Research Methodology - Dr. Krishan K. Pandey
Research Methodology - Dr. Krishan K. Pandey Research Methodology - Dr. Krishan K. Pandey
Sampling Fundamentals 173 We now illustrate the use of this formula by an example. Illustration 4 A market research survey in which 64 consumers were contacted states that 64 per cent of all consumers of a certain product were motivated by the product’s advertising. Find the confidence limits for the proportion of consumers motivated by advertising in the population, given a confidence level equal to 0.95. Solution: The given information can be written as under: n = 64 p = 64% or .64 q = 1 – p = 1 – .64 = .36 and the standard variate (z) for 95 per cent confidence is 1.96 (as per the normal curve area table). Thus, 95 per cent confidence interval for the proportion of consumers motivated by advertising in the population is: p ± z⋅ = . 64 ± 196 . pq n b gb g = . 64 ± 196 . . 06 b gb g 064 . 036 . 64 = . 64 ± . 1176 Thus, lower confidence limit is 52.24% upper confidence limit is 75.76% For the sake of convenience, we can summarise the formulae which give confidence intevals while estimating population mean bg μ and the population proportion bg $p as shown in the following table. Table 8.3: Summarising Important Formulae Concerning Estimation Estimating population mean p X ± z⋅ n σ bg μ when we know σ p Estimating population mean s X ± z⋅ n σ bg μ when we do not know σ p In case of infinite In case of finite population * population σ p X ± z ⋅ × n σ s X ± z⋅ × n N − n N − 1 N − n N − 1 ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ ○ Contd.
174 Research Methodology and use σ s as the best estimate of σ p and sample is large (i.e., n > 30) Estimating population mean X ± t ⋅ σ bg μ when we do not know σ p and use σ s as the best estimate of σ p and sample is small (i.e., n < 30 ) In case of infinite In case of finite population * population s n σ s X ± t ⋅ × n Estimating the population proportion bg $p when p is not known but the sample is large. p ± z ⋅ pq n p ± z⋅ pq n × N − n N − 1 N − n N − 1 * In case of finite population, the standard error has to be multiplied by the finite population multiplier viz., bN − ngbN −1 g . SAMPLE SIZE AND ITS DETERMINATION In sampling analysis the most ticklish question is: What should be the size of the sample or how large or small should be ‘n’? If the sample size (‘n’) is too small, it may not serve to achieve the objectives and if it is too large, we may incur huge cost and waste resources. As a general rule, one can say that the sample must be of an optimum size i.e., it should neither be excessively large nor too small. Technically, the sample size should be large enough to give a confidence inerval of desired width and as such the size of the sample must be chosen by some logical process before sample is taken from the universe. Size of the sample should be determined by a researcher keeping in view the following points: (i) Nature of universe: Universe may be either homogenous or heterogenous in nature. If the items of the universe are homogenous, a small sample can serve the purpose. But if the items are heteogenous, a large sample would be required. Technically, this can be termed as the dispersion factor. (ii) Number of classes proposed: If many class-groups (groups and sub-groups) are to be formed, a large sample would be required because a small sample might not be able to give a reasonable number of items in each class-group. (iii) Nature of study: If items are to be intensively and continuously studied, the sample should be small. For a general survey the size of the sample should be large, but a small sample is considered appropriate in technical surveys. (iv) Type of sampling: Sampling technique plays an important part in determining the size of the sample. A small random sample is apt to be much superior to a larger but badly selected sample.
- Page 140 and 141: Processing and Analysis of Data 123
- Page 142 and 143: Processing and Analysis of Data 125
- Page 144 and 145: Processing and Analysis of Data 127
- Page 146 and 147: Processing and Analysis of Data 129
- Page 148 and 149: Processing and Analysis of Data 131
- Page 150 and 151: Processing and Analysis of Data 133
- Page 152 and 153: Processing and Analysis of Data 135
- Page 154 and 155: Processing and Analysis of Data 137
- Page 156 and 157: Processing and Analysis of Data 139
- Page 158 and 159: Processing and Analysis of Data 141
- Page 160 and 161: Processing and Analysis of Data 143
- Page 162 and 163: Processing and Analysis of Data 145
- Page 164 and 165: Processing and Analysis of Data 147
- Page 166 and 167: Processing and Analysis of Data 149
- Page 168 and 169: Editing Coding Processing of Data (
- Page 170 and 171: Sampling Fundamentals 153 1. Univer
- Page 172 and 173: Sampling Fundamentals 155 should no
- Page 174 and 175: Sampling Fundamentals 157 certain l
- Page 176 and 177: Sampling Fundamentals 159 (i) Stati
- Page 178 and 179: Sampling Fundamentals 161 (ii) To t
- Page 180 and 181: Sampling Fundamentals 163 2 (ii) Sq
- Page 182 and 183: Sampling Fundamentals 165 (ii) Stan
- Page 184 and 185: Sampling Fundamentals 167 σ s 1⋅
- Page 186 and 187: Sampling Fundamentals 169 mean is c
- Page 188 and 189: Sampling Fundamentals 171 08 . = ×
- Page 192 and 193: Sampling Fundamentals 175 (v) Stand
- Page 194 and 195: Sampling Fundamentals 177 where N =
- Page 196 and 197: Sampling Fundamentals 179 Since $p
- Page 198 and 199: Sampling Fundamentals 181 (i) Find
- Page 200 and 201: Sampling Fundamentals 183 25. A tea
- Page 202 and 203: Testing of Hypotheses I 185 Charact
- Page 204 and 205: Testing of Hypotheses I 187 when th
- Page 206 and 207: Testing of Hypotheses I 189 Mathema
- Page 208 and 209: Testing of Hypotheses I 191 PROCEDU
- Page 210 and 211: Testing of Hypotheses I 193 MEASURI
- Page 212 and 213: Testing of Hypotheses I 195 We can
- Page 214 and 215: Testing of Hypotheses I 197 HYPOTHE
- Page 216 and 217: 1 2 3 4 5 z OR X − X 1 2 2 2 p p
- Page 218 and 219: 1 2 3 4 5 z = p q 0 0 p$ − p$ F H
- Page 220 and 221: Testing of Hypotheses I 203 to have
- Page 222 and 223: Testing of Hypotheses I 205 S. No.
- Page 224 and 225: Testing of Hypotheses I 207 S. No.
- Page 226 and 227: Testing of Hypotheses I 209 nX + nX
- Page 228 and 229: Testing of Hypotheses I 211 (Since
- Page 230 and 231: Testing of Hypotheses I 213 Table 9
- Page 232 and 233: Testing of Hypotheses I 215 σ diff
- Page 234 and 235: Testing of Hypotheses I 217 Solutio
- Page 236 and 237: Testing of Hypotheses I 219 Hence t
- Page 238 and 239: Testing of Hypotheses I 221 of succ
174 <strong>Research</strong> <strong>Methodology</strong><br />
and use σ s as the best estimate<br />
of σ p and sample is large (i.e.,<br />
n > 30)<br />
Estimating population mean X ± t ⋅ σ<br />
bg μ when we do not know σ p<br />
and use σ s as the best estimate<br />
of σ p and sample is small (i.e.,<br />
n < 30 )<br />
In case of infinite In case of finite population *<br />
population<br />
s<br />
n<br />
σ s<br />
X ± t ⋅ ×<br />
n<br />
Estimating the population<br />
proportion bg $p when p is not<br />
known but the sample is large.<br />
p ± z ⋅<br />
pq<br />
n<br />
p ± z⋅<br />
pq<br />
n<br />
×<br />
N − n<br />
N − 1<br />
N − n<br />
N − 1<br />
* In case of finite population, the standard error has to be multiplied by the finite population multiplier viz.,<br />
bN − ngbN −1<br />
g .<br />
SAMPLE SIZE AND ITS DETERMINATION<br />
In sampling analysis the most ticklish question is: What should be the size of the sample or how large<br />
or small should be ‘n’? If the sample size (‘n’) is too small, it may not serve to achieve the objectives<br />
and if it is too large, we may incur huge cost and waste resources. As a general rule, one can say that<br />
the sample must be of an optimum size i.e., it should neither be excessively large nor too small.<br />
Technically, the sample size should be large enough to give a confidence inerval of desired width and<br />
as such the size of the sample must be chosen by some logical process before sample is taken from<br />
the universe. Size of the sample should be determined by a researcher keeping in view the following<br />
points:<br />
(i) Nature of universe: Universe may be either homogenous or heterogenous in nature. If<br />
the items of the universe are homogenous, a small sample can serve the purpose. But if the<br />
items are heteogenous, a large sample would be required. Technically, this can be termed<br />
as the dispersion factor.<br />
(ii) Number of classes proposed: If many class-groups (groups and sub-groups) are to be<br />
formed, a large sample would be required because a small sample might not be able to give<br />
a reasonable number of items in each class-group.<br />
(iii) Nature of study: If items are to be intensively and continuously studied, the sample should<br />
be small. For a general survey the size of the sample should be large, but a small sample is<br />
considered appropriate in technical surveys.<br />
(iv) Type of sampling: Sampling technique plays an important part in determining the size of the<br />
sample. A small random sample is apt to be much superior to a larger but badly selected<br />
sample.