Data collection — primary vs secondary, tally charts, frequency tables

1.3.1 · Maths › Basic Data & Probability

Primary vs Secondary Data

[!definition] Primary Data

Primary data woh information hoti hai jo aap khud, firsthand, ek specific purpose ke liye collect karte ho.

• Examples: Apne classmates se favorite subjects ke baare mein survey karna, apne garden mein plants ki height measure karna, apne thermometer se daily temperatures record karna
• Primary kyun? Aap quality control karte ho, exactly jaante ho kaise gather kiya gaya, aur yeh AAPKE specific question ka jawab deta hai
• Collect kaise karein: Surveys, experiments, observations, measurements

[!definition] Secondary Data

Secondary data woh information hoti hai jo kisi aur ne pehle se collect ki hui hoti hai, jise aap apne analysis ke liye use karte ho.

• Examples: Government websites se census data, meteorological departments se rainfall records, school archives se historical test scores
• Secondary kyun? Time aur resources bachata hai; aise large-scale data tak access deta hai jo aap akele collect nahi kar sakte
• Access kaise karein: Published reports, databases, research papers, websites

Tally Charts

[!definition] Tally Chart

Ek tally chart marks (tallies) use karta hai real-time mein observations count karne ke liye jaise aap unhe collect karte ho. Har tally ek occurrence represent karta hai. Har paanchwa tally pehle chaar ko cross karta hai: |||| jo counting ke liye 5 ke groups banata hai.

Tally Charts kyun?

1. Real-time recording: Events hote hi tallies mark karo (yaad rakhne ki zaroorat nahi)
2. Error reduction: 5s mein grouped → counting mistakes kam
3. Visual clustering: Jaldi dekh sako kaun si category mein zyada marks hain

Tally Chart kaise banayein

Step-by-step derivation zaroorat se:

1. Categories identify karo: Aap kya count kar rahe ho? (cars ke colors, survey responses, dice rolls)
2. Do columns draw karo: Category | Tally
3. Jab bhi koi observation ho, corresponding row mein EK tally mark add karo
4. Har 5th mark pehle 4 ko cross karta hai: |||| (yeh key convention hai)
5. Ant mein tallies count karo: Har |||| = 5, baaki marks alag se

Frequency Tables

[!definition] Frequency Table

Ek frequency table data ko summarize karta hai har category aur uski frequency (count) list karke. Yeh tally chart ka final cleaned version hota hai, jisme tallies ki jagah numbers hoti hain.

Structure:

Frequencies kyun? Numbers ko tallies se zyada jaldi analyze kiya ja sakta hai. Ab aap percentages calculate kar sakte ho, categories ko quantitatively compare kar sakte ho, aur mode (sabse common value) dhundh sakte ho.

Tally Chart se Frequency Table derive karna

Diya gaya: Grouped marks ke saath ek tally chart
Goal: Numeric frequency mein convert karna

Formula (simple lekin explicit): $\text{Frequency}=(\text{Number of complete groups of 5})\times 5+\text{Remaining tallies}$

Frequency Tables ko Extend karna: Additional Columns

Real-world frequency tables mein aksar derived columns hote hain:

Cumulative Frequency

Cumulative frequency frequencies ka running total hota hai.

Formula: ${\text{Cumulative Freq}}_i={\sum }_{k=1}^i{f}_k$

Kyun? Aisa sawaal answer karta hai jaise "Kitne students ne 70 tak score kiya?" ya "Median position kya hai?"

Relative Frequency (Proportion)

Relative frequency counts ko proportions ya percentages mein convert karta hai.

Formula: $\text{Relative Freq}=\frac{f_i}{\sum f}\text{or as percentage:}\frac{f_i}{\sum f}\times 100\%$

Kyun? Alag-alag sizes ke datasets ke beech comparison allow karta hai. "11 out of 23" ko "15 out of 50" se compare karna mushkil hai, lekin 47.8% vs 30% turant clear hai.

[!mistake] Common Mistakes (aur yeh sahi kyun lagte hain)

Mistake 1: Har 5th tally cross karna bhool jaana

Galat: ||||||||| (10 individual marks)
Steel-man: Aise lagtaa hai ki bina cross kiye marks draw karte rehna zyada fast hai.
Yeh kyun fail hota hai: 50+ tallies ke saath, aap galat count karoge. Aankhen randomly bane marks ko reliably group nahi kar sakti.
Fix: Har 5th mark hamesha cross karo. |||| ke groups instantly 5 ke roop mein pehchane jaate hain.

Mistake 2: Secondary data ko hamesha reliable maanna

Galat assumption: "Yeh published hai, toh perfect hai."
Steel-man: Published data authoritative aur official lagta hai.
Yeh kyun fail hota hai: Secondary data mein collection bias, outdated methods, ya errors ho sakte hain. Aapne collection witness nahi kiya.
Fix: Source ki credibility, methodology, aur date check karo. Secondary data use karte waqt limitations note karo.

Mistake 3: "Total" row bhool jaana

Galat: Total sum row ke bina frequency table.
Steel-man: Individual frequencies complete lagti hain.
Yeh kyun fail hota hai: Total ke bina aap correctness verify nahi kar sakte ya relative frequencies calculate nahi kar sakte.
Fix: Hamesha ek Total row add karo: $\sum f$. Ise apni counting check karne aur percentages ke liye denominator ki tarah use karo.

Mistake 4: Primary aur secondary data ko bina distinction ke mix karna

Galat: Apna survey data + government census data ek dataset mein bina sources label kiye use karna.
Steel-man: "Yeh sab ek hi topic ke baare mein data hai."
Yeh kyun fail hota hai: Alag collection methods = alag reliability aur potential bias. Aapka analysis credibility kho deta hai.
Fix: Clearly label karo kaun sa data primary hai, kaun sa secondary hai, aur koi bhi methodological differences note karo.

[!recall]- Feynman Explanation (Ek 12-saal ke bachche ko explain karo)

Socho tum ek cricket match mein ho aur count karna chahte ho ki har batsman ne kitni baar four maara aur kitni baar six. Tum har shot yaad karne ki koshish kar sakte ho, lekin bhool jaoge!

Isliye tum ek tally chart banate ho: jab bhi four hoti hai, tum "Fours" row mein ek chhoti mark | banate ho. Chaar marks ke baad, agla mark unhe cross karta hai |||| toh ek bundle of 5 ek nazar mein dikh jaata hai. Yeh lakdiyon ko bundle karne jaisa hai — loose lakdiyon se kahin zyada aasaan count karna.

Match ke end mein, tum bundles count karte ho: 3 bundles of 5 = 15, plus 2 extra marks = 17 fours. Ab tum "17" ek clean table mein likhte ho jise frequency table kehte hain. Yeh tumhari final report hai!

Primary vs Secondary data: Agar TUM stadium mein baith ke count kiya, toh yeh primary hai (tumne kaam kiya). Agar tumne kisi ki banai scorecard online padhi, toh yeh secondary hai (tum unka kaam borrow kar rahe ho). Dono useful hain, lekin fark jaanna tumhe apne project ke liye sahi data par trust karne mein madad karta hai.

[!mnemonic] Memory Aids

TALLY = Take A Look, Lines Yield (5 lines ke groups tumhe jaldi totals dete hain)

Primary = Personal Recollection (data collection ke liye tum Present ho)
Secondary = Someone Else's Collection (pehle se kahi Stored hai)

Frequency Table columns mnemonic: "CFRF" → Category, Frequency, Relative Freq (Common Full Reporting Format)

Connections

• Pictorial representation — bar charts and pictograms — Frequency tables numerical base hain; bar charts unka visual translation hain
• Measures of central tendency — mean median mode — Mode woh category hai jisme aapki table mein sabse zyada frequency ho
• Grouped data and class intervals — Jab data mein bahut saari values ho, aap ranges mein group karte ho (frequency tables extend karke)
• Probability from frequency — experimental vs theoretical — Relative frequency experimental probability ban jaati hai
• Sampling methods — Primary data collection proper sampling follow karni chahiye representative hone ke liye

#flashcards/maths

Concept Map