Interactive Lessons

Confidence intervals

Lecture notes

Definition

One number is not enough

A sample gives one number, such as the sample share , to estimate the true value. A point estimate is only that one number: another random sample gives another one, and nothing in the number tells how far from the truth it may be. An interval estimate gives a range of values instead: the estimate with a margin that says how much it can vary.
0.40.50.60.7
Example
Three random polls of 100 voters about the same plan give , and . They differ by up to , and no one of them is “the” answer. An interval such as says how far the true share can lie from .
Definition

The confidence interval

A confidence interval is a range of values built from a random sample by a method that captures the true value in a stated share of all such samples. That share is the confidence level, for example 95%. The interval has the form estimate margin of error: its ends are and , where the margin of error is half of the width of the interval.
0.400.480.560.640.720.46270.6573
Example
In a random sample of 100 voters 56 back a plan, so . The 95% interval is .Its centre is , its width is and its margin of error is .
Rule

Where the form comes from

For a random sample the sample share is close to normal, with mean and standard deviation (the sampling distribution). In 95% of random samples lies within of these standard deviations of . Then also lies within that distance of : the interval around holds . That is the whole idea of the interval.
95%0.350.40.450.50.550.60.65
Example
Take and : the standard deviation of is and .So the middle 95% of the sample shares lie from to .
Rule

The standard error of the sample share

The true is not known, so the standard deviation of cannot be worked out. The standard error puts in its place: SE = \sqrt{\dfrac{\hat p (1 - \hat p)}{n}}. It estimates how far a sample share typically lies from , and it falls when grows.
Example
With and : , ..
Rule

The critical value z*

The critical value cuts off the middle area of the standard normal curve, the level of the interval, and leaves in each tail. Learn the three common ones: : ; : ; : . For any other level use invNorm on the calculator: the area to the left of is .
95%2.5%2.5%−1.96−3−2−10123
Example
Level 95%: each tail holds , so the area to the left of is .. In the same way for 90% (left area ) and for 99% (left area ).
Tip

The Dutch factor 2

The Dutch formula list writes the 95% interval with the rounded factor 2: . The factor 2 is a little more than , so the interval is a little wider. Use it when a task says “with the factor 2”, only at the level 95%; in every other case use the exact .
0.440.500.560.620.680.46270.65731.960.46070.65932
Example
For 56 of 100: , so the interval is .With it was : the factor 2 is larger than and the margin grows from to .
Rule

The interval for a proportion, step by step

Four steps. (1) The sample share . (2) The standard error . (3) The margin of error . (4) The ends and . The calculator does all four at once: on a TI.
0.400.480.560.640.720.46270.6573E
Example
56 of 100 at 95%: ; ; ; the ends and .Calculator: gives the same interval.
Tip

The four steps of the AP answer

A full answer has four parts. Parameter: say in words what is. Procedure: name the interval (a one-sample -interval for a proportion). Conditions: check them with the numbers. Conclusion: the interval, the level and a sentence in context that follows the fixed frame (see Two right sentences).
Example
Poll of 100 voters, 56 in favour. = the share of all voters who support the plan. One-sample -interval for a proportion. Random sample; is under 10% of all voters; successes and failures. Interval : we are 95% confident that this interval captures the true share of all voters who support the plan.
Rule

Conditions for a proportion

Check before you trust the interval. Random: the sample is random (or a randomised experiment). 10% condition: is at most 10% of the population size , so the draws are nearly independent. Counts: the numbers of successes and failures are both at least 10 (AP; some books accept 5; 9709 only asks for a large sample). If a condition fails, the interval is not justified.
Example
56 of 100: successes and failures : the counts are fine.4 of 30: successes is under 10 (and under 5), the failures are fine: the counts fail, so the interval that the formula gives is not justified.
Watch out!

The interval is rough for small counts

This interval (the Wald interval) is an approximation: stands in for in the standard error and the normal curve for the exact counts. It works well for large counts, but its real capture rate can be below the level, mostly for small counts or near 0 or 1; if is 0 or 1 it is a single point. (Not asked in any exam; shown to be honest about “approximate”.)
−0.10.00.10.20.30.481/100
Example
Exact capture rate of the 95% interval: for and it is ; for and only . In the application 100 seeded samples with , capture in cases (a run, not exact).
Rule

A higher level gives a wider interval

For the same sample a higher level needs a larger critical value , so the margin of error and the width grow. You buy more confidence in the method with a less precise interval. Only a larger sample can give both: more confidence and a smaller margin (see The margin falls like 1 / √n).
0.400.480.560.640.720.47840.641790%0.46270.657395%0.43210.687999%
Example
56 of 100 (): at 90% ; at 95% ; at 99% .The intervals: , and ; the 99% interval is times as wide as the 95% one.
Rule

The interval for a mean, σ known

When the population standard deviation is known, the sample mean has standard error and the interval is \bar x \pm z^* \cdot \dfrac{\sigma}{\sqrt n}. The margin of error is . (9709 and the IB AI HL course use the normal distribution here.)
949810210611097.1001106.8999E
Example
A sample of has and is known: ., so the 95% interval is .
Rule

A normal population or a large sample

The sample mean is exactly normal, with mean and standard deviation , when the population is normal. For any population it is close to normal when is large (the central limit theorem). That is why the rule of 9709 reads “normal population or large sample”. A larger also makes the interval narrower: falls.
100
Example
With : for the standard error is , for it is . Four times the sample, half the standard error, so half the margin of error.
Tip

Other levels and the calculator

Any level works: is with replaced by . The calculator also builds the whole interval: (σ known) or (σ unknown); on a Casio the same are 1-Sample ZInt and 1-Sample tInt. Write the calculator call you used, not only the answer.
Example
Level 98% for the sample , , : , so . and the interval is , wider than the 95% one.
Watch out!

s is not σ

The population standard deviation is almost never known. The sample standard deviation is only an estimate of it, and for a small sample it can be far off. Putting in place of and still using the normal critical value is a mistake: it ignores the extra uncertainty that comes from . The answer is the distribution (see The t distribution).
8090100110120130100
Example
Two random samples of 5 from the same population (): has and ; has and .The two values of differ by a factor and neither equals .
Definition

The t distribution

When is unknown we standardise with : . For a normal population this follows a t distribution with degrees of freedom. A curve is symmetric and bell-shaped like the normal curve, but its peak is lower and its tails are heavier: more area lies far from the middle. As grows the curve comes closer to the standard normal curve.
−3−2−10123
Example
For the area beyond is , while for the standard normal curve it is : the curve has more than twice as much in its tails.
Rule

The critical value t*

The critical value cuts off the middle area of the curve with . It is larger than because the tails are heavier, and it falls towards as grows. At 95%: for , for , for , for , and (the value of ) for very large . The calculator gives it with .
ν0.950.9750.990.99516.31412.7131.8263.6652.0152.5713.3654.032101.8122.2282.7643.169301.6972.0422.4572.750∞1.6451.9602.3262.576
Example
A sample of has , and at 95% the area to the left is : , clearly more than .
Tip

Reading the printed table

The Cambridge formula list prints for the upper-tail probability . Choose the row and the column : for 95% that is the column . The table shows three decimals (four figures for large values); the calculator gives more digits.
ν0.950.9750.990.995101.8122.2282.7643.169111.7962.2012.7183.106121.7822.1792.6813.055
Example
at 95%: row , column : . The calculator gives , which rounds to the same three decimals.
Rule

The interval for a mean, σ unknown

When is unknown use the sample standard deviation and the distribution: \bar x \pm t^* \cdot \dfrac{s}{\sqrt n}, \qquad df = n - 1. The standard error is and the margin of error is . The IB guide uses this rule for every sample size when is unknown.
1112131415161712.230416.1697E
Example
, , : , , ., so the 95% interval is . Calculator: .
Watch out!

z instead of t gives a narrower interval

With and a small , the normal critical value is smaller than , so the interval comes out too narrow: it looks more precise than it is. With unknown always use with . The narrower the sample, the larger the difference; for large the two critical values are almost equal.
1112131415161712.230416.1697t12.446015.9540z
Example
For , , : with the margin is , giving , against and with .The interval is about narrower than it should be.
Rule

Matched pairs

When the data are matched pairs (a before and an after for the same route or person), subtract inside each pair and treat the differences as one sample: , and = the number of pairs, , and the interval . Say which way you subtracted. If lies inside the interval, “no difference” is plausible.
−10123451.05353.9466
Example
Six routes, times before and after minutes. Before after: ; , , , ., , : the interval does not hold .
Rule

Conditions for a mean

Check three things. Random: a random sample (or a randomised experiment). 10% condition: is at most 10% of the population. Shape: the population is normal, or the sample is large ( in AP), or a small sample has data without strong skew and outliers. The rules differ a little: 9709 asks for a normal population or a large sample, the IB guide assumes a normal population, AP looks at the size and at the data.
Example
A sample of delivery times: , so the size rule is met (still look for extreme values). A sample of is under 30: the data must be looked at, with a dot plot (see Checking the shape) before the interval is trusted.
Tip

Checking the shape: the fences

For a small sample draw a dot plot and look for strong skew and outliers. A value is an outlier by the rule when it lies below or above (the fences; the quartiles are the medians of the lower and the upper half). An outlier in a small sample means the interval is not justified.
1018263442
Example
Data (): , , , fences and . is an outlier: it lifts to (without it ). Do not use the interval for these data.
Rule

Which interval?

Ask what the data are. A share (successes out of ): the interval for a proportion. A mean with known: the interval . A mean with unknown: the interval with and . Matched pairs: the interval on the differences. Then check the conditions of that interval.
Example
“56 of 100 say yes”: a share, so . “Mean 102, known, ”: the interval . “Mean , , ”: the interval with , .
Definition

What “95% confident” means

The level describes the method. If we took many random samples of the same size and built an interval from each, about 95% of those intervals would capture the true value. One interval is a hit or a miss and we cannot tell which: the 95% is the long-run capture rate of the method. The interval is the random thing; the true value is a fixed number.
0.20.30.40.50.60.70.894/100
Example
The application draws 100 seeded samples of 100 from and makes a 95% interval from each: of them capture , miss (other runs gave and ). The exact capture rate of this method is , the sum of the binomial probabilities of the counts whose interval holds .
Rule

The interval moves, the true value stays

The true value of the population is one fixed number, even when we do not know it. Every random sample gives its own estimate and so its own interval: it is the interval that changes from sample to sample. Some intervals capture the true value and some miss it, and in real life we never see which.
0.30.40.50.60.70.80.46270.65730.36230.55770.53540.7246
Example
Suppose the true share is (a pollster does not know it). Three polls of 100 give , and and the 95% intervals , and . The first two capture ; the third has lower end and misses it.
Rule

Two right sentences

Two sentences say it right, and in both the interval is the subject that captures. The frame of AP and the IB guide: “We are confident that the interval from to captures the true (parameter, in context).” The repeated-sampling frame: “In many random samples of the same size, about of the intervals would capture the true (parameter, in context).” Always name the parameter in context, not just “”.
Example
For the poll with : “We are 95% confident that the interval from to captures the true proportion of all voters who support the plan.” And: “In many random samples of the same size, about 95% of the intervals would capture the true proportion of all voters who support the plan.”
Watch out!

Misreading 1 (WRONG): the individual values

WRONG: “95% of the individual values lie between and .” Verdict: the interval is about one number, the true value of the population, not about the data. With a larger sample the interval gets narrower, while the values keep their spread, so fewer and fewer of them lie inside.
11.611.812.012.212.412.611.840012.2934
Example
Six readings : , , (), 95% interval . Only of the 6 readings lie inside it; lie outside. That is far below 95%, and with more readings it would be fewer.
Watch out!

Misreading 2 (WRONG): a probability for this interval

WRONG: “There is a 95% probability that the true proportion lies between and .” Verdict: the true value is a fixed number and, once the sample is taken, the interval is fixed too: it holds the true value or it does not. The 95% belongs to the method before the sample is drawn, as the share of intervals that capture the true value in the long run.
0.20.30.40.50.60.70.817/20
Example
Take the first 20 of the 100 seeded intervals (, ): capture and miss it. Each one is a hit or a miss; none of them is “95% a hit”. The 95% appears only over many intervals: of all 100 captured.
Watch out!

Misreading 3 (WRONG): the next samples

WRONG: “95% of the results of the next samples will fall between and .” Verdict: the interval is centred on the sample result of this one sample, not on the true value, so later results fall around the true value and only part of them lands in this interval. A probability about the next sample result is a different statement, with a different number.
0.30.40.50.60.7
Example
From of we got . If the true share is , the next sample count of 100 is binomial with , and the next falls in this interval when (since and ).Exactly , about of the next samples, not 95%.
Watch out!

Misreading 4 (WRONG): the true value moves

WRONG: “The true mean changes from sample to sample, and in 95% of the samples it moves into the interval.” Verdict: the true mean never moves. It is the sample, and so the interval, that changes. A picture of intervals jumping around a fixed line is the right picture.
909510010511011598.1107.993.1102.9101.1110.9
Example
The true mean is with and (). Samples with , and give , and . stays on its line in all three; the third interval has lower end and misses it.
Rule

Why the level works: the same event

The two statements and “ lies in the interval ” say the same thing: and are at most apart. Since is within of in a share of random samples, a share of the intervals capture . That is where the level comes from.
100.095.1104.998.1107.9101.1110.9
Example
, , : . If : and the interval holds . If : and the interval does not. The two statements are true together or false together.
Watch out!

z with s captures less than the level

Build the 95% interval with and from small samples and fewer than 95% of the intervals capture the true mean: the exact rate is . The interval captures exactly at the level. The shortfall is large for small and fades as grows.
506070809010011012013014036/40506070809010011012013014038/40
Example
Exact rates with : : ; : ; : . In the application 100 samples of 5 from : with captures , captures (the picture shows the first 40: and ).
Watch out!

An interval does not repair a biased sample

The margin of error only measures random variation. If the sample is not random (volunteers, whoever is easy to reach) the interval is built around a biased estimate: a large makes it narrow and makes it more wrongly sure. The level is true only for random samples. No formula, level or sample size repairs a bad sampling method.
0.450.500.550.600.650.700.60660.6335
Example
A website asks visitors to vote and of volunteers say yes: , , , the interval is very narrow. If the share of all voters is , the interval is far from it: .
Rule

The margin falls like 1 / √n

The margin of error contains in the denominator ( or ). So four times the sample gives half the margin, and a hundred times the sample a tenth. A narrower interval is paid for with many more observations.
1000.09804000.049016000.0245
Example
With at 95%: gives ; gives ; gives .Each step multiplies by and divides by .
Rule

The sample size for a proportion

To get a margin of error of at most , solve for : n \ge \left(\dfrac{z^*}{m}\right)^2 \hat p (1 - \hat p). Substitute, work out the number, then round up to the next whole number: a smaller would give a margin above . Check the margin with the you chose.
Example
Margin at 95% with : , squared , times : , so .Check: gives , but gives .
Tip

The safe value p = 0.5, and the factor 2

Before the sample is taken is not known. The product is largest, , at , so is the safe choice that never gives too small an ; a good guess for gives a smaller . The Dutch formula list uses the factor 2 for (at 95% only): .
Example
For at 95%: with , , so . If is a good guess, and , so . With the factor 2 and : , so .
Rule

The sample size for a mean, and rounding up

For a mean with known (or guessed): gives n \ge \left(\dfrac{z^* \sigma}{m}\right)^2. Always round up, never to the nearest: becomes , not . Rounding down breaks the promise of the margin.
Example
and margin at 95%: , squared , so .Check: gives ; gives .
Rule

Trade-offs: level, margin and sample size

Three things pull against each other: the level, the margin and the sample size. A higher level or a smaller margin needs a larger ; halving the margin needs four times ; going from 90% to 99% needs about times . You cannot have a high level and a small margin from a small sample.
Example
Sample sizes for : margin : at 90%, at 95%, at 99%. Margin : , , .At 95% a margin of needs and a margin of needs , which is . The ratio of the 99% to the 90% values is .
Tip

A margin from simulation

The margin of error can also be found by simulation (CCSS S-IC.B.4): take many random samples of the same size from a population with the known share , work out each sample share, and read off the middle 95% of the values. Half the distance between its ends is the simulated margin. It lands near the formula value, but not exactly: the simulation has its own random error.
0.30.40.50.60.7
Example
The application draws 1000 seeded samples of 100 from : the middle 95% of the values runs from to , so the simulated margin is . The formula gives . They are close; the gap of comes from the 1000 repeats and from moving in steps of .
Rule

Plausible values and claims

To judge a claimed value, look at the interval. A value inside the interval is plausible: the data do not rule it out. A value outside the interval is not supported by the data. A plausible value is not proved: other values inside the interval are just as plausible, so the data cannot choose between them.
0.40.50.60.70.80.46270.6573
Example
The interval from 56 of 100. Claim : inside (), plausible, not ruled out. Claim : inside, plausible too: the data cannot choose between and . Claim : , outside, not supported.
Watch out!

Overlapping intervals do not settle a difference

When two group intervals overlap you cannot conclude that the groups do not differ. The right comparison is an interval for the difference itself (a later topic, the intervals of two groups). It is narrower than the two intervals put together. If two intervals do not overlap at all, the groups clearly differ; the other way round does not hold.
4045505560657045.154.9A53.162.9B
Example
Two groups of 36 with : means and , each, intervals and overlap from to . For the difference the standard error is , and the interval does not hold : the groups do differ.
Tip

Everyday: an opinion poll

A poll reports a share with a margin of error, “ points”. The margin of error is the of the interval, and its size depends on : about a thousand people give about three points. A lead smaller than the margin is not a clear lead: the interval still holds .
0.460.480.500.520.540.560.580.48900.5510
Example
A random poll of people: in favour, , , ( points). The 95% interval is : it holds , so “a majority” is not supported.A margin of needs , so a poll of people.
Tip

Everyday: lab readings

Repeating a measurement gives readings that vary a little. Their mean estimates the true value of the quantity, and the interval says how well. More readings narrow the interval, but slowly: the margin falls like and also gets smaller.
11.811.912.012.112.212.312.411.840012.2934611.975512.157924
Example
Six readings give and with . With four times as many readings (, , ) and the same and : , about of the old margin.
Tip

Everyday: a factory check

A random sample of items is checked and the defective ones are counted: a share, so the interval for a proportion. Check the counts: both the number of defective and the number of good items should be at least 10. A small share needs a large sample for a small margin, because the interval is narrow only when is big.
0.000.020.040.060.080.01780.0622
Example
defective in items: , counts and . , , the 95% interval .For a margin of only with : , so items.
Tip

Everyday: delivery times before and after

Times on the same routes before and after a change are matched pairs. Subtract inside each route (before after, so a positive difference means faster) and build the interval of the differences. If is outside the interval, the change is supported; if it is inside, “no change” is plausible.
−10123450.84104.4090
Example
Eight routes, differences minutes: sum , , , , , , .The 95% interval is : it does not hold , so the times did go down.
Tip

Which course asks what

Cambridge 9709 (Paper 6): the interval for a mean and an approximate interval for a proportion; the formula list MF19 prints the critical values. IB AI HL (AHL 4.16): normal if is known, if not; the IB AA course has no confidence intervals (not examined at IB AA). AP Statistics (units 3 and 4): conditions, interpretation, claims, sample size. CCSS S-IC.B.4: a margin of error by simulation. Dutch wiskunde A: the statement with its reliability, the formula list with the factor 2. No UK A level, GCSE or IGCSE course asks for a confidence interval.
Example
9709: the interval for a mean and the interval for a share. IB AI HL: also the interval and the calculator. AP: the four steps of the answer. Dutch: the factor 2 and a sample size ( for a margin of ).

Exercises

A random poll of 200 people finds 110 in favour of a plan. Find the sample share and the standard error . Easy
Show solution
The sample share is .
Then and divided by : .
.
and
Check → , which is rounded.
For the poll of 200 people with 110 in favour, give the 95% confidence interval for the share of all voters in favour (4 decimal places). Easy
Show solution
and for 95%.
The margin of error is .
The ends are and .
Check → at 90% the margin is smaller (), at 99% larger (): the 95% value lies between them.
Which interval? (a) 38 of 120 buses were late. (b) The mean of 50 readings is known to have . (c) The mean of 15 pupils’ times, with from the sample. Name the interval and the degrees of freedom if it has any. Easy
Show solution
(a) is a share: the interval for a proportion.
(b) is a mean with known: the interval .
(c) is a mean with unknown: the interval with .
(a) interval for a proportion; (b) interval for a mean; (c) interval,
Check → only (c) uses from a sample, so only (c) needs .
A 95% interval for a share is . Find the sample share and the margin of error. Easy
0.380.420.460.500.540.580.620.420.58
Show solution
The sample share is the centre: .
The width is .
The margin of error is half the width: .
and
Check → and .
Find the critical value from the printed table: (a) a 95% interval from a sample of 8; (b) a 99% interval from a sample of 20. Easy
Show solution
(a) ; at 95% the column is : .
(b) ; at 99% the column is : .
(a) ; (b)
Check → both are larger than the matching ( and ), as they must be for a small .
A 95% interval for a mean is . Find the sample mean and the margin of error. Is the value 100 plausible? Is 110? Easy
Show solution
The sample mean is the centre: .
The margin of error is half the width: .
lies inside (): plausible. lies outside: not supported.
, ; 100 is plausible, 110 is not supported
Check → and . That 100 is plausible does not prove that .
A random sample of 25 has mean 48 and the population standard deviation is known to be 6. Find the 95% interval for the mean (4 decimal places). Medium
444648505245.648050.3520
Show solution
.
.
The interval is to .
Check → the calculator gives the same ends.
The same sample (mean 48, ) has sample standard deviation , and is not known. Find the 95% interval and compare its margin with the previous one. Medium
Show solution
and at 95%.
and .
The interval is ; the margin is larger than with .
; the margin is a little larger than
Check → for .
In a random sample of 40 pupils, 6 walk to school. May the 95% interval for a proportion be used? Say what you conclude. Medium
Show solution
The counts: successes and failures . AP asks both at least 10: fails.
The formula would give , , and the interval .
With AP’s rule the counts fail, so the interval is not justified
No: only 6 successes (under 10), so the interval is not justified
Check → , and .
A margin of error of at most 0.05 is wanted for a share at 95%, and nothing is known about . How large must the sample be? Medium
Show solution
With nothing known use the safe value : .
.
Round up: .
Check → is not a whole number and the sample size must be at least that: round up, never down.
A 95% interval for the proportion of students who walk to school is . Write the conclusion in the fixed frame, in context. Medium
Show solution
Name the parameter in words: the proportion of all students who walk to school.
The interval is the subject that captures: “the interval from to captures the true proportion”.
Add the level as “We are 95% confident that …” and the context.
We are 95% confident that the interval from to captures the true proportion of all students who walk to school.
Check → the centre is and the margin ; the sentence is about the interval, not about the students.
Five pupils take a test before and after a lesson; the differences (after before) are . Find the 95% interval for the mean difference. Is 0 plausible? Medium
−1135790.27507.7250
Show solution
. Squares of the deviations: , , .
, , , .
The interval is ; lies below it, so “no change” is not supported.
; 0 is not plausible
Check → ; the calculator agrees.
A pupil writes for the interval about the proportion of students who walk to school: “There is a 95% probability that the true proportion is between 0.31 and 0.45.” This is WRONG. Explain why and write a right sentence. Hard
Show solution
The true proportion is one fixed number; the drawn interval is fixed too, so it holds it or it does not.
The 95% belongs to the method: in many random samples about 95% of the intervals capture it.
A right sentence: “We are 95% confident that the interval from to captures the true proportion of all students who walk to school.”
The interval is the random thing and the true value is fixed; the 95% describes the method. Right sentence: see the last step
Check → in the right sentence the interval is the subject that captures.
The standard deviation of a population is 15. How large a sample gives a 99% margin of error of at most 2? Compare it with the 95% sample size. Hard
Show solution
At 99%: .
.
Round up: , against at 95% (from ).
at 99%, against at 95%
Check → the ratio and , near .
The poll of 1000 people with 520 in favour is worked with the Dutch factor 2. Find the interval, and compare it with the interval that uses . Hard
0.480.500.520.540.560.48840.551620.48900.55101.96
Show solution
and .
With the factor 2: , the interval .
With : and ; the factor 2 interval is a little wider.
Factor 2: ; with :
Check → , so the margin with the factor 2 () is larger than ; both intervals hold .
A sample of 5 has and . Find the 95% interval with , then the one a pupil gets with . How much wider is the correct interval (in %)? Hard
Show solution
; , , : the interval is .
With : and .
The margins are in the ratio : the correct interval is about wider.
about wider: against
Check → the interval with captures the true mean in only about of such samples.
A poll of 400 people has margin 0.049 at 95% (with ). The pollster wants half this margin and a 99% level. How many people are needed, and how many times the old is that? Hard
Show solution
The new margin is and .
, so .
Compared with : times; halving the margin alone gives times (to at 95%), and the 99% level adds the rest.
, about times the old sample
Check → , where .
Two groups of 36 have means 50 and 58 and the known in both. Their 95% intervals overlap. Does that show that the groups do not differ? Use the interval for the difference with standard error (a later topic). Hard
Show solution
Each group has : and overlap.
For the difference : and .
The interval does not hold , so the groups do differ although the group intervals overlap.
No: the difference interval excludes , so overlap does not settle it
Check → . (The point: overlapping group intervals do not settle it.)
A small sample has the values . Is a interval for the mean justified? Use the fences of the rule. Hard
28142026
Show solution
Lower half : ; upper half : ; .
The fences are and .
is an outlier in a sample of 8: the interval is not justified.
No: lies above the fence , an outlier in a small sample
Check → , so no value is below the lower fence; only is outside.
Are you a teacher?

Start live lessons with these applications for your whole class. Free to try for one month.

Try it free

Fits these school years

IB (MYP, Diploma): Diploma, year 1, Diploma, year 2

Cambridge International: A Level

Netherlands: Havo · Mathematics A, Vwo · Mathematics A

USA (Common Core): Algebra 2, Precalculus

What the applications of this topic teach 6 applications

Interval for a proportion: margin of error and conditions

  • Building a 95% interval for a share
  • Checking the conditions and saying when the interval is not justified
  • Writing the answer in four steps ending with the conclusion in context

Interval for a mean: z, t and matched pairs

  • Building an interval for a mean with σ known
  • Building an interval for a mean with σ unknown: the t distribution
  • Treating matched pairs as one sample of differences

Capture rate: what 95% confident means

  • Saying what the level of a confidence interval means
  • Seeing that the interval is random and the true value is fixed
  • Explaining why a small sample with z captures less than the level

Margin and sample size

  • Seeing that the margin of error falls like 1 / √n
  • Finding the least sample size for a wanted margin
  • Saying how level, sample size and margin affect each other

Read an interval: say it right

  • Choosing the right sentence for an interval in context
  • Saying what is wrong with each common misreading
  • Using an interval to support a claim

Intervals in everyday life

  • Building an interval for a poll, a lab measurement or a factory check
  • Choosing the right interval for each story
  • Writing the result as a sentence in context