© Data Collection : Primary and Secondary Data © = Classification and Tabulation of Data © Presentation of Data & Frequency Distribution Data Collection : Primary and Secondary Data iiatiedae eo cee Long Answer Type Questions Q.15. What do you mean b: y data ? State the types of data based on. OR collection. Define data. Define and distinguish between primary and secondary data. Ans. Data are facts, figures and other Televant materials, Past and present, serving as bases for study and anal lysis. The data serve as the bases or raw materials for analysis. Without an analysis of factual data, no specific questions. The relevance, adequacy and teliability of data determine the quality of the findings of a study. Types of Data The data needed for a social science research may be broadly classified (a) Data pertaining to human beings, (b) Data relating to organizations, and (©) Data pertaining to territorial areas. Personal data or data related to human beings consist of demographic and socio-economic characteristics of individuals like age, sex, race, social class, religion, marital status, education, occupation, income, family size, Jocation of the household, life style, etc. and behavioral variables like attitudes, opinions, awareness, knowledge, practice, intentions, etc, Organisational data consist of data relating to an organisation’s ownership, objectives, resources, functions, performance and— ail 26 / Yashra Business Statistics sarvcture, degree of development, ete. of spatial divisions like vil Tadias, Woredas, sate/ regions and the nation, NBS cities, Primary Data refers tothe statistical material which the investigator originates fog Dims for the purpose of the enquiry in hand. In other words, itis one wich is collected by the investigator forthe first time e.g. ifthe com of living of workers ina city are tobe computed, then the information rearding ‘Se facts collected by the investigators or enumerators would be termed 22 Primary data. In India there are various agencies which colleet primary data ©.g.- National Sample Survey (NSS), State Level Economic and Statistical Departments etc. When we use primary data, it is called raw material, According to Wessel, “Data originally collected inthe process of investigation are known as primary data.” Merits (Degree of accuracy is quite high. (Gi) 1 does not require extra caution. (Gi) It depicts the data in great detail. Gy) Primary source of data collection frequently includes definitions of various terms and units used. (0) For some investigations, secondary data are not available. Demerits @ Collection of data requires a lot of time. Gi) It requires lot of finance. ii) In some enquiries itis not possible to collect primary data. (Gv) It requires a lot of labour. (¥) It requires a lot of skill. Secondary Data Secondary data are those which are collected from published ot ‘unpublished sources. Such data are also known as the second hand data. Moreover, secondary data are use in the shape of finished products ‘since they have been treated statistically in some form the other. Data published by CSO, Economic Surveys, RBI Bulletins are the secondary data. In the words of Wessel, “Data collected by other persons are cal secondary data.” ‘Some examples are quoted to make a clear analysis of secondary data: (a) Suppose we study the level of birt rate in Orissa between 1999-2000, For this data cannot be originally collected. We can obtain the required data from different issues of Population Census published by the Govt (b) Suppose we study World Bank assistance to poor countries. FOF this we get the data from different annual reports of World Bank whieh termed as secondary data. si Data Collection : Primary and Secondary Data /27 Merits (Use of secondary data is very convenient. (i) It saves time and finance. (it In some enquires primary data cannot be collected, (Gv) Reliable secondary data are generally available for many investigations. Demerits (i) Itis very difficult to find sufficiently accurate secondary data. (i) Its very difficult to find secondary data which exactly fulfils the need of present investigation (ii) Extra caution is required to use secondary data (iv) These are not availabe for all types of enquiries. Primary Data Secondary Data Primary data are always original | 1. Secondary data lacks originality. as it is collected by the invest-| The investigator makes use ofthe ‘ator. ata collected by other agencies. 2, Suitability of the primary data|2. Secondary data may or may not will be positive because it has} suit the objects of enquiry been systematically collected, 3. Primary data are expensive and|3. Secondary data are relatively time consuming, cheaper. 4, Extra precautions are not|4. It is used with great care and required. caution, 5. Primary data are in the shape of | 5. Secondary data are usually in the raw material shape of readymade products. 6. Possibility of personal prejudice. |6. Possibility of lesser degree of ‘Perso-nal prejudice. 7. Primary data is according to|7. Some other investigating agency objective of researcher collects it for its own use 8. More reliable because the inves-| 8. Less reliable as someone else has tigator himself collects it. investig . 1e data cx ted in the but ee Da Se Sd by him wee et eg Invasion bs Eas GSAS acca ge A OCmNCY AMclancai ga shou" eStigaton (0) Primary daa oe degree ‘racy maintained by each iene ‘keep in mind the (6) None ofthe two (@ Imaginary data ‘$:Time and Condition of Collate 10, Sources of secondary data are: before making use of avalaie ogee em of Ft: ale (@ Data obtained by survey for the purpose was collected, Which period and conditions, the daa (©) Data obtained by personal investigation " (©) Production records ofa firm 6. Comparison : Invesigaor should keepin mind wheter te @ All of these, Secondary data’ reasonable, consistent and comparable, ‘Ans. 1. (@).2. (6,3. (4.0), 5. (9), 6. @), 7. (0,8. (9,9. (0), 10. ). ee ee Oe at their face value without knowing their means, values and limitations. i 8. Homogeneous Conditions: Iris not sae to take published statistics Classification and Tabulation of Data Q21. Define Classification and show their importance in statistical Statistical data are of what type ? three —__(€) None of tse, oo (©) one © study. by the investigator himself is called : Ans. Inthe words of Secrist, “Classification isthe process of arrani The data collected by () Secondary data into sequences and groups according to their common characteris we 4 The process of arranging data ilo homogenous group or classes The method for collecting primary ct 4 Ora Investigation | J cording wo some common charciercs present in te dais called ee} 38 / Yashraj Business Statistics ‘Cuassification is the way of arranging the data in different classes jn, ‘order to give a definite form and a coherent structure to the data collected, facilitating their use in the most systematic and effective manner. It isthe process of grouping the statistical data under various understandable Tpomogencous groups for the purpose of convenient interpretation. A uniformity of attributes is the basis criterion for classification; and the grouping of data is made according to similarity. Classification becomes necessary when there is diversity in the data collected for meaningful [presentation and analysis. However, in respect of homogeneous presentation of daa, classification may be unnecessary. Objectives and Importance of Classification of Data : ‘To group heterogeneous data under the homogeneous group of ‘common characteristics; : ‘© To facility similarity of various group; To facilitate effective comparison; ‘© To present complex, haphazard and scattered dates in a concise, logical, homogeneous, and intelligible form; of ‘© To maintain clarity and simplicity of complex data; - ‘* To identify independent and dependent variables and establish their ‘« Toestablish a cohesive nature for the diverse data for effective and logical analysis; ‘© To make logical and effective quantification. . Q.22. What do you understand by tabulation? Explain objective and importance of tabulation. ‘Ams. The process of placing classified data into tabular form is known a8 tabulation. A table is a symmetric arrangement of statistical data in rows and ‘columns. Rows are horizontal arrangements whereas columns are vertical ‘arrangements Itmay be simple, double or complex depending upon the type of classification. . Objective of Tabulation 1L To simplify complex data : In the process of tabulation of dat unnecessary details are avoided and data are presented systematically in ‘columns and rows in a concise form. All tabular data re presented in such: ‘manner that they become more meaningful and can be easily understood by ‘common man. 2. To facilitate comparison : Data presented in rows and facilitate comparison, Since a table is divided into various parts and for Part separate sub-totals and totals are given relationship between vari items of the table can be easily understood. 1 Classification and Tabulation of Data / 39 3. To economies space : Economy of space is achieved by tabulation, as all unnecessary details and, ‘quality 4. To depict trend and pattern of data : the trend of the information under study and 1 figures and utility of the data, a niet = Tabulation of a depicts reveal the pteres within te ‘Which cannot be understood in a descriptive form of presentation, 5. Tohelp reference: When ata ae arranged in bes with esa table numbers, hey can be exlySdenfed ate reference for future studies, “ eee 6, To facilitate tats analysis: After classifcaton and tabulation, statsical data becomes fit for analysis and interpretation, Various seca measures like averages, dispersion, correlation, ete can be aes cay ffom te data which are systematically tabulated Importance of Tabulation (1) Tabulation makes complex data simple and easy to understand. @) Maximum information can be collected from tables. G) Tabulation helps in finding mistakes easily. (4) Tabulation isa cheap mode of presentation. It same time and energy. (5) Tables make data more comparable and easy to analyse. Q.23. Ans. Q.24. Ans. the clas b 7 Short Answer Type Questions ‘State the essentials of good classification. Essentials of classification The classification must be exhaustive so that every unit of the distribution may find place in one group or another. Classification must conform to the objeets of investigation. All the items constituting a group must be homogeneous. Classification should be elastic so that new facts and figures may easily be adjusted. Classification should be stable. If it is not so and is changed for | ‘every enquiry then the data would not ft for an enquiry. ‘The data must not overlap. Each item of the data must be found in ‘one class Distinguish between classification and tabulation. (1) First the data are classified and then they are presented in tables, ation and tabulation in fact goes together. So classification is the is for tabulation, (2) Tabulation is a mechanical function of classification because in tabulation classified data are placed in row and columns. (3) Classification is a process of statistical analysis where as tabulation. isa proc e88 of presenting the data in suitable form. . tas7, ‘Ams. 1. (@),.2. B), 3. (D4. ©), 5: 0), 6: (8, 7. (0), 8. @)- 40/ Yashraj Business Statistics ‘Classification of the tasaeaton of the student (@) Qualitative (©) Geographi waa one zy following aed (@) Individual om oy setae sre (© Classified Ae When two t) ah ue YS of Information obtained from tablet (@) simple table double (©) treble table : is pert at oar S aim of tabulation is not : ot cua (a) systematic presentation : © erro (©) comparative study (8) tol about se ‘The effect of data on mind throw tabulation is : (@) permanent oy i (©) hypothetical RS ‘Whose statement is this : “Tabulatio, in its broadest xdatiy sctenpecilil ie Wt bisa atone brie eee, (©) Tippett (©) Fisher (@ Blair Which statement is true ? (2) Classification is not the basis of tabulation (b) Tabulation is mechanical aspect of classification (©) To keep the data in systematic form is nt an objective of tabulation (6) None of these ‘ Classification is the process of arranging data in : (a) different rows (b) different columns (©) different columns and rows (@) grouping of related facts in different classes. Presentation of Data and Frequency Distribution Long Answer Type Questions {What do you mean by Presentation of Data ? Discuss the types of presentation, or ‘What do you mean by ‘frequency distribution’? Describe the kind of Frequency Distribution. Frequency Disribution ‘Meaning - Frequency distribution is a table in which datas are divided into diferent classes and numbers of units in each partis classified. In other words, in this different frequencies of the same figures are presented. Frequency distribution is formed for three main reasons. (a) To make analysis of datas easy. (b) to take out the frequencies of data - disribution. (©) To make calculation of different statistical quantities easy. Kinds of Frequency Distribution Frequency distribution are mainly of two types : (a) Univariate Frequency Distribution. () Bivariate Frequency Distribution (1) Univariate Frequency Distribution are of three types : (a) Series of individual observations; (b) Discrete Series; (©) Continuous Series. ( Series of Individual observation - In series of individual observation every characteris measures differently. For example ifthe marks obtained by 20 sudents are written differently or monthly income of 10 family or the heights of7 people are written differently then they comes under the category of series of Individual observation, ‘Ans. For Example : Name: EINA MEENA DIKA TINA BINA BIKA SEEMA Height; 165 162 150 155 153. 164166 Following is one more example of Frequency Distribution : ~ Roll No, Marks Roll No. 7 ir 80 2 4 B 4e ee + vashray Business Statistics ‘ 3 tvution / 43 ‘ « ié a Presentation of Data and Frequency Distril as 9s “The variable whic 7 a ” “4 connyus, According 1 Prof. Bordington, “The variable which xn : 89 7] orimmediate valve between the smallest and largest : 3 ~ take oi called continuous series.” In continuous series the class 0 7 i 7 Stun Gon called cominnous series In coninoos series the ° — 20 Tr] iter ence fe present in the frequency distribution from starting 10 the 88 class difference is pres i uous series and discrete a difference between continuous se al calculation series of Fi end. Like this there can be ween cor panera ct sequency Distibution 1 in the first one each class is divided into uppe dosed ct TRS can en 8 rag eal Sc ee wn on of fe ao Seeing ones ca Be aranged inh loving meng Nr example of continuous series is given below. Marks Arranged in Ascending Order Y “aneomaies: 020° 2040 4060 e080 0-100 Toa! i 3 81 Ne. of Suodecal/ sae 0) ots ae a0aiam 15S 10 Fe sai 84 "i Class Intervals or classification of groups 5 7 8s a When there is visible statistical measure between statistical units then 7 is; only lasifcation between class interval is possible height, weight, income, at 8s 94 export, production etc. only datas of these types can be classified. For is 2 a se] Siac mun cps of 10 se of wares i Marks Arranged i t0 500 Rs. to 2000 Rs. datas of 1000 will be collected. These figures o8 ieee rc eda srs tts a ear 2 80 " class of expenses are divided with 200 Rs. difference then the series will be oe = 78 1m like this = = be? z 7 B Class intervals Frequencies ss ot 7 B ‘ + 9 81 16 de Expenses in Rupees No. of Students (Gi Discrete Series - In discrete series each unit can be exactly (Lowest value) $00-750 00 and there is definite difference between the units In this numbers are 750-1000 150 ‘umbers. According to Prof. Bodington, “Discrete series isa series in w 1000-1250. 300 there is definite differance between the units.” The difference between 1250-1500 a units are clear numbers of children in a family. No. of rooms ina house 1500-1750 ao x aerate 1750-2000 PT ieaanateny Example of Discrete Series 4 eee Never Chldren in Pansy ()30/061,21863 4 SSI Bivariate Frequency Distribution - Bivariate Frequency Distribution No. of Families (F) 210 20 50 60 40 12 8 .2Pe of frequency Distribution in which datas are clasifed by keeping ‘Some times by caleulation the no. of alphabets in a word also a ee ars Classifies the pair of inspected on figures series is made and different statistical measures are calculated. In this ‘equencies. For example presenting the number of alphabets of a word are calculated and then after writing there discrete series is made. - (Gil) Continuous Series - In continuous series the measures at definite instead there isa class internal between two numbers, In thisPresentation of Data and Frequency Distribution / 5 Ff 4447 Yasnraj Business Statistics 2.26. Ans. Important words s For making any type Renin to con (0.27. class test of 0 students were examined and thee more : juency ibutic of 50) are given, roll-numberwise, as under. Prepare # yivariate Q) Range : Range of any freq distribution the Cable in the class-interval of 10- tic 12° 3,74 A Oy? AS 10 Series difference between the upper limit 12 23614 10 2 4 Marks in Statistics 10 34 12 RNo. 1 12 13 14 15 Marks in Economics 8 20.26 18 8 16 2 14 6 ‘Marks in Statistics. 26-20 30 4 22 frequency distaneticits imi it ‘Tally-Sheet scr fon nova ein ino a of the clags inscrval Eau ee i za] 0-10 | 10-20 | 20-30 | 30-40 | 40-50 | Total ; many expected values ct one class interval and Nien —_ limits. In the i et Timitofnent cissinewawecagamg °° | 2 | NO) = m |. - 3 mee Me a 1000, 1250 1500 and 1750 are he i020 >|“, eve) | gee led 4 ne wee oe i 0, 1000, 1250, 1500, 1750 and 20-30 ya) | 2) | 2) = - 6 upper limits. For making statistical 30-40 =| a] wey | ve | - 5 — ‘easy lower limit is denoted by h 40-50 = = = = = = , and upper limit is denoted by ‘ 4 aja = (4) Magnitude of class intervals : : # 20 students appeared in an examination. The marks obtaiend ‘out of 50 maximum marks are as follows : ‘The difference between the lower and 5, 16, 17, 17, 20, 21, 22, 22, 22, 25, 25, 26, 26, 30, 31, 31, 34, upper limit of a class interval is known as the magnitude of class intervals. | 35, 42, 48 (5) Mid value or mid points : The Classify the data by “Ecclusive Method’ and by i~ Inclusive Method” the width of the class-intrval being 10. mid place of class limit is known as the mid value or mid points. To take out the ‘mid point or mid value the upper and the ower limit is added and then halfed. or Rens Mang [ Ta Marts | oa Students Mid - value = Ath inthis example the mid value off ‘i 0-10 T Hit 500 +750 695 in dhe same way the mid vales ‘ TAL LL (500 ~ 750) is classes will be 875, class limit is 1500-750 is 2000. Thisr 46 / Yashraj Business Statistics Q.29. The marks scored by SO students in an examination sven below : 19 i SSige DMB aS1 44 926 arse gg STIRS? Wigs Mey 1s” sy 17 TG SS 31) a6 38 8s7 35247” 29 ay Ree 8857258 37, 54 See Mast ge 25838 29.029" 45 a Prepare a frequency Table taking a class internal of ten Paper Tally Sheet a4 Presentation of Data and Frequency Distribution / 47 36 | 2s 91-5015 60 ads OF TE a2 8 43 80 om 57 6 3 Ml 35 8% 10 23 9 4 Objective Type Questions 1, Iman exclusive series : () both class limits are considered (©) the upper limit is excluded () both limits are excluded (@) the lower limit is excluded 2, Difference of upper and lower limit of a class is called : () Class frequency (b) Magnitude of class-interval (€) Class limits (@ Mid-point 3. In usual notation Sturges! formula is : (@n= 14332 logN @)n = 1-332 10g N (©) n= 1+ 3.322 log N @ None of these. 4. Mid-value of 50 - 60 is (@) 50 (@) 55 oo @ 34 5. If the elass-intervals in a frequency distribution are 72-73.9, 74~ 18.9, 16-71.9, 78-79.9, then the mid-value of the class 74-75.9 is: (@) 74.50 (b) 74.90 ©) 74.95 @ 75.00 Ans. 1. (0), 2. (0), 3. (@), 4. 0), 5. ©). .