Nielsen Media Research has been rating television programs for nearly 50 years. Nielsen uses several sampling procedures, but its main one is to track the viewing pattern of 5000 households. These contain over 13,000 people and are chosen from a cross section of the overall population. The households represent various locations, ethnic groups, and income brackets. The data gathered from the Nielsen sample of 5000 households are used to draw inferences about the populations of all households in the United States.
1. Rating Points. Each rating point represents 1,084,000 households, or 1 % of the households in United States. Does a program with ranking of 8.4 have twice the number of households as a program with a ranking of 4.2? Explain your reasoning.
2. Sampling Percent. What percentage of the total number of US households is used in the Nielsen sample?
3. Nominal Level of Measurement. Which columns in the table contain data at the nominal level?
4. Ordinal Level of Measurement. Which columns in the table contain data at the ordinal level ? Describe two ways in which data can be ordered.
5. Interval Level of Measurement. Which columns in the table contain data at the interval level ? How can these data be ordered? What is the unit of measuremnt for the difference of two entries in the data set?
6. Ratio Level of Measurement. Which three columns in the table contain data at the ratio level ?
7. Share. The column listed as "Share" gives the percentage of televisions in use at a given time. Does the Nielsen rating rank shows by rating or by share? Explain your reasoning.
8. Inferences. What decisions (inferencec) can be made on the basis of the Nielsen ratings?
The solution uses the rating of television shows in the United States by Neilsen Media Research to illustrate levels of measurement (nominal, ordinal, interval and ratio scales ).