Confidence Interval Estimation for the Population Proportion — Transcript
Full transcript
- 0:00welcome to this tutorial on interval
- 0:02estimation for the population proportion
- 0:05just as we have created confidence
- 0:07intervals for the population mean with
- 0:10both Sigma known and sigma unknown we
- 0:13can also construct a confidence interval
- 0:15estimate for the population
- 0:18proportion the general form of an
- 0:20interval estimate is the sample
- 0:22statistic plus or minus a margin of
- 0:24error for a proportion that would be as
- 0:28shown here P bar plus or minus some
- 0:31margin of error we have seen in previous
- 0:34tutorials that the sampling distribution
- 0:36of P bar can be approximated by a normal
- 0:40distribution whenever n * p is greater
- 0:44than or equal to 5 and n * 1 minus p is
- 0:48also greater than or equal to 5 you can
- 0:50refer back to the tutorial on sampling
- 0:52distributions if you need a refresher on
- 0:55the topic but for this tutorial you need
- 0:58to remember that the mean of the
- 1:01sampling distribution of P bar is the
- 1:04population proportion p and the standard
- 1:08error of P bar is shown as Sigma
- 1:12subscript P bar and that is equal to the
- 1:14square root of P * 1us P / little n the
- 1:19sample size this standard Arrow will now
- 1:22be used in the formula for computing a
- 1:24confidence interval estimate for
- 1:27p here is the formula for calculating
- 1:30the confidence interval estimation for a
- 1:32proportion we can see that the standard
- 1:34error is used as an integral part of the
- 1:36formula we also see that we will be
- 1:39using the Z table with Alpha divided in
- 1:42half since the sampling distribution of
- 1:44P bar is normally distributed so to
- 1:47calculate the interval we have the
- 1:48formula shown here P bar which is a
- 1:51sample proportion plus and minus Z of
- 1:54alpha / half so that is the value we
- 1:57look up in the Z table times the
- 2:00standard error for p bar which is the
- 2:02square < TK of P * 1us P bar / little n
- 2:07the original formula for the standard
- 2:09error of P bar shown on the previous
- 2:10slide actually uses P not P bar but
- 2:14since we don't know what P the
- 2:16population proportion is we use P bar as
- 2:19a point estimator for p let's see how
- 2:22this formula might work in an example
- 2:25let's say that 200 fans were surveyed at
- 2:28the stadium to see how many order at
- 2:30least one hot dog and we find that 130
- 2:33of these 200 fans say they ordered one
- 2:36at least one hot dog then P bar is 130 /
- 2:41200 or 65 that is 65% of the people we
- 2:47asked 130 out of 200 said that they
- 2:49ordered at least one hot dog n the
- 2:52sample size is
- 2:54200 therefore the standard error for p
- 2:57bar is calculated as the square root of
- 3:0065 * 1
- 3:03-65 / 200 and we get
- 3:090337 now that we have the standard error
- 3:12we are ready to use the formula for
- 3:14constructing a confidence interval on
- 3:17P here is the general formula again we
- 3:20have P bar that is 65 we have n that is
- 3:25200 and we have the standard error which
- 3:28is 033 7 so what is left is to determine
- 3:32Z of alpha / in
- 3:36half now let's say we want to construct
- 3:39a 99% confidence interval on the true
- 3:41population proportion P here we can see
- 3:44the distribution marked off with the
- 3:46area of 099 around the middle of the
- 3:49distribution this N9 corresponds to a
- 3:5399% confidence interval first we have to
- 3:56determine our level of significance
- 3:58Alpha which would be the tail areas now
- 4:01if we are drawing a 99% confidence
- 4:03interval then Alpha is 1 minus our level
- 4:07of confidence so 1
- 4:09-99 is 01 so Alpha is
- 4:1301 this is the area in both the upper
- 4:16tail and lower area Tails so we split
- 4:19Alpha and half with half in the upper
- 4:20tail and half in the lower tail and
- 4:22Alpha divided in half is
- 4:2605 now we are ready to look up 00 05 in
- 4:30the netive Z
- 4:33table looking in the middle of the table
- 4:36we find two numbers are close to
- 4:3905 we have
- 4:420.49 and
- 4:440.51 and obviously 05 would be right in
- 4:48the middle of these two numbers looking
- 4:50to the left we find
- 4:52-2.5 and looking up we find that we are
- 4:55in between 007 and 08 so we get a z
- 5:00value of - 2.57 5 which is between -
- 5:042.57 and -
- 5:072.58 for this example we will use a zv
- 5:10value of plus or minus
- 5:132575 if you watched my previous tutorial
- 5:16on common Z values we used a value of
- 5:192576 since that is the value we would
- 5:22get without a rounding error or if we
- 5:24used Excel to compute the zv value but
- 5:27since we manually looked it up in this
- 5:29table let's use the table
- 5:31value okay so now getting back to
- 5:34calculating the interval let's start to
- 5:36plug in the numbers into the formula P
- 5:39bar is 65 so we get 65 plus and minus
- 5:472575 the zv value that we looked up in
- 5:49the table times the square < TK of 65 *
- 5:541 - 65 or. 35 / 200 and we we get 65
- 6:01plus andus
- 6:032575 *
- 6:060337 which is 65 plus and minus
- 6:12868 which is an interval of between.
- 6:155632 and
- 6:187368 this represents the interval within
- 6:22which we are 99% confident that the true
- 6:25population proportion exists plotted on
- 6:28the normal distribution curve the
- 6:30interval would look like
- 6:32this this is the normal distribution
- 6:34curve with P the population proportion
- 6:37marked off in the middle and a 99%
- 6:40confidence interval drawn around it we
- 6:42can see the lower limit is marked at0
- 6:455632 and the upper limit is marked at
- 6:497368 when we say this is a 99%
- 6:52confidence interval we are saying that
- 6:54based on this sample of 200 we are 99%
- 6:58confident that the true portion of fans
- 7:00ordering hot dogs at the stadium is
- 7:02within the interval between and
- 7:04including 5632 and
- 7:097368 that concludes this tutorial on
- 7:11confidence interval estimation for
- 7:13population proportions I hope you
- 7:15enjoyed this tutorial and I hope you
- 7:17learned
- 7:27something
About this transcript
This page contains the full transcript of Confidence Interval Estimation for the Population Proportion by Learn Something, generated from the public captions YouTube serves with the video. The transcript has 1,039 words across 149 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.
What you can do with it
Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.
Free YouTube transcript tool
YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.