সেশন ৪/৩০

Numerical Data-র বর্ণনা

মাঝখানটা কোথায়, ছড়িয়ে আছে কতটা, আর কোন জোড়া সংখ্যা ছাপবেন

১২০ মিনিট · ৬টি পর্বে ৩৭টি স্লাইড · স্লাইড ও নোট ইংরেজিতে

৩টি স্লাইড

Orientation

  1. Session 4 title slide: Describing Numerical Data.

    স্লাইড ১

    Describing Numerical Data

  2. Slide comparing a Sylhet survey table that prints medians with a COBRA-BPS table that prints means.

    স্লাইড ২

    Two Good Papers, Two Opposite Habits

    The session opens on a puzzle, not a definition. Same kind of thing, numbers measured on people, and opposite conventions. Somebody decided. On what?

  3. Session 4, Orientation: What you will be able to do at the end of today.

    স্লাইড ৩

    What you will be able to do at the end of today

৮টি স্লাইড

Act I · Where the Middle Is

  1. Session 4, Act I · Where the middle is: Act I · Where the middle is.

    স্লাইড ৪

    Act I · Where the Middle Is

  2. Slide distinguishing mean, median, and mode as three different middles.

    স্লাইড ৫

    Three middles, and they answer different questions

    Mean, median, and mode are not three ways to say ‘average.’ They answer three different questions about the same column. The rest of the afternoon is about which question a paper is allowed to ask.

  3. Session 4, Act I · Where the middle is: One value moves, and only one of them moves with it.

    স্লাইড ৬

    One value moves, and only one of them moves with it

  4. Session 4, Act I · Where the middle is: Trimming the ends, and the summary that survives it.

    স্লাইড ৭

    Trimming the ends, and the summary that survives it

  5. Session 4, Act I · Where the middle is: The spread that matches the median.

    স্লাইড ৮

    The spread that matches the median

  6. Session 4, Act I · Where the middle is: So the gap between them describes the shape.

    স্লাইড ৯

    So the gap between them describes the shape

  7. Slide showing why the mean of a column with a floor at zero can be a fiction.

    স্লাইড ১০

    A column with a floor, and why its mean would be a fiction

    Years of schooling, counts, anything that cannot go below zero: the mean can sit in a place no person occupies. That is already enough to prefer a median, before anyone has drawn a histogram.

  8. Session 4, Act I · Where the middle is: Reading a median off a table you did not collect.

    স্লাইড ১১

    Reading a median off a table you did not collect

১১টি স্লাইড

Act II · How Spread Out It Is

  1. Session 4, Act II · How spread out it is: Act II · How spread out it is.

    স্লাইড ১২

    Act II · How Spread Out It Is

  2. Session 4, Act II · How spread out it is: Means do pool, if you weight them.

    স্লাইড ১৩

    Means do pool, if you weight them

  3. Session 4, Act II · How spread out it is: A center on its own describes almost nothing.

    স্লাইড ১৪

    A center on its own describes almost nothing

  4. Session 4, Act II · How spread out it is: Quartiles, and the middle half of the data.

    স্লাইড ১৫

    Quartiles, and the middle half of the data

  5. Session 4, Act II · How spread out it is: Quartiles are percentiles, and you already read those.

    স্লাইড ১৬

    Quartiles are percentiles, and you already read those

  6. Session 4, Act II · How spread out it is: The five-number summary, as a reporting standard.

    স্লাইড ১৭

    The five-number summary, as a reporting standard

  7. Session 4, Act II · How spread out it is: The standard deviation, in the units of the thing measured.

    স্লাইড ১৮

    The standard deviation, in the units of the thing measured

  8. Session 4, Act II · How spread out it is: Spread as a share of size.

    স্লাইড ১৯

    Spread as a share of size

  9. Session 4, Act II · How spread out it is: Where the standard deviation comes from, without the algebra.

    স্লাইড ২০

    Where the standard deviation comes from, without the algebra

  10. Session 4, Act II · How spread out it is: Two groups, two spreads, and what that tells you.

    স্লাইড ২১

    Two groups, two spreads, and what that tells you

  11. Slide distinguishing standard deviation from standard error.

    স্লাইড ২২

    Standard deviation is not standard error

    One describes how spread out the people are. The other describes how unstable the mean would be in another sample. Mixing them is the most expensive confusion in a Table 1, and it is named here so Session 7 can own the second one properly.

৮টি স্লাইড

Act III · Choosing, and the Answer to the Puzzle We Opened With

  1. Session 4, Act III · Choosing, and the answer to the puzzle we opened with: Act III · Choosing, and the answer to the puzzle we opened with.

    স্লাইড ২৩

    Act III · Choosing, and the Answer to the Puzzle We Opened With

  2. Session 4, Act III · Choosing, and the answer to the puzzle we opened with: A change is a column too, and it has its own center and spread.

    স্লাইড ২৪

    A change is a column too, and it has its own center and spread

  3. Slide showing that the choice of mean or median can be audited from the printed table alone.

    স্লাইড ২৫

    You can audit the choice from the printed table alone

    You do not need the dataset. If a paper prints a mean and an SD for a column that must be skewed, the choice is already visible. Reading becomes checking, not trusting.

  4. Slide asking why the Sylhet paper never printed a mean.

    স্লাইড ২৬

    So why did the Sylhet paper never print a mean?

    The question the opening slide withheld. The answer is the shape of the columns, not a house style. Once you can see that from the printed numbers, you can say why a careful paper made the choice it made.

  5. Session 4, Act III · Choosing, and the answer to the puzzle we opened with: Reconstructing a mean you were never given.

    স্লাইড ২৭

    Reconstructing a mean you were never given

  6. Slide stating a short rule for choosing a mean or a median.

    স্লাইড ২৮

    The rule, and it is shorter than the discussion

    Mean and SD when the column can support them. Median and IQR when it cannot. The long discussion exists so the short rule is believed, not so it can be replaced by a slogan.

  7. Slide on what to print and in what form.

    স্লাইড ২৯

    What to print, and in what form

    Precision, units, and the digits you are entitled to. A summary that cannot be true is worse than no summary. Session 5 then owns the shape behind the choice; today only decides which pair of numbers leaves the room.

  8. Session 4, Act III · Choosing, and the answer to the puzzle we opened with: Precision, units, and the digits you are entitled to.

    স্লাইড ৩০

    Precision, units, and the digits you are entitled to

৫টি স্লাইড

Act IV · When One Number Will Not Do the Job

  1. Session 4, Act IV · When one number will not do the job: Act IV · When one number will not do the job.

    স্লাইড ৩১

    Act IV · When One Number Will Not Do the Job

  2. Session 4, Act IV · When one number will not do the job: Summaries that cannot be true.

    স্লাইড ৩২

    Summaries that cannot be true

  3. Session 4, Act IV · When one number will not do the job: When the summary is the wrong object entirely.

    স্লাইড ৩৩

    When the summary is the wrong object entirely

  4. Session 4, Act IV · When one number will not do the job: The third option, and it is no longer deferred.

    স্লাইড ৩৪

    The third option, and it is no longer deferred

  5. Session 4, Act IV · When one number will not do the job: Common traps, collected.

    স্লাইড ৩৫

    Common traps, collected

২টি স্লাইড

Close

  1. Session 4, Close: Close.

    স্লাইড ৩৬

    Close

  2. Session 4, Close: Before the next session.

    স্লাইড ৩৭

    Before the next session

নাম বলে রেখে দেওয়া

যা ইচ্ছে করেই এখনো পড়াইনি

  • একটা কলামের Shape, আর কখন সেটা যথেষ্ট Skewed (সেশন ৫)।
  • Standard Error ও Sampling Variability (সেশন ৭)।
  • Outlier ধরার 1.5 × IQR নিয়ম (সেশন ৫)।

এরপর কী আসছে

সেশন ৫: Distribution ও Outlier বোঝা

পরের সেশনগুলো পরিকল্পনায় আছে, তবে সাইটে দেওয়া হয়নি। নিজের কাজের জন্য এমন ক্লাস চাইলে একটা প্ল্যান চেয়ে নিন।

সিলেবাসে ফিরে যান লার্নিং প্ল্যান চেয়ে নিন
Stat.BD