Name
G M Firoz Khan
Roll No.
520931217
Program MBA Subject
Statistics for Management [Set 2]
Code
MB 0024
Learning Systems Domain –Indira Nagar, Centre Bangalore [2779]
S t 2
MB0024
1. What What do you you mean mean by samp sample le surv survey ey? ? What hat are are the the different sampling methods? Briefly describe them. Sample is a finite subset of a population drawn from it to estimate the characteristics of the population. Sampling is a tool which enables us to draw conclusions about the characteristics of the population. Survey sampling describes the process of selecting a sample of elements from a target population in order to conduct a survey. A survey may refer to many different types or techniques of observation, but in the context of survey sampling it most often refers to a questionnaire used to measure the characteristics and/or attitudes of people. The purpose of sampling is to reduce the cost and/or the amount of work that it would take to survey the entire target population. A survey that measures the entire target population is called a census. Sample survey can also be described as the technique used to study about a population with the help of a sample. Population is the totality all objects abou aboutt whic which h the the stud study y is pro propose posed. d. Sa Samp mple le is on only ly a port portio ion n of this this popu popula lati tion on,, whic which h is se sele lect cted ed usin using g ce cert rtai ain n stat statis isti tica call prin princi cipl ples es ca call lled ed sampling designs (this is for guaranteeing that a representative sample is obta obtain ined ed for for the the stud study) y).. Once Once the the sa samp mple le deci decide ded d info inform rmat atio ion n will will be collected from this sample, which process is called sample survey. It is incumbent on the researcher to clearly define the target population. There are no strict rules to follow, and the researcher must rely on logic and judgment. The population is defined in keeping with the objectives of the study. Someti Some time mes, s, the the enti entire re popu popula lati tion on will will be suff suffic icie ient ntly ly smal small, l, and and the the rese resear arch cher er ca can n incl includ ude e the the enti entire re popu popula lati tion on in the the stud study. y. This This type type of research is called a census study because data is gathered on every member of the population. Usually, the population is too large for the researcher to attempt to survey all of its members. A small, but carefully chosen sample can be used to repres represent ent the popula populatio tion. n. The sample sample reflec reflects ts the chara characte cteris ristic tics s of the population from which it is drawn. Sampling methods are classified as either probability or probability or non-probability . In probability samples, each member of the population has a known nonzero probability of being selected. Probability methods include random sampling, system systemati atic c sampli sampling, ng, and strati stratifie fied d sampli sampling ng.. In nonprobability sampling, members are selected from the population in some non-rand non-random om manner. manner. These include include convenien convenience ce sampling, sampling, judgment judgment sampling, quota sampling, and snowball sampling. The advantage of probability sampling is that sampling error can be calculated. Sampling error is the degree to which a sample might differ from the population. When inferring to the population, results are reported plus or minus the sampling
S t 2
MB0024
error. In non-probability sampling, the degree to which the sample differs from the population remains unknown. Probability Sampling Methods 1.
2.
3.
Random Random sampling sampling is the purest form of probability sampling. Each member of the population has an equal and known chance of being selected. When there are very large populations, it is often difficult or impossible to identify every member of the population, so the pool of available subjects becomes biased. Systematic sampling is often used instead of random sampling. It is also called an Nth name selection technique. After the required sample size has been calculated, every Nth record is selected from a list of population members. As long as the list does not contain any hidden orde or der, r, this this sa samp mpli ling ng meth method od is as good good as the the rand random om sa samp mpli ling ng method method.. Its Its on only ly advant advantage age over over the random random sampli sampling ng techni technique que is simplicity. Systematic sampling is frequently used to select a specified number of records from a computer file. Stratified Stratified sampling sampling is co comm mmon only ly used used prob probab abil ilit ity y meth method od that that is superi superior or to rando random m sampli sampling ng becau because se it reduce reduces s sampli sampling ng error. error. A stratum is a subset of the population that share at least one common characteristic. Examples of stratums might be males and females, or mana manage gers rs and and no nonn-ma mana nage gers rs.. The The rese resear arch cher er firs firstt iden identi tifi fies es the the releva relevant nt stratu stratums ms and and their their actual actual repres represent entati ation on in the popul populati ation. on. Random sampling is then used to select a sufficient number sufficient number of subjects from each stratum. "Sufficient "Sufficient " refers to a sample size large enough for us to be rea reaso sona nabl bly y con onfi fide den nt that that the the stra stratu tum m rep represe resen nts the population.
Stratified sampling is often used when one or more of the stratums in the population have a low incidence relative to the other stratums. Non Probability Methods 1.
Convenien Convenience ce sampling sampling is used used in explor explorato atory ry resear research ch where where the researcher is interested in getting an inexpensive approximation of the truth. As the name implies, the sample is selected because they are con co nven venient ient.. This This no nonn-pr pro obabi babili litty meth metho od is often ften used used dur during ing prelim prelimina inary ry resear research ch effort efforts s to get a gross gross estima estimate te of the result results, s, without incurring the cost or time required to select a random sample.
2.
Judgment Judgment sampling sampling is a co comm mmon on no nonn-pr prob obab abil ilit ity y meth method od.. The The rese resear arch cher er se sele lect cts s the the sa samp mple le base based d on judg judgme ment nt.. This This is usua usuall lly y extens extension ion of conven convenien ience ce sa sampl mpling ing.. For For exampl example, e, a resear researche cherr may decide to draw the entire sample from one "representative" city, even though the population includes all cities. When using this method, the rese resea arch rcher must must be co conf nfid iden entt that that the chos osen en sample mple is truly ruly representative of the entire population.
3.
Quota sampli Quota sampling ng is the the no non n-pro -proba babi bili lity ty equi equiva vale lent nt of stra strati tifi fied ed sampli sampling. ng. Like Like strati stratifie fied d sa sampl mpling ing,, the resear researche cherr first first identi identifie fies s the
S t 2
MB0024
stra stratu tums ms and thei theirr pro proport portio ion ns as they they are are repr repres esen ente ted d in the the population. Then convenience or judgment sampling is used to select the required number of subjects from each stratum. This differs from stratified sampling, where the stratums are filled by random sampling. 4.
Snowball sampling is a special non-probability method used when the desired sample characteristic is rare. It may be extremely difficult or costt prohib cos prohibiti itive ve to loc locate ate respon responden dents ts in these these situat situation ions. s. Snowb Snowball all sampling relies on referrals from initial subjects to generate additional subjects. While this technique can dramatically lower search costs, it comes at the expense of introducing bias because the technique itself reduce reduces s the likeli likelihoo hood d that that the sa sampl mple e will will repres represent ent a good good cross cross section from the population.
2. What is the different between correlation and regression? What do you understand by Rank Correlation? When we use rank correlation and when we use use Pear Pearso soni nian an Co Corr rre elati lation on Co Coef effi fici cien ent? t? Fit a line linear ar regression line in the following data – X Y
12 123
15 150
18 158
20 170
27 180
34 184
28 176
48 130
Correlation When two or more variables move in sympathy with other, then they are said to be correlated. If both variables move in the same direction then they are are sa said id to be posi positi tive vely ly co corr rrel elat ated ed.. If the the vari variab able les s move move in oppo opposi site te dire direct ctio ion n then then they they are are sa said id to be nega negati tive vely ly co corr rrel elat ated ed.. If they they move move haphazardly then there is no correlation between them. Correlation analysis deals with 1) Measuring the relationship between variables. 2) Testing the relationship for its significance. 3) Giving confidence interval for population correlation measure. Regression Regression is defined as, “the measure of the average relationship between two or more variables in terms of the original units of the data.” Correlation analysis attempts to study the relationship between the two variables x and y. Regression analysis attempts to predict the average x for a given y. In Regression it is attempted to quantify the dependence of one variable on the other. The dependence is expressed in the form of the equations. Different between correlation and regression Cor orre rela lati tion on and and line linear ar regr regres essi sion on are are no nott the the sa same me.. Cons Consid ider er thes these e differences: S t 2
MB0024
•
•
•
•
•
Corre Correlat lation ion quanti quantifie fies s the degree degree to which which two variab variables les are relate related. d. Correlation does not find a best-fit line (that is regression). You simply are computing a correlation coefficient (r) that tells you how much one variable tends to change when the other one does. With correlation simp simply ly quan quanti tify fy regr regres essi sion on,, yo you u regression line is
you don't have to think about cause and effect. You how ho w well well two two vari variab able les s rela relate te to ea each ch othe other. r. With With do have have to thin think k abou aboutt ca caus use e and and effe effect ct as the the determined as the best way to predict Y from X.
With correlation, it doesn't matter which of the two variables you call "X" and which you call "Y". You'll get the same correlati correlation on coefficient coefficient if you swap the two. With linear regression, the decision of which variable you call "X" and which you call "Y" matters a lot, as you'll get a different best-fit line if you swap the two. The line that best predicts Y from X is not the same as the line that predicts X from Y. Correlation is almost always used when you measure both variables. It rarely is appropriate when one variable is something you experimentally manipulate. With linear regression, the X variable is often something you experimental manipulate (time, concentration...) and the Y variable is something you measure. The correlati correlation on answers answers the STRENGTH STRENGTH of linear linear asso associati ciation on between between paired variables, say X and Y. On the other hand, the regression tells us the FORM of linear association that best predicts Y from the values of X. (2a) Correlation is calculated whenever: -
-
Both X and Y is measu Both measure red d in each each subje subject ct and and quant quantif ifie ies s how much much they are linearly associated. In partic particula ularr the Pearson' Pearson's s product product moment moment correl correlati ation on coeffi coefficie cient nt is use sed d when hen the the assum sumptio ption n of both X and Y are are sa samp mple led d fro from normally-distributed normally-distributed populations are satisfied Or the Spear Spearman man's 's momen momentt order order correla correlatio tion n coeffic coefficien ientt is used if the the assumption of normality is not satisfied. Cor orre rela lati tio on is not use sed d when the the vari varia ables bles are are man manipul ipula ated, ted, for for example, in experiments.
(2b) linear regression is used whenever: -
•
At lea least one of the the inde indepe pen ndent dent varia ariabl bles es (Xi' (Xi's s) is to pred predic ictt the the dependent variable Y. Note: Some of the Xi's are dummy variables, i.e. Xi = 0 or 1, which are used to code some nominal variables. If one one mani manipul pulate ates s the X vari variabl able, e, e.g. e.g. in an expe experim riment ent..
Line Linear ar regr regres essi sion on are are no nott symm symmet etri ric c in term terms s of X and and Y. That That is interchanging X and Y will give a different regression model (i.e. X in terms of Y) against the original Y in terms of X.
S t 2
MB0024
•
•
On the the other ther hand hand,, if you inte interrcha change nge vari varia ables bles X and and Y in the the calculation of correlation coefficient you will get the same value of this correlation coefficient. The "best" linear regression model is obtained by selecting the variables (X's) with at least strong correlation to Y, i.e. >= 0.80 or <= -0.80 The same underlying distribution is assumed for all variables in linear regression. Thus, linear regression will underestimate the correlation of the the inde indepe pend nden entt and and depe depend nden entt when when they they (X's (X's and and Y) co come me from from different underlying distributions.
Spearman' Spearman's s rank correlatio correlation n coefficie coefficient nt or Spearman's rho, rho, named after Charles Spearman and often denoted by the Greek letter ρ (rho) or as r s, is a nonparametric measure of correlation – that is, it assesses how well an arbitrary monotonic function could describe the relationship between two variables, without making any other assumptions about the particular nature of the the rela relati tion onsh ship ip betw betwee een n the the vari variab able les. s. Cert Certai ain n othe otherr meas measur ures es of corr co rrel elat atio ion n are are para parame metr tric ic in the the se sens nse e of bein being g base based d on poss possib ible le relationships of a parameterized form, such as a linear relationship. In princi principle ple,, ρ is simply simply a speci special al cas case e of the Pearso Pearson n produc product-m t-mome oment nt coefficient in which two sets of data X i i and Y i i are converted to rankings x i i and y i i before before calcul calculati ating ng the coe coeffi fficie cient. nt. In practi practice, ce, howeve however, r, a simple simplerr procedure is normally used to calculate ρ. The raw scores are converted to ranks, and the differences d i,i, between the ranks of each observation on the two variables are calculated. If there are no tied ranks, then ρ is given by:
Where: d i i = x i i − y i i = the difference between the ranks of corresponding values X values X i i and Y i i , and n = the number of values in each data set (same for both sets). If tied ranks exist, classic Pearson's correlation coefficient between ranks has to be used instead of this formula .
One has to assign the same rank to each of the equal values. It is an average of their positions in the ascending order of the values. Conditions under which P.E can be used: used:
S t 2
MB0024
1. Samples should be drawn from a normal population. 2. The value of “r” must be determined from sample values. 3. Samples must have been selected at random.
3. What What do you you mean mean by business business forecas forecastin ting? g? What What are the different methods of business forecasting? Describe the effectiveness of time-series analysis as a mode of busin business ess forec forecast asting ing.. Descr Describe ibe the the method method of moving moving averages. Business forecasting refers to the analysis of past and present economic condi co nditio tions ns with with the object object of drawin drawing g infere inference nces s about about probab probable le future future business conditions. To forecast the future, various data, information and facts concerning to economic condition of business for past and present are analyz analyzed. ed. The proces process s of foreca forecasti sting ng includ includes es the use of stati statisti stical cal and mathem mathemati atical cal method methods s for long long term, term, short short term, term, medium medium term or any specific term. Following are the main methods of business forecasting:1. Busin Business ess Barom Baromete eters rs Business indices are constructed to study and analyze the business activities on the basis basis of which which future future condit condition ions s are predet predeterm ermine ined. d. As busin busines ess s indices are the indicators of future conditions, so they are also known as “Business Barometers” or “Economic Barometers‟. With the help of these S t 2
MB0024
business business barometers barometers the trend of fluctuat fluctuations ions in business business conditions conditions are made known and by forecasting a decision can be taken relating to the problem. The construction of business barometer consists of gross national produc product, t, wholes wholesale ale prices prices,, co consu nsumer mer prices prices,, indust industria riall produc productio tion, n, sto stock ck prices, prices, bank deposits deposits etc. These quantitie quantities s may be converted converted into relatives relatives on a certain base. The relatives so obtained may be weighted and their average be computed. The index thus arrived at in the business barometer. The business barometers are of three types: i.
ii.
iii.
2.
Barometers relating to general business activities: activities : it is also known as gene genera rall inde index x of busi busine ness ss ac acti tivi vity ty whic which h refe refers rs to weig weight hted ed or composite indices of individual index business activities. With the help of gene genera rall inde index x of busi busine ness ss ac acti tivi vity ty long long term term tren trend d and and cycl cyclic ical al fluctuations in the „economic activities of a country are measured but in some specific cases the long term trends can be different from genera generall trends trends.. These These types types of index index help help in format formation ion of co count untry ry economic policies. Busi Bu sine ness ss baro barome mete ters rs for for spec specif ific ic busi busine ness ss or indu indust stry ry : These barometers are used as the supplement of general index of business activity and these are constructed to measure the future variations in a specific business or industry. Business barometers concerning to individual business firm: firm : This type of barometer is constructed to measure the expected variations in a specific individual firm of an industry.
Time Series Analysis is also used for the purpose of making business forecasting. The forecasting through time series analysis is possible only when the business data of various years are available which reflects a definite trend and seasonal variation.
3. Extrapolation is the the simp simple lest st meth method od of busi busine ness ss fore foreca cast stin ing. g. By extrapolat extrapolation, ion, a businessma businessman n finds out the possible possible trend of demand of his goods and about their future price trends also. The accuracy of extrapolation depends on two factors: i) Knowledge about the fluctuations of the figures, ii) Knowledge about the course of events relating to the problem under consideration. 4. Regression Analysis The regression approach offers many valuable contributions to the solution of the forecasting problem. It is the means by which we select from among the many possible relationships between variables in a complex economy those those which which will will be useful useful for foreca forecasti sting. ng. Regres Regressio sion n relati relations onship hip may involve one predicted or dependent and one independent variables simple regr regres essi sion on,, or it may may invo involv lve e rela relati tion onsh ship ips s betw betwee een n the the vari variab able le to be foreca forecast st and and severa severall indepe independe ndent nt variab variables les under under multip multiple le regres regressio sions. ns. Statistical techniques to estimate the regression equations are often fairly complex and time-consuming but there are many computer programs now available that estimate simple and multiple regressions quickly.
S t 2
MB0024
5. Modern Econometric Methods Econometric techniques, which originated in the eighteenth century, have recently gained in popularity for forecasting. The term econometrics refers to the the appl applic icat atio ion n of math mathem emat atic ical al ec econ onom omic ic theo theory ry and and stat statis isti tica call procedure procedures s to economic economic data in order order to verify verify economic economic theorems. theorems. Models Models take the form of a set of simultaneous equations. The value of the constants in such equations is supplied by a study of statistical time series. 6. Exponent Exponential ial Smooth Smoothing ing Method Method This This method method is regard regarded ed as the best best method method of busin business ess forecast forecasting ing as compa co mpared red to other other method methods. s. Expone Exponenti ntial al smoot smoothin hing g is a specia speciall kind kind of weighted average and is found extremely useful in short-term forecasting of inventories and sales. 7. Choice of a Method of Forecasting The selection of an appropriate method depends on many factors – the context of the forecast, the relevance and availability of historical data, the degree of accuracy desired, the time period for which forecasts are required, the cost benefit of the forecast to the company, and the time available for making the analysis. Effectiveness Effectiveness of Time Series Analysis: Time Time se seri ries es anal analys ysis is is also also used used for for the the purp purpos ose e of maki making ng busi busine ness ss forecasting. The forecasting through time series analysis is possible only when when the the busi busine ness ss data data of vari variou ous s year years s are are avai availa labl ble e whic which h refl reflec ects ts a definite trend and seasonal variation. By time series analysis the long term tren trend, d, se secu cula larr tren trend, d, se seas ason onal al and and cycl cyclic ical al vari variat atio ions ns are are as asce cert rtai aine ned, d, analyzed and separated from the data of various years. Merits: i) It is an easy method of forecasting. ii) By this method a comparative study of variations can be made. iii) Reliable results of forecasting are obtained as this method is based on mathematical model. Method of Moving Averages One One of the most most simple simple and popula popularr techni technical cal analys analysis is indica indicator tors s is the moving averages method. This method is known for its flexibility and userfriendliness. This method calculates the average price of the currency or stock over a period of time. The term “moving average” means that the average moves or follows a certain trend. The aim of this tool is to indicate to the trader if there is a beginning of any new trend or if there is a signal of end to the old trend. Traders use this method, as it is relatively easy to understand the direction of the trends with the help of moving averages.
S t 2
MB0024
Moving average method is supposed to be the simplest one, as it helps to unde unders rsta tand nd the the char chartt patt patter erns ns in an ea easi sier er way. way. Sinc Since e the the curr curren ency cy’s ’s average price is considered, the price’s volatile movements are evened. This method rules out the daily fluctuation in the prices and helps the trader to go with the right trend, thus ensuring that the trader trades in his own good. We come across different types of moving averages, which are based on the way way thes these e aver averag ages es are are co comp mput uted ed.. St Stil ill, l, the the basi basis s of inte interp rpre reta tati tion on of averages is similar across all the types. The computation of each type set itself different from other in terms of weightage it lays on the prices of the curre currenci ncies. es. Curren Currentt price price trend trend is always always given given a higher higher weight weightage age.. The three basic types of moving averages are viz. simple, linear and exponential. A simple moving average is the simplest way to calculate the moving price averages. The historical closing prices over certain time period are added. This sum is divided by the number of instances used in summation. For exam exampl ple, e, if the the movi moving ng aver averag age e is ca calc lcul ulat ated ed for for 15 days days,, the the past past 15 historical closing prices are summed up and then divided by 15. This method is effective when the number of prices considered is more, thus enabling the trader to understand the trend and its future direction more effectively. A linear moving average is the less used one out of all. But it solves the problem of equal weightage. The difference between simple average and linear average method is the weightage that is provided to the position of the prices in the latter. Let’s consider the above example. In linear average method, the closing price on the 15th day is multiplied by 15, the 14th day closing price by 14 and so on till the 1st day closing price by 1. These results are totalled and then divided by 15. The exponential moving average method shares some similarity with the lin linea earr movi moving ng aver averag age e met metho hod d. This This met metho hod d lay lays emph empha asis sis on the smoothing factor, there by weighing recent data with higher points than the previous data. This method is more receptive to any market news than the simp simple le aver averag age e meth method od.. Henc Hence e this this make makes s expo expone nent ntia iall meth method od more more popular among traders. Moving Movin g averag averages es method methods s help help to identi identify fy the correc correctt trends trends and their their respective levels of resistance.
4. What What is defin definit ition ion of Statis Statistic tics? s? What What are the differen differentt char charac acte teri rist stic ics s of stat statis isti tics cs? ? What What are are the the diff differ eren entt func functi tion ons s of Stat Statis isti tics cs? ? What What are are the the limi limita tati tion ons s of Statistics? According to Croxton and Cowden, ‘Statistics is the science of collection, presentation, analysis and interpretation of numerical data.’ Thus, Statistics contains the tools and techniques required for the collection, presentation,
S t 2
MB0024
analy nalysi sis s and inte interrpret pretat atio ion n comprehensive.
of
data data..
Thi This
defi defini nittion ion
is
prec preciise
and and
Characteristic of Statistics a. Statistics Deals with aggregate of facts: Single figure cannot be analyzed. b. Statistics are affected to a marked extent by multiplicity of causes: The statistics of yield of paddy is the result of factors such as fertility of soil, amount of rainfall, quality of seed used, quality and quantity of fertilizer used, etc. c. Statis Statistic tics s are numeri numerical cally ly expres expressed sed:: Only Only nume numeri rica call fact facts s ca can n be statistically analyzed. Therefore, facts as ‘price decreases with increasing production’ cannot be called statistics. d. Statistics are enumerated or estimated according to reasonable standards of accuracy: The facts should be enumerated (collected from the field) or estima estimated ted (compu (computed ted)) with with requir required ed degree degree of acc accura uracy. cy. The degree degree of accu ac cura racy cy diff differ ers s from from purp purpos ose e to purp purpos ose. e. In meas measur urin ing g the the leng length th of screw screws, s, an acc accura uracy cy upto upto a millim millimetr etre e may be requir required, ed, wherea whereas, s, while while measuring the heights of students in a class, accuracy upto a centimetre is enough. e. Statis Statistic tics s are col collec lected ted in a system systemati atic c manner manner:: The The fact facts s shou should ld be collected according to planned and scientific methods. Otherwise, they are likely to be wrong and misleading. f. Statistics are collected for a pre-determined purpose: There must be a definite purpose for collecting facts. Eg. Movement of wholesale price price of a commodity g. Statistics are placed in relation to each other: The facts must be placed in such a way that a comparative and analytical study becomes possible. Thus, only related facts which are arranged in logical order can be called statistics. Functions of Statistics 1. 2. 3. 4. 5.
It simplifies mass data It makes comparison easier It brings out trends and tendencies in the data It brings out hidden relations between variables. Decision making process becomes easier.
Major limitations of Statistics are: are: 1. Stati tatist stic ics s does does no nott dea deal with ith qual qualit itat ativ ive e data. ata. It dea ealls on only ly with ith quantitative data. 2. Statis Statistic tics s does does not deal with indivi individua duall fact: fact: Statisti Statistical cal methods methods ca can n be applied only to aggregate to facts. 3. Statistic Statistical al inferences inferences (conclusions (conclusions)) are not exact: Statistica Statisticall inferences inferences are true only on an average. They are probabilistic statements. Statistic tics s can be misuse misused d and misint misinterp erpret reted: ed: Incre Increasi asing ng misuse misuse of 4. Statis Statistics has led to increasing distrust in statistics. 5. Commo Common n men canno cannott handle handle Statis Statistic tics s proper properly: ly: Only Only stati statisti sticia cians ns can handle statistics properly.
S t 2
MB0024
5. What are the different stages of planning a statistical survey? Describe the various methods for collecting data in a statistical survey. The planning stage consists of the following sequence of activities. 1. Nature Nature of the problem problem to be investigated investigated should should be clearly clearly defined in an un- ambiguous manner. 2. Object Objective ives s of invest investiga igatio tion n should should be stated stated at the outset. outset. Objectiv Objectives es could be to obtain certain estimates or to establish a theory or to verify a existing statement to find relationship between characteristics etc. 3. The scope scope of investigati investigation on has to be made clear. clear. It refers refers to area to be covered, identification of units to be studied, nature of characteristics to be observed, accuracy of measurements, analytical methods, time, cost and other resources required. 4. Whether Whether to use data collected collected from primary primary or secondary secondary source source should be determined in advance. 5. The The orga organi niza zati tion on of inve invest stig igat atio ion n is the the fina finall step step in the the proc proces ess. s. It encom encompas passes ses the determ determina inatio tion n of number number of invest investiga igator tors s requir required, ed, their training, supervision work needed, funds required etc. Collection of primary data can be done by anyone of the following methods. i. Direct personal observation ii. Indirect oral interview iii. Information through agencies iv. Information through mailed questionnaires iv. iv. Info Inform rmat atio ion n throu through gh sche schedu dule le fill filled ed by inv inves esti tiga gato tors rs
6. What What are the funct function ions s of classi classific ficati ation? on? What are the requisites of a good classification? What is Table and describe the usefulness of a table in mode of presentation of data? The functions of classification are: a. b. c. d.
It It It It
redu reduce ce the the bulk bulk data data simplifies simplifies the data data and makes the data data more comprehe comprehensibl nsible e facilita facilitates tes compari comparison son of of character characteristic istics s renders renders the data data ready for for any statistic statistical al analysis analysis
Requisites of good classification are: i. ii. iii. iii. S t 2
Unam Unambi bigu guou ous: s: It shou should ld not not lea lead d to to any any con confu fusi sion on Exhaus Exhaustiv tive: e: ever every y unit unit sho should uld be allo allotte tted d to one and on only ly one one clas class s Mutual Mutually ly exclu exclusiv sive: e: There There sho should uld not be any overla overlappi pping. ng. MB0024
iv . v. vi. vii. vii. viii. viii.
Flexibility: It should be capable of being adjusted to changing situation. Suitab Suitabili ility: ty: It should should be suitab suitable le to object objective ives s of of surv survey. ey. Stabil Stability ity:: It shoul should d remai remain n stabl stable e throu througho ghout ut the the inve investi stigat gation ion Homoge Homogenei neity: ty: Simila Similarr unit units s are are placed placed in the same same clas class. s. Reveal Revealing ing:: Shoul Should d bring bring out essent essential ial feat feature ures s of the the coll collect ected ed data data..
Table is nothing but logical listing of related data in rows and columns. Objectives of tabulation are:i. To simplify complex data ii. To highlight important characteristics iii. To present data in minimum space iv. To facilitate comparison v. To bring out trends and tendencies vi. To facilitate further analysis
S t 2
MB0024