 और देटा अपाज़ी इस थी रब खीबोग़ा नहीं और और उगादे लगादा वहते हैं ज़े वहाँ रब देटा, भी ठीटा सोगा देटा कुई आगमने देटा मग़े लगी और तीटा नहीं रब भी और शापचा, बे अदे लेग काई देटा एक देटा रब पीच्त Which is a fiftieth percentile and it divides the data into two equal parts. So regardless क Uganda kyaالके द Ehta mein extreme values हैं یे लहा recycled less thatrooms extreme values hai Hai it will exactly find the center of the data is last example mein baat ki if my data main values 1, 2, 3, 4 or 50 hain tawis engil id you call called symbol on 50 still it is the central value of the data वटूगगछ़ी यह देटा करा तो आप थी. तो आप वाईढ़ tenen pe chaha hai 5,000 dal de, या वाईबईटिन लीची आप मेटिन मेटिनूछ आप थी वटूगगछ थी. वाईछ़ी बाईटी लीची तो ज्फाजगखखगजगखखो।. कुकिं, कि मुटट आड़ारती अग़ वpound कच्सरा अएसी येन्पे है, तो डीब तो वान और 2 अग फिव एकष्च्टीम वलूए, हाँ मसको, और जंब कर कि मुछ्ट आगे चलेट हो जाएगीगागी, अआमसоре आप वो ज़ान गध्याड़ जी जी तोईतर छोड़ें, दोईतर छोड़ें। अजी भी आपने भी वहामते गुए anywhere खाछ उस देखॉरी आप वी कोंबाप्णाद. अजी वान का पास में यहाहो न तो वोजारना ती राकनापार लोगता। 13 20 50 and then we will find the center of the distribution which is 13. This is the way how we find median for the ungrouped data and this is an example. अगर हमारे पास, values even numbers में हो, yani odd में तो हम simple कर लेते हैं, कि तो हम एदर चोड दें, तो हो एदर चोड दें, अगर में अफहि पास थीम है, अगर मेरे लेत्सामने आप चूड़ंस बटे हो ते अब आप लोग रिल में, अगर में अप देखने आशक यूँ तो कल्डिलेट योस्ट्ट बिक्र रहाँ है, यहनी क्लास्ग आद खुभत्तार, lime, 50th percent of the score. तो आप मेरे वोट हुट प्लागएन वैलूँँस कर है. And the then we will plug-in values अशकिनधय मेंगे अनगो अचानगेंगें वित्योग कर लोगाएन भी में. and we will find the median within that. जबने लिएट है, उगर मेरे सामने स्वोग्डिति सब आप लोग रील्में नहीं। यह आप इसक्वीड़ी आप लगा लिएद पहले टी तो अप लगा लिएद लिएद़ लेगे ती, 25, this is a rank, this is a position, I have to find out किसके अपर कुन्सी वेल्यो परी ये, so 25 is in this, इसके अंदर होगा, so this is our model class. आपने अपनी model class identify कर लिए this is step one क्या आपने अपना 50th percentile निकाल के model class identify की और उसकी real limits आपने देखनी now you will plug in the values in the formula, which is L plus N by 2 minus Cf multiplied by class interval, और आपने वेल्यो जब प्लागिन करेंगे, तो मैंने lower limit लेके, उसके बाद हम ने ये निकाला है N by 2 which is 25, ये मैंने calculate already किया यहांपे, और फिर मैंने इसके नीचे वली cumulative frequency below the model or proceeding class क्या बले लिते हैं, अगर data अपका sending, descending में, तो 24 is the frequency below, अं आदम हमारा जो है, उसकी model class क्या त्रीज्वेएंचे अचा सतर हैं, और फिर उसका जो जो मारा class interval है, यह यह लोस की 10. �今 म saborा चलकड़्या है, खर की Its class interval is also 10. तो मेंने ड़ाकिन और प्लगा है, चरते भी एचे चालकलगत ऴिदियन कार, So, our 50th percentile which is median which is central value which divides the data into two equal parts. What are the benefits of median? As I have told you, we use extreme scores. Similarly, if someone asks me how much are the average salaries in your office. So, we have two people who are working on a kind of high rank whose salaries are in six digits. And then we have staff in which mostly our research assistants or our staff whose salaries are mostly between 10 to 20,000. So, only two people have a six digit salary as compared to other 15 people who are working under two of us who have salary between 10 to 20,000. Below 20,000 are their salary. So, if someone asks me what are the average salary you give them. So, maybe median is an appropriate measure to report rather than mean. Because mean will come forward by collecting those two big salaries which would not be appropriate. So, what are the data sets where we require median. But it is you who will decide how we will choose mean or median. Thirdly, our central tendency is mod. We basically use mod when we have nominal data or ordinal data or categorical data. Then we use mod. Mod is basically the most frequently occurring value in the data. And it also gives us information about central value or center of the data. Just as this is an example, if you have ungrouped data, then the most frequently occurring value that will be the mod. For example, 1, 3, 4, 4, 5, 5, 6, 7, 7. So, the value which is occurring most is 5. It is occurring three times. So, in this data mod will be 5. Similarly, even in group data, mod is easy to find out. And even you can see it from a graphical distribution. Because wherever the peak of the distribution is formed, that will be the mod value. Because peak of the distribution corresponds to the frequency. So, frequency means that the highest number of individuals are present in this group. So, you can also find out mod from it. But as I said that mod is mostly for categorical variables or nominal or ordinal data. Just like a small survey we have done in the class, asking the fast food choices of students, what they prefer. In that you can see that KFC 20 people preferred, McDonald's was choice of 25 people, Burger King 8 people preferred that, Subway 12 and Hardee's 15. So, now we have to find out what is the most favorite food of students among the fast food given. So, maybe our McDonald's is an answer because most people, majority or maximum people, or the group with the most occurring frequencies are your McDonald's. So, we have a favorite fast food answer. If we have to take out the central value, then we will take out the mod in it. Similarly, we have a lot of examples in our daily life, where we need a lot of mod. And it is very useful to calculate mod. For example, if a designer makes shoes, or any shoe seller, any brand or any shoe maker, how they will order which number of pairs to be made. So, mod actually gives them information. For example, if we look at all the women, then 5, 6 sizes will be of women, and 10, 11 will also be of women. Majority of people will have shoe size, 8, 7, 8. Similarly, when they order or make shoes, then they will make smaller or bigger numbers, but mostly he will order 7 or 8 numbers shoes Similarly, when we take the example of dress designing, your medium size will be more, compared to extra large or extra small. So, mod gives us a lot of... If I am a dress designer and I have to launch a winter collection for the next month, then maybe I can do a quick survey on which colors young girls will prefer for the winter for December-January. So, mod color, which mod is more modern, modern means that the majority of people will like it, maybe I will focus on that color more so people what they like, I will deliver more of that. So, this is pretty much about mod and it is also a formula for group data, but I will prefer to calculate it in SPSS, but you should understand when, where and why we should prefer one central tendency mayor over other mayors, which we will discuss in next module.