FAQ: The Nielsen Ratings By Matthew Greenberg Washingtonpost.com Staff December 9, 1997

Hey, George! Who's watching? (AP/NBC)

Cold, hard numbers, on the other hand, will do the trick.

And that's why we have ratings, those oft-mentioned numbers that attempt to quantify just how many people are watching a television broadcast. In this age of information overload, the average viewer can readily find out the ratings figures for his favorite network sitcom (in The Post and on washingtonpost.com, John Carmody reports the national weekly numbers every Wednesday in The TV Column). But does everyone know what they mean?

What's a Ratings Point?
Let's go back to our example: The Oct. 30, 1997, episode of NBC's "ER" garnered a 20.6 rating, making it the top-rated show of the week. One ratings point is equal to one percent of the total number of possible TV households or viewers in the United States. In his TV Column, Post writer John Carmody reports the ratings based on the total TV households. Therefore, when Carmody writes that "ER" scored a 20.6 rating, it means that of all the households in the United States with TVs, 20.6 percent of them were tuned in to "ER."

So, how many households is that? With an estimated 98 million TV households in the United States, one ratings point equals approximately 980,000 TV households. That means an estimated 20,188,000 TV households were watching Dr. Greene turn grumpier and more withdrawn.

In addition to the national weekly ratings, Carmody also reports on overnight and local ratings. In the overnight ratings numbers, which are calculated based on metered households in the 38 largest TV markets, one ratings point equals 583,590 TV households. (For more about metered households, see below.) In ratings for the local Washington market (the 7th largest), one local ratings point equals 19,283 TV households.

What's a Share?
In the popular media, ratings numbers are often quickly followed by another number: the share. A share is also a percentage of a whole, but with an important difference from a ratings point. While a show's rating is the percentage of all possible TV households or viewers in the country, its share is the percentage of households or viewers actually watching TV at the time. Shares are nearly always reported alongside ratings since not every TV in America is on all the time (it only seems that way). In The Post, Carmody reports shares as a percentage of TV households with TV sets actually in use.

Therefore, going back to our "ER" example, the Oct. 30 episode had a 33 share. That means of all the TV households actually watching TV between 10 and 11 p.m. EST that night, 33 percent of them were watching "ER." Yes, that's a lot.

Demographics and Dissatisfaction
It should be noted, though, that while the media often report ratings points and shares, the TV industry is usually more interested in another set of numbers: demographics. These numbers, which show how much of certain segments of the population are watching TV (i.e., women ages 18 to 34), can often mean the difference between life and death for a show. Advertisers thirst over specific demographics for their products (viewers ages 18 to 49 are the most highly prized) and are less likely to pay top dollar to advertise on shows that can't deliver those groups. That's why it is possible for a show with respectable overall ratings to still be cancelled if its demographic numbers are less than spectacular.

Demographic numbers are so prized, in fact, that the debate over their measurement has played a significant role in the TV industry's dissatisfaction with the how the Nielsen rating system works (see below for more about the Nielsen system). In the last year, criticism over the Nielsen system has grown louder, as TV networks and cable broadcasters say the Nielsens are skewed toward some demographics and away from others. For example, the placement of "People Meters" (usually in middle-class and higher-educated homes) and those who have the most time to fill out Nielsen diaries (the elderly) can skew the demographics, network executives say. Even worse, Nielsen ratings don't count TV viewing in bars and college dorms, among other places, which the industry says can affect the demographics of sports and late-night programming.

In 1996, NBC executives went so far as to ask a New Jersey-based company, Statistical Research Inc. to draft a plan to create a new ratings measurement system. Early in 1997, the American Association of Advertising Agencies called for the formation of an industry commission to think about new ways to measure ratings and demographics.

But so far, Nielsen is still the standard-bearer of ratings information. In response to criticisms, the company is working toward improving the distribution of its rating diaries and how the set meters work. But in its defense, it also says that the networks, who have seen total television viewership decline over recent years, are just blaming the messenger.

How does Nielsen Media Research know who is watching?
For national ratings estimates, Nielsen uses a sample of more than 5,000 households, containing over 13,000 people who have agreed to participate.

How does Nielsen make sure that a sample is representative of the population?
If every member of the population has an equally good chance of being in the sample, then this makes it a representative sample. Through statistical theory (and many years of practical experience that is consistent with that theory), Nielsen knows that fairly drawn (or random) samples vary in usually small ways from the population. Over time these small difference tend to average out.

Measuring TV sets
In a specially selected sample of homes, Nielsen Media Research technicians install metering equipment on TV sets, VCRs and cable boxes (and even satellite dishes). The Nielsen TV meters automatically and invisibly keep track of when the sets are on and what the sets are tuned to. These meters are connected to a central "black box," which is actually a very small computer and modem. Information from the meters is collected by the black box and, in the middle of the night, all the black boxes call in their information to Nielsen's central computers.

Measuring people
Nielsen Media measures who is watching programs that reach the entire nation with the Nielsen People Meter. In the national sample, Nielsen installs set meters, which have an attachment called a "people meter." The people meter, a box about the size of a paperback book, is placed on or near each TV set. The box has buttons and lights assigned to each person who lives in the household (with additional buttons for guests). There is also a remote control to operate the people meter from anywhere in the room.

When a viewer begins watching TV, they push their button, changing their indicator light from red to green. When they finish watching, they push their button again and the indicator changes back to red. Periodically, the lights flash to remind people to check to make sure that the information in the people meter is accurate.

Information from the people meters is combined with set-tuning information and relayed to Nielsen Media Research each night.

Local measurement & diaries: another way to know who is watching
Nielsen Media measures more than 200 individual local television markets in addition to the national measurement service.

To measure the audiences for local television, Nielsen Media Research gathers viewing information using TV diaries, booklets in which samples of viewers record their television viewing during a measurement week. Nielsen conducts diary measurement for each of the 211 television markets in the country four times each year; during February, May, July and November. (You may have heard these called "sweep" months, in which Nielsen conducts a complete diary measurement across the nation.)

The diary requests that viewers write down not only who watched, but what program and what channel they watched.

In 38 of the largest markets, Nielsen has a sample of homes with set meters (not people meters), which provide the tuning status (set on/off, channel and time) of TV sets in the home. Nielsen collects information about who is viewing from separate samples of home in these markets with diaries for each TV set. Nielsen combines the meter and diary information in a way that projects the diary viewing data adjusted to the meter tuning data.

How do I become a member of the Nielsen TV sample?
Strictly through chance. Naturally, Nielsen would like to accommodate people who offer to be in our sample, but doing so would violate basic laws of sampling practice. The sample could immediately become biased because those who ask to join may be systematically different from the population at large.

Instead, Nielsen draws a sample in a way that offers every U.S. television household an equal chance of being selected. Once the homes are selected and agree to participate, Nielsen Media protects their privacy by keeping their identities confidential.

Excerpted from "What TV Ratings Really Mean"
Copyright 1997 Nielsen Media Research