Você está na página 1de 7

CHAPTER III DESIGN OF THE STUDY This chapter briefly sketches the rationale behind the choice of the

study area, the sampling framework, and the statistical and econometric techniques used for analysing the data collected. 3.1 Choice of study !e The Second-Tier cities of Tamil Nadu state were considered as the universe of this study. Among the five Second-Tier cities of Tamil Nadu, two corporation cities, vi ., !oimbatore and Salem "#ig. $.%& were selected randomly. 'ncreased industrial growth coupled with rapid urbani ation that in turn triggered increasing inhabitations of different income strata are the characteristic features of these two selected corporation cities. The residents of these cities not only had the benefit of urbani ation in terms of a variety of consumer products, but also had reaped the advantages of accessing to fresh livestock products, as the leading livestock production pockets were ad(acent to these cities. )f these two cities, !oimbatore is the second largest city of Tamil Nadu, known for its te*tile and manufacturing factories, engineering firms and automobile parts manufacturers, while Salem is the fifth largest city of the State, sheltering largely cottage industries, besides a number of industries including Steel Authority of 'ndia +imited "SA'+& and an e*clusive ,lectrical and ,lectronics 'ndustrial ,state. 3." Se#ectio$ of househo#ds A multistage sampling procedure was adopted to select the respondents of the study. 'n the first stage, as stated above, two Second-Tier cities, vi ., !oimbatore and Salem were selected randomly. 'n the second stage, eight ones, four from each of the two selected cities, were chosen and in the third stage, %- wards, two from each chosen one were selected using simple random sampling technique. 'n the fourth stage, %-. household respondents, %. from each of the selected wards were chosen randomly. Thus, this study had the sample si e of %-. household consumers comprising /. from each of the cities "Table $.%&.

T %#e 3.1& S '(#e househo#ds i$ the study !e S#. No. %. 1. $. 6. %. 1. $. 6. Salem !oimbatore Dist!ict N 'e of the )o$e N 'e of the chose$ * !d ,ast 2est North South Suramangalam 8asthampatty Ammapet 9ondalampatty Sowripalayam 0pplipalayam 3.S.4uram Thillai nagar 4eelamedu 5andhipuram 5opalapuram Ashok nagar Tot # 7agirammapalayam Seerangapalayam Swarnapuri Suramangalam Ammapet 9ichipalayam 9ondalampatty +inemedu Tot # G! $d Tot # -S '(#e si.e/ 3.3 Pe!iod of study The reference year for the study was 1..:-./ and the data collection was undertaken during the months of 7anuary, #ebruary, ;arch and April, 1../. 3.1 2ethod of e$3ui!y $d co##ectio$ of d t #rom the household consumers so selected, relevant data were collected to achieve the ob(ectives of the study. The data were collected through personal enquiry, by interviewing the sample respondent households with the help of a structured and pilot-tested interview schedule. The interview schedule had the demographic and socio-economic details of the consumers, followed by the e*penditure on <food= items "cereals, pulses, vegetables, spices, condiments, milk, meat, egg, etc.& and <non-food= items "education, recreation, medical e*penses, rent, etc.&. The interview schedule also had the provision to assess the quality perceptions, awareness and preferences for various products of milk and meat. No. of househo#ds se#ected %. %. %. %. %. %. %. %. +, %. %. %. %. %. %. %. %. +, 10,

Secondary data relevant for the study were collected from the >irectorate of ,conomics and Statistics, 5overnment of Tamil Nadu and also from the offices of !oimbatore and Salem !orporations. 3.4 C# ssific tio$ of househo#ds The selected households were classified based on the monthly income of the household, religion and educational level of the head of the household. #ollowing 3ao "%?/1&, consumption units of the households were worked out as below, so as to facilitate comparison among households. T %#e 3."& Co$su'(tio$ u$its of househo#ds S#. No. %. 1. $. 6. @. 3.0 C te5o!ies Adult male above %6 years Adult female above %6 years !hild between %..% - %6 years !hild between - - %. years !hild below - years Co$su'(tio$ u$its %... ../$ ../$ ..:$ ..@.

Too#s of $ #ysis The analyses of the data were carried through conventional, tabular and functional

methods. 3.0.1 Fu$ctio$ # $ #ysis 'n order to assess the interrelationships between consumption of livestock products and the socio-economic and psychological factors, as described by >aisy 3ani "%??@&, three Semi-log functions, one each for milk, meat and eggs, were fitted. The functional forms were as belowA %nB% C D E F%G% E F1G1 E F$G$ E F6G6 E F@G@ E F-G- E F:G: E F/G/ E F?G? E F%.G%. E F%%G%% E H %nB1 C D E F%G% E F1G1 E F$G$ E F6G6 E F@G@ E F-G- E F:G: E F/G/ E F?G? E F%.G%. E F%%G%% E H %nB$ C D E F%G% E F1G1 E F$G$ E F6G6 E F-G- E F:G: E F/G/ E F?G? E F%.G%. E F%%G%% E H 2here, B% C Iuantity of milk consumed per household per month "in litres& B1 C Number of eggs consumed per household per month B$ C Iuantity of meat consumed per household per month "in kg&

G% C #amily si e in consumption units G1 C 8indu religion dummy "%-if 8induJ .-otherwise& G$ C !hristian religion dummy "%-if !hristianJ .-otherwise& G6 C ,ducational level of the head of the household ".-if 'lliterateJ %-if 4rimaryJ 1-if SecondaryJ and $-if college& G@ C #ood habit dummy "%-if Non-vegetarianJ .-otherwise& G- C 3egion dummy "%-if !oimbatoreJ .-otherwise& G: C !hild dummy "%-if family had child-below %6 yearsJ .-otherwise& G/ C Aged dummy "%-if family had aged person-above -. yearsJ .-otherwise& G? C +ow income dummy "%-if household income is less than 3s.%....J .-otherwise& G%. C ;iddle income dummy "%-if household income is 3s.%....-1....J .-otherwise& G%% C 4hysical e*ertion dummy "%-if family member does physical workJ .-otherwise& H C Stochastic disturbance term Fi C 3egression coefficients to be estimated D C 'ntercept 3.0." O!de!ed P!o%it 2ode# )rdered-response models recogni e the inde*ed nature of various response variablesJ in this study, consumers= preferences towards attributes of milk and meat quality were the ordered responses. 0nderlying inde*ing in such models is a latent, but continuous descriptor of the response. 'n an )rdered 4robit ;odel, the random error associated with this continuous descriptor is assumed to follow a normal distribution. 'n contrast to )rdered-response models, ;ultinomial +ogit and 4robit ;odels neglect the data=s ordinality, require estimation of more parameters "in the case of three or more alternatives, thus reducing the degrees of freedom available for estimation&, and are associated with undesirable properties, such as the independence of irrelevant alternatives in the case of a ;ultinomial +ogit "Ken-Akiva and +erman, %?/@& or lack of a closed-form likelihood as in the case of a ;ultinomial 4robit "5reene, 1...&. An individual consumers= utility function or preference ordering was hypothesi ed to be represented by consumers= importance ratings 3 "3C%-strongly noJ 3C1-noJ 3C$-slightly noJ 3C6-slightly yesJ 3C@-yesJ and 3C--strongly yes& on different milk and meat quality attributes. 3atings "3=s& are determined by a % * % vector "G& consisting of socio-economic, geographic and demographic factors of the representative household respondent "Table $.$&. T %#e 3.3& Desc!i(tio$ of 6 !i %#es used i$ O!de!ed P!o%it $ #ysis

E7(# $ to!y 6 !i %#es #amily si e Se* 8indu !hristian ,ducation #ood habit 3egion !hild Aged +ow income

8e6e#s !ontinuous ;aleJ #emale 8induJ Non-8indu !hristianA Non-!hristian #our

S(ecific tio$ !onsumption units in the household % L if maleJ . L otherwise % L if household is a 8induJ . L otherwise % L if household is a !hristianJ . L otherwise ,ducational level of the head of the household ". L if 'lliterateJ % L if 4rimaryJ 1 L if SecondaryJ and $ L if !ollege&

Non-vegetarianJ % L if Non-MegetarianJ . L otherwise Megetarian !oimbatoreJ % L if !oimbatoreJ . L otherwise Salem Two Two Two % L if family had child"ren&-below %6 yearsJ . L otherwise % L if family had aged person"s&-above -. yearsJ . L otherwise % L if household income is less than 3s.%....J . L otherwise % L if household income is 3s.%...%-1....J . L otherwise % L if respondent does physical workJ . L otherwise

;iddle income Two 4hysical e*ertion Two

The ordered probit models of this study were estimated using STATA ?.. N software packages. The following model specification was used hereA
Oz + TP = n n n

2here,
TP n

C latent and continuous measure of preference of the respondent n in the study, C a vector of e*planatory variables describing the respondent, C a vector of parameters to be estimated, and C a random error term "assumed to follow a standard normal distribution&.
TP n

The observed and coded discrete preference variable, model as belowA

was determined from the

Tn

%if TnP % " strongly no& P 1 if % Tn 1 "no& $ if T P " slightly no& 1 n $ C P 6 if $ Tn 6 " slightly yes& @ if T P " yes& 6 n @ P - if @ Tn - " strongly yes&

where, the i s represent thresholds to be estimated "along with the parameter vector &. The probabilities associated with the coded responses of an )rdered 4robit ;odel are as followsA
O O O Pn ".& =4r"Tn =.& =4r"TnP " % & =4r" z n +n % & =4r"n % z n & = % z n & O Pn "%& =4r"Tn = %& =4r" TnP 1 & = 4r"n 1 O z n & 4r"n % < % z n & O = " 1 O z n & " % z n &

..... Pn " k & =4r"Tn =k & =4r" k <TnP k +% & = " k +% O z n & " k O z n & ..... Pn " K & =4r"Tn =K & =4r" K <TnP & =% " K O z n &

where n is an individual, k is a response alternative, 4r"Tn =k & is the probability that the individual n responds in manner k, and ".& is the standard normal cumulative distribution function. The interpretation of this model=s primary parameter set, , is that positive signs indicate higher preference as the value of the associated variables increase, while negative signs suggest the converse. 3.0.3 F cto! A$ #ysis 'n addition to assessing the determinants of consumers= importance ratings for limited livestock products= attributes, #actor analysis was used to detect the interrelationships for consumer=s ratings "in si* point scale, as in )rdered 4robit analysis& among the detailed questions placed on attributes "Table $.6&. Thus, the #actor analysis used in this study identified the latent factors underlying important ratings "3& on the set of livestock products= attributes and e*plained the structure of importance ratings "3& on these selected products= attributes using the reduced number of latent factors "4eng et al., 1..@&. The following equation describes the #actor analysis model in a matri* formA
X " n %& = A" n m & F" m %&

2here,

<G= is the matri* of variablesJ <A= is the matri* of factor loadings "ai(&J <#= is the matri* of dimensionsJ <ai(= is the net correlation between (th dimension ith observed variableJ <n= is the number of variablesJ and <m= is the number of dimensions. #ollowing > iuban and Shirkey "%?:6&, the sampling adequacy was determined by the 9aiser-;eyer-)lkin "9;)& measure. According to them, the 9;) inde* in the ..?.s was <marvelous=, in the ../.s <meritorious=, in the ..:.s <middling=, in the ..-.s <mediocre=, in the ..@.s <miserable= and below ..@. <unacceptable=. The 4rincipal !omponent Analysis method was followed to e*tract dimensions and the initial orthogonal solution was rotated by the varima* method with 9aiser normalisation ">ave et al., 1..:&. T %#e 3.1& 8ist of f cto!s used fo! F cto! $ #ysis 2i#9 3u #ity tt!i%utes
8igh price is permeable for safety 8igh price is permeable for high sensory property 8igh SN# is important +ow fat is important !olour is important #eeding condition is important +ow price is important 5ood odour is important Te*ture is important 5ood taste is important Safety is important #reshness is important Shopping environment is important 5ood flavour is important 8omogeni ation is important 4asteuri ation is important 5ood packaging is important !ow milk is preferred Kuffalo milk is preferred ;ilking environment is important (R=1-strongly no R=!-no R="-slightly no R=#-slightly yes R=$-yes an% R=&-strongly yes'

2e t 3u #ity tt!i%utes
Tenderness is important 8igh price is permeable for safety 8igh cookery property "parts and form& is important 8igh price is permeable for high sensory property 3etail cut is important Ageing is important ;eat colour is important #eeding condition is important +ow price is important 5ood odour is important 7uiciness is important 5ood taste is important Safety is important +eanness is good #reshness is important Shopping environment is important

Você também pode gostar