Inference for categorical data

In August of 2012, news outlets ranging from the Washington Post to the Huffington Post ran a story about the rise of atheism in America. The source for the story was a poll that asked people, “Irrespective of whether you attend a place of worship or not, would you say you are a religious person, not a religious person or a convinced atheist?” This type of question, which asks people to classify themselves in one way or another, is common in polling and generates categorical data. In this lab we take a look at the atheism survey and explore what’s at play when making inference about population proportions using categorical data.

The survey

To access the press release for the poll, conducted by WIN-Gallup International, click on the following link:

http://www.wingia.com/web/files/richeditor/filemanager/Global_INDEX_of_Religiosity_and_Atheism_PR__6.pdf

this link does not take me to the report Take a moment to review the report then address the following questions.

Exercise 1

In the first paragraph, several key findings are reported. Do these percentages appear to be sample statistics (derived from the data sample) or population parameters?

Exercise 2

The title of the report is “Global Index of Religiosity and Atheism”. To generalize the report’s findings to the global human population, what must we assume about the sampling method? Does that seem like a reasonable assumption? That the samples are independently and randomly selected, and that they were collected without bias.

The data

Turn your attention to Table 6 (pages 15 and 16), which reports the sample size and response percentages for all 57 countries. While this is a useful format to summarize the data, we will base our analysis on the original data set of individual responses to the survey. Load this data set into R with the following command.

download.file("http://www.openintro.org/stat/data/atheism.RData", destfile = "atheism.RData")
load("atheism.RData")
glimpse(atheism)
## Rows: 88,032
## Columns: 3
## $ nationality <fct> "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan"…
## $ response    <fct> non-atheist, non-atheist, non-atheist, non-atheist, non-at…
## $ year        <int> 2012, 2012, 2012, 2012, 2012, 2012, 2012, 2012, 2012, 2012…

Exercise 3

What does each row of Table 6 correspond to? What does each row of atheism correspond to?

To investigate the link between these two ways of organizing this data, take a look at the estimated proportion of atheists in the United States. Towards the bottom of Table 6, we see that this is 5%. We should be able to come to the same number using the atheism data.

I can’t see the report, but I get 3% of respondents in USA responding as “atheist”.

#levels(atheism$nationality)
usRespondents<- filter(atheism, atheism$nationality == "United States")

table(usRespondents$response)
## 
##     atheist non-atheist 
##          60        1944
table(usRespondents$response)[[1]]/count(usRespondents)
##            n
## 1 0.02994012

Exercise 4

Using the command below, create a new dataframe called us12 that contains only the rows in atheism associated with respondents to the 2012 survey from the United States. Next, calculate the proportion of atheist responses. Does it agree with the percentage in Table 6? If not, why?

Yes, this is 5%

us12 <- subset(atheism, nationality == "United States" & year == "2012")

table(us12$response)
## 
##     atheist non-atheist 
##          50         952
table(us12$response)[[1]]/count(us12)
##           n
## 1 0.0499002

Inference on proportions

As was hinted at in Exercise 1, Table 6 provides statistics, that is, calculations made from the sample of 51,927 people. What we’d like, though, is insight into the population parameters. You answer the question, “What proportion of people in your sample reported being atheists?” with a statistic; while the question “What proportion of people on earth would report being atheists” is answered with an estimate of the parameter.

The inferential tools for estimating population proportion are analogous to those used for means in the last chapter: the confidence interval and the hypothesis test.

Exercise 5

Write out the conditions for inference to construct a 95% confidence interval for the proportion of atheists in the United States in 2012. Are you confident all conditions are met?

Conditions for probability confidence interval (without Wilson adjustment): - Data are randomly sampled from the population - Observations are chosen independently, and - All items in the population have the same chance of being sampled - Sample size is sufficiently large

I am assuming all the conditions are met. Given that I cannot access the report, that is all I can do.

If the conditions for inference are reasonable, we can either calculate the standard error and construct the interval by hand, or allow the inference function to do it for us.

inference(us12$response, est = "proportion", type = "ci", method = "theoretical", success = "atheist")
## Single proportion -- success: atheist 
## Summary statistics:

## p_hat = 0.0499 ;  n = 1002 
## Check conditions: number of successes = 50 ; number of failures = 952 
## Standard error = 0.0069 
## 95 % Confidence interval = ( 0.0364 , 0.0634 )

Note that since the goal is to construct an interval estimate for a proportion, it’s necessary to specify what constitutes a “success”, which here is a response of “atheist”.

Although formal confidence intervals and hypothesis tests don’t show up in the report, suggestions of inference appear at the bottom of page 7: “In general, the error margin for surveys of this kind is ± 3-5% at 95% confidence”.

Exercise 6

Based on the R output, what is the margin of error for the estimate of the proportion of the proportion of atheists in US in 2012?
The margin of error for inferred proportion of US atheists in 2012 is ± 1.35%

Exercise 7

Using the inference function, calculate confidence intervals for the proportion of atheists in 2012 in two other countries of your choice, and report the associated margins of error. Be sure to note whether the conditions for inference are met. It may be helpful to create new data sets for each of the two countries first, and then use these data sets in the inference function to construct the confidence intervals.

ag12 <- subset(atheism, nationality == "Argentina" & year == "2012")
inference(ag12$response, est = "proportion", type = "ci", method = "theoretical", success = "atheist")
## Single proportion -- success: atheist 
## Summary statistics:

## p_hat = 0.0706 ;  n = 991 
## Check conditions: number of successes = 70 ; number of failures = 921 
## Standard error = 0.0081 
## 95 % Confidence interval = ( 0.0547 , 0.0866 )

The margin of error for inferred proportion of Argentinian atheists in 2012 is ± 1.6%

sw12 <- subset(atheism, nationality == "Sweden" & year == "2012")
inference(sw12$response, est = "proportion", type = "ci", method = "theoretical", success = "atheist")
## Single proportion -- success: atheist 
## Summary statistics:

## p_hat = 0.0808 ;  n = 495 
## Check conditions: number of successes = 40 ; number of failures = 455 
## Standard error = 0.0122 
## 95 % Confidence interval = ( 0.0568 , 0.1048 )

The margin of error for inferred proportion of Argentinian atheists in 2012 is ± 2.4%

How does the proportion affect the margin of error?

Imagine you’ve set out to survey 1000 people on two questions: are you female? and are you left-handed? Since both of these sample proportions were calculated from the same sample size, they should have the same margin of error, right? Wrong! While the margin of error does change with sample size, it is also affected by the proportion.

Think back to the formula for the standard error. This is then used in the formula for the margin of error for a 95% confidence interval. Since the population proportion p is in this ME formula, it should make sense that the margin of error is in some way dependent on the population proportion. We can visualize this relationship by creating a plot of ME vs. p.

The first step is to make a vector p that is a sequence from 0 to 1 with each number separated by 0.01. We can then create a vector of the margin of error (me) associated with each of these values of p using the familiar approximate formula (ME=2×SE). Lastly, we plot the two vectors against each other to reveal their relationship.

n <- 1000
p <- seq(0, 1, 0.01)
me <- 2 * sqrt(p * (1 - p)/n)
plot(me ~ p, ylab = "Margin of Error", xlab = "Population Proportion")

Exercise 8

Describe the relationship between p and me.

With n = 1000, and the proportion at 0%, the margin of error is near 0%. As the proportion p increases from 0 and approaches .5, the margin of error me is positively corellated and it approaches 3%. After the proportion has passed 50% and as it approaches 100%, the margin of error is negatively corellated, and it approaches 0%.

Success-failure condition

The textbook emphasizes that you must always check conditions before making inference. For inference on proportions, the sample proportion can be assumed to be nearly normal if it is based upon a random sample of independent observations and if both np≥10 and n(1−p)≥10. This rule of thumb is easy enough to follow, but it makes one wonder: what’s so special about the number 10?

The short answer is: nothing. You could argue that we would be fine with 9 or that we really should be using 11. What is the “best” value for such a rule of thumb is, at least to some degree, arbitrary. However, when np and n(1−p) reaches 10 the sampling distribution is sufficiently normal to use confidence intervals and hypothesis tests that are based on that approximation.

We can investigate the interplay between n and p and the shape of the sampling distribution by using simulations. To start off, we simulate the process of drawing 5000 samples of size 1040 from a population with a true atheist proportion of 0.1. For each of the 5000 samples we compute p̂ and then plot a histogram to visualize their distribution.

p <- 0.1
n <- 1040
p_hats <- rep(0, 5000)

for(i in 1:5000){
  samp <- sample(c("atheist", "non_atheist"), n, replace = TRUE, prob = c(p, 1-p))
  p_hats[i] <- sum(samp == "atheist")/n
}
hist(p_hats, main = "p = 0.1, n = 1040", xlim = c(0, 0.18))

These commands build up the sampling distribution of p̂ using the familiar for loop. You can read the sampling procedure for the first line of code inside the for loop as, “take a sample of size n with replacement from the choices of atheist and non-atheist with probabilities p and 1−p, respectively.” The second line in the loop says, “calculate the proportion of atheists in this sample and record this value.” The loop allows us to repeat this process 5,000 times to build a good representation of the sampling distribution.

Exercise 9

Describe the sampling distribution of sample proportions at n=1040 and p=0.1. Be sure to note the center, spread, and shape. Hint: Remember that R has functions such as mean to calculate summary statistics.

summary(p_hats)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## 0.07019 0.09327 0.09904 0.09969 0.10577 0.12981
sd(p_hats)
## [1] 0.009287382

The sampling distribution at n=1040 and p=0.1 appears to be normally distributed with a mean and median around 0.1, a standard deviation of 0.009

Exercise 10

Repeat the above simulation three more times but with modified sample sizes and proportions: for n=400 and p=0.1, n=1040 and p=0.02, and n=400 and p=0.02. Plot all four histograms together by running the par(mfrow = c(2, 2)) command before creating the histograms. You may need to expand the plot window to accommodate the larger two-by-two plot. Describe the three new sampling distributions. Based on these limited plots, how does n appear to affect the distribution of p̂ ? How does p affect the sampling distribution?

Once you’re done, you can reset the layout of the plotting window by using the command par(mfrow = c(1, 1)) command or clicking on “Clear All” above the plotting window (if using RStudio). Note that the latter will get rid of all your previous plots.

p2 <- 0.1
n2 <- 400
p2_hats <- rep(0, 5000)

for(i in 1:5000){
  samp <- sample(c("atheist", "non_atheist"), n2, replace = TRUE, prob = c(p2, 1-p2))
  p2_hats[i] <- sum(samp == "atheist")/n2
}


p3 <- 0.02
n3 <- 1040
p3_hats <- rep(0, 5000)

for(i in 1:5000){
  samp <- sample(c("atheist", "non_atheist"), n3, replace = TRUE, prob = c(p3, 1-p3))
  p3_hats[i] <- sum(samp == "atheist")/n3
}


p4 <- 0.02
n4 <- 400
p4_hats <- rep(0, 5000)

for(i in 1:5000){
  samp <- sample(c("atheist", "non_atheist"), n4, replace = TRUE, prob = c(p4, 1-p4))
  p4_hats[i] <- sum(samp == "atheist")/n4
}



par(mfrow = c(2, 2))
hist(p_hats, main = "p = 0.1, n = 1040")
hist(p2_hats, main = "p2 = 0.1, n2 = 400" )
hist(p3_hats, main = "p3 = 0.02, n3 = 1040")
hist(p4_hats, main = "p4 = 0.02, n4 = 400")

#Once you’re done, you can reset the layout of the plotting window by using the command 
par(mfrow = c(1, 1))

Increasing n appears to result in smoother histogram, and decreasing p from .1 to .02 introduces right skew to the distribution.

Exercise 11

If you refer to Table 6, you’ll find that Australia has a sample proportion of 0.1 on a sample size of 1040, and that Ecuador has a sample proportion of 0.02 on 400 subjects. Let’s suppose for this exercise that these point estimates are actually the truth. Then given the shape of their respective sampling distributions, do you think it is sensible to proceed with inference and report margin of errors, as the reports does?

Given that np is less than 10 for Ecuadors parameters, I do not think it is sensible to use this sample for inference. Australia’s np exceeds the commonly used threshold of 10, so one could safely proceed with inference using that data.