Slstats

07/02/2026

5. Drawing a biased sample

📊 “Our analysis shows Party A is the most popular!” ✅
Sounds convincing… right? 🤔
Look at how the data was collected.
❓ The real question:
👤 Who chose the sample—and from where?
📌 What actually happened (example):
The invigilator collected responses based on personal preference:
🏘️ Surveyed only areas known to support Party A
👥 Asked friends/contacts who already like Party A
🚪 Skipped neighborhoods that prefer other parties
➡️ The sample was not neutral. The result was pre-decided.
⚠️ This is drawing a biased sample.
When the selection is tilted,
📉 Statistics lose accuracy
📊 Results echo the collector’s desire
⚖️ It reflects bias, not reality
🚨 Selecting samples in favour of a party = Misuse of statistics
✅ Honest analysis needs:
• Neutral selection
• Diverse respondents
• Fair coverage areas
❌ Biased inputs = Biased outputs
💡 Trust data that’s fairly collected—not data that flatters a preference.
Always ask: How was the sample chosen?

07/02/2026

4. Making recommendations without using a sufficient and unbiased sample

💊 “This drug is recommended by 80% of doctors!” ✅
Sounds trustworthy… right? 🤔
Look closer.
❓ Ask the key question:
👨⚕️👩⚕️ How many doctors were consulted?
📌 The actual situation:
Only 5 doctors were asked.
✅ 4 recommended the drug.
So yes… mathematically,
📊 4 out of 5 = 80%
But does this mean the drug is widely recommended by doctors in general? ❌
⚠️ This is making recommendations using an insufficient and biased sample.
📉 A tiny sample creates misleading percentages
📊 Numbers look strong, but evidence is weak
⚖️ Reliable recommendations need broad, unbiased opinions
🚨 Small sample + Big claim = Misuse of statistics
✅ Medical recommendations require
• Large samples
• Diverse representation
• Careful interpretation
❌ Percentages alone should never drive health decisions
💡 Good statistics protect people.
Bad statistics persuade them.

07/02/2026

3. Making bias interpretation for statistical data

📣 “A survey says Candidate X is winning!”
Sounds convincing… doesn’t it?
🤔 But wait—
Did anyone ask:
📍 Where was the survey conducted?
If the sample is taken only from areas favourable to Candidate X:
🏘️ One-sided locations
👥 Like-minded voters
📍 Limited coverage
➡️ The result is already biased.
📊 Statistics are only as fair as the sample.
When selection isn’t balanced, numbers stop telling the truth.
⚠️ Biased interpretation = misuse of statistics
⚖️ Fair sampling > fancy percentages
❌ Numbers without context can mislead minds
💡 Statistics need fairness, not favoritism.
Always question where the data comes from
— before believing what it claims.
📊 Numbers can look powerful,
but how they’re collected matters more than what they show.
✅ Think critically. Question the data.

07/02/2026

2.Using Insufficient data for making comparisons

📊 “Company Y earns more than Company X!”
Company X profit: Rs. 100,000
Company Y profit: Rs. 150,000
So… does that mean Company X performs worse? 🤔
Not necessarily.
❓ Ask the important question first:
📦 How large is each business?
A small scale company earning Rs. 100,000
vs
a large scale company earning Rs. 150,000
➡️ The smaller company might actually be more efficient and stronger.
⚠️ This is using insufficient data for comparison.
📉 Profit without business volume = incomplete picture
📊 Bigger numbers don’t always mean better performance
⚖️ Fair comparison needs proper context
🚨 Insufficient data = Misuse of statistics
✅ Real analysis looks at scale, volume, efficiency, and costs
❌ Comparing numbers alone can lead to false conclusions
💡 Statistics should inform decisions, not mislead them.
Always ask for the full story behind the numbers.

07/02/2026

07/02/2026

1. Falsely interpretation of the results of an analysis

📊 A statistic says: “This school has a 66% university entrance rate!” 🎉
Impressive… right? 🤔
Not always.
Ask the missing question:
👥 How many students sat for the exam?
🎓 The reality:
Only 3 students sat for the A/L exam.
✅ 2 got selected to university.
So yes… mathematically,
📈 2 out of 3 = more than 66%
But does this truly mean the school has a high university entrance rate? ❌
⚠️ This is false interpretation of results.
📉 Small numbers give big percentages
📊 Percentages without context mislead conclusions
⚖️ Results need proper explanation, not exaggeration
🚨 False interpretation = Misuse of statistics
✅ Statistics must be read with context and scale
❌ Percentages alone can distort reality
💡 Always look beyond the percentage.
Understanding numbers is more important than admiring them.

16/10/2024

Advanced Level

Business Statistics

Medium-(English/Sinhala)

For more details
Whatsapp- 0763612534

13/10/2024

වෙන් රූප සටහන් මගින් සිද්ධි නිරූපණය කිරීම

06/10/2024

01/07/2024

https://youtu.be/EZ7P7VOGd9E

සමූහිත සංඛ්‍යාත ව්‍යාප්තියක මාතය (දෙවන පාඩම)අලුතින් ආරම්භ වෙන A/L Statistics class එකට සම්බන්ධ වීමට WhatsApp පණිවිඩයක් පහත අංකයට ය.....

29/06/2024

https://youtu.be/c1cbf3IQFLg?si=CVbLwWPFfe3K66mb

මාතය - උසස් පෙල ව්‍යාපාර සංඛ්‍යානය (පලමු පාඩම)අලුතින් ආරම්භ වෙන A/L Statistics class එකට සම්බන්ධ වීමට WhatsApp පණිවිඩයක් පහත අංකයට ය.....