estimator if the mean of its sampling distribution is not equal
to the parameter being estimated.
Q) What do you mean by unbiased estimator?
A) An estimator θ is said to be unbiased estimator of the parameter θ if the mean of the sampling
distribution of θ is θ.
Q) Define level of confidence.
A) The probability that a confidence interval will contain the unknown parameter is called level of
confidence or confidence coefficient.
Q) What is meant by confidence interval?
A) A range of values used to estimate a population parameter is known as interval estimation by
confidence interval and the interval (a,b) that will include the population parameter with a high
probability.
 HYPOTHESIS TESTING
Q) What do you mean by hypothesis testing?
A) It is a procedure which enables us, based on the sample information, whether to reject or not
any specified statement.
Q) What is the statistical hypothesis?
A) A statistical hypothesis is a statement about a characteristics of one or more populations. This
statement may or may not be true.
Q) What is null hypothesis?
A) An assumptions to be tested for possible rejection is called a null hypothesis. It is denoted by H0
Q) What is alternative hypothesis?
A) Any hypothesis that is different from the null hypothesis and is set up in parallel to the null
hypothesis is called an alternative hypothesis. It is denoted by H1.
Q) What is simple hypothesis?
A) A hypothesis in which all the parameters of a distribution are specified is called a simple
hypothesis.
A) What is composite hypothesis?
A) A hypothesis that is not simple i.e a hypothesis in which all the parameters of the distribution
are not specified is called a composite hypothesis.
Q) Define level of significance.
A) The probability of making a type I error, that is, the probability of rejecting a true null
hypothesis.
Q) Define degree of freedom.
A) The degree of freedom is defined as the number of observations that can be chosen freely.
Q) What is a rejection region?
A) A rejection region refers to a set of values for the test statistic that leads to the rejection of the
null hypothesis.
Q) What is an acceptance region?
A) The area of the distribution in which the null hypothesis is not rejected is called the acceptance
region.
Q) Define one tail test.
A) If the critical region is located only in one tail of the sampling distribution of the test statistic,
the test is called one tailed test.
Q) Define two-tail test.
A) If the critical regions are located equally in both tails of the sampling distribution of the tets
statistic, the test is called two-tail test.
Q) Distinguish between Type I error and Type II error.
A) Rejection of H0 when H0 is true is type I error, whereas acceptance of H0 when H1 is true is type
II error.
 REGRESSION & CORRELATION
Q) Define regression.

A) The dependence of one variable (dependent variable) to the other variable (independent
variable) is called regression.

Q) Define regressand.

A) The variable whose resulting value depends upon the selected value of independent variable is
called as regressand.It is also called response variable, predictand variable, dependent variable or
explained variable.

Q) Define regressor.

A) The variable that forms the basis of prediction is called as regressor.It is also called predictor
variable, independent variable, controlled variable or explanatory variable.

Q) Define scatter diagram.

A) The graphic representation of a set of n pairs of bivariate data is called scatter diagram.

Q) What is curve fitting?

A) Curve fitting is a process of estimating the parameters of the population regression function
from an observed sample.

Q) What is the method of least square method?

A) The method of least square consists of determining the values of unknown parameters that will
minimizes the sum of squares of residuals.

Q) Define slope.

A) The between covariance and variance of independent variable.

OR

Slope is the per unit change in independent variable.

Q) What is correlation?

A) The interdependence of one variable to the other variable is called correlation.

Q) Write down the properties of least square line.

A) 1) The sum of the residuals is zero, that is ∑e=0

 2) The sum of the squares of the residuals is minimum, that is ∑e2=minimum

3) The sum of the observed values equals to the sum of the fitted values. ∑yi=∑ŷi

4) The regression line is always passes through the point of means (ẍ,ӯ)

Q) Define positive correlation.

A) The correlation is said to be positive if the two random variables tend to move in the same
direction.

Q) Define negative correlation.

A) The correlation is said to be positive if the two random variables tend to move in the opposite
direction.

Q) Define no correlation.

A) If one least squares regression line is horizontal and the other least squares regression line is
vertical then there is no correlation between the two random variables.

Q) Write down the properties of correlation coefficient.

A) 1) r is symmetrical with respect to the variables X and Y, that is ryx = rxy

2) r is the covariance of values of the two variables X and Y, r = Cov(zx, zy)

3) r is always lies between -1 to +1

4) r is geometric mean of two regression coefficients.

r= √𝑏𝑥𝑦 ∗ 𝑏𝑦𝑥
 ASSOCIATION
Q) Define variable.
A) A variable that can be expressed numerically is called variable.
Q) Define association.
A) The relationship between two attributes is known as association.
Q) Define multinomial population.
A) When each element of a population is assigned to one and only one of more than two attribute
categories, the population is called multinomial population.
Q) What is attribute?
A) A characteristics that cannot be expressed numerically is called an attribute.
Q) Define positive and negative classes.
A) The classes are formed by positive attributes are called positive classes, while the classes are
formed by negative attributes are called negative classes.
Q) Define contrary classes.
A) The classes are formed both positive as well as negative attributes are called contrary classes.
Q) Define Class and Class frequency.
A) Class: A class is a set of the objects which are sharing a given characteristics.
Class frequency: A class frequency is the number of observations, which are distributed
in a class.
Q) Define association.
A) The relationship between two attributes is known as association.
Q) Define Dichotomy.
A) The process of dividing the objects into two mutually exclusive classes is called dichotomy.
Q) Define order of class.
A) Order of class is known by the number of attributes specifying the class.
Q) Define ultimate class frequency.
A) The frequencies of classes of the highest order are called ultimate class frequencies.
Q) Define consistent of the data.
A) We calculate the ultimate class frequencies and find out whether anyone is negative. When
none of the class frequencies is negative we say that the data is consistent.
Q) What is meant by independence of attributes?
A) Two attributes A and B are said to be independent If there is no relationship of any kind
between the attributes A and B.
(𝐴)(𝐵)
(AB) = 𝑛
Q) Define positive and negative associated attributes.
A) Two attributes A and B are said to be positively associated if (AB)>(A)(B)/n
Two attributes A and B are said to be negatively associated if (AB)<(A)(B)/n
Q) Define coefficient of association.
A) A numerical measure of the strength of association, between two attributes A and B, is known
as coefficient of association.
(𝐴𝐵)(𝛼𝛽)−(𝐴𝛽)(𝛼𝐵)
Q = (𝐴𝐵)(𝛼𝛽)+(𝐴𝛽)(𝛼𝐵)
Q) Define contingency table.
A) A table that consists of two or more rows and two or more columns into which observations are
classified according to two different criteria is commonly called as contingency table.
Q) Define coefficient of contingency.
A) Coefficient of contingency measures the strength of association of two criteria of classification
of a contingency table.
Q) Define rank correlation.
A) The correlation between two sets of ranking is called rank correlation.
rr = 1-(6∑𝑑𝑖2)/(𝑛(𝑛2 − 1))
Q) Write down the properties of rank correlation.
A) 1) The rank correlation coefficient is a pure number.
2) The rank correlation coefficient always lies between -1 and +1
 TIME SERIES
Q) Define time series.
A) A time series consists of numerical data collected, observed or recorded at successive time
periods.
Q) Define analysis of time series.
A) Analysis of time series is a decomposition of a time series into its different component for
separate study.
Q) What is the difference between histogram and historigram.
A) The graph of a time series is called historigram.
A histogram is a series of adjacent rectangles drawn for a grouped frequency distribution such
that the area of each rectangle is proportional to the frequency.
Q) Define signal.
A) The systematic component of variation in time series is called signal.
Q) Define noise.
A) An irregular component of variation in time series is called noise.
Q) What are the components of time series?
A) There are four components of time series.
1) Secular trend
2) Seasonal variations.
3) Cyclical movements
4) Irregular movements
Q) What is the additive and productive model?
A) Additive model: Y= t+s+c+i
Productive model: Y = t*s*c*i
Q) Define secular trend.
A) A secular trend is a long term movement that indicates the general direction of the variation in a
time series. This movement is smooth, steady and regular in nature.
Q) Define seasonal variations.
A) Seasonal variations are short term movements that indicate the identical changes in a time
series during the corresponding seasons.E.g. an after Eid sale in a departmental store.
Q) Define cyclical movements.
A) Cyclical movements refer to the long term oscillations about the trend line the movements take
the form of upward and downward swings they are also called cycles. The four phases of a
business cycle are prosperity, recession, depression and revival provide important examples of
cyclical movements.
Q) Define irregular movements.
A) Irregular movements are unsystematic in nature. They occur in a completely unpredictable
manner by chance events such as wars, floods, etc.
Q) What are the different methods of measuring the secular trend?
A) There are four methods of measuring the secular trend.
1) Free hand curve method 2) Method of semi average
3) Method of moving average 4) Method of least square
Q) Define free hand curve method.
A) In free hand curve method time series is plotted on the graph paper taking time along X axis and
time series observations along Y axis.

Q) Define method of semi average.

A) Method of semi averages the observed values of time series are divided into two equal parts. If
the number of values is odd then the middle value is ignored. The averages of each part are
placed against the mid points of two parts.
Q) Define method of moving average.
A) The k period moving averages are defined as the averages calculated by using the first k
consecutive values of the observed time series then repeating the operation by discarding one
value at the beginning and including the first value after the proceeding total and so on. This
process is continued till the last k consecutive values have been averaged.
Q) Define principle of least square.
A) The principle of least square states the sum of squares of the deviations of the observed values
from the corresponding estimates values should be least.
Q) What is forecasting?
A) Forecasting is a process of assessing the magnitude of a time series variable in future on the
base of past pattern.