Edgar F. Borgatta

Level of Measurement

The distinctions between nominal, ordinal, interval, and ratio measurement were popularized by S. S. Stevens. Unfortunately, positions taken by Stevens have often been disseminated without criticism. One problem is the common assumption that ordinal statistics are the best statistics to use for presumed noninterval continuous social variables, when, in fact, they use addition, subtraction, and division, which make the measurements interval by definition. Additionally, the relationship of the normal distribution to interval measurement is commonly misunderstood, the latter existing by definition if a normal distribution exists. Concern with levels of measurements may mislead persons into attending to issues other than maximizing (utility, given) the particular limits of the state of the measurement art in the social sciences.

Some Limitations On Generalizability From Social Psychological Experiments

The experimental model has severe limitations that often are ignored by experimenters. The limitations are likely to account for the low level of external validity of experiments. Placing the model in the context of requirements for measurement emphasizes the limitations and suggests alternatives for improvements in the future.

Aggregate Data Analysis

n the social and psychological sciences, in contrast to the biological and physical sciences, being latecomers has, at times, created invidious comparisons. Because of lack of money, which may be the same as lack of credibility, the resources to do research in the social sciences have not been available, and so alternatives to direct study have been sought. Looking for other sources of available data, for those who can not collect their own, is the common alternative, and to find data in the form required is more than can be expected. Availability of aggregated data based on censuses and registrations, thus attracted many users over the history of the social sciences. The demographers are among the more prominently visible empirical researchers of the past. However, interest in topics such as suicide and anomie,

Correlates of Age The NORC General Social Survey

The NORC General Social Survey represents the central social indicator data collection device that is not an enumeration or registration procedure. It has serious limitations in design, but offers useful data on social and psychological correlates of age. A framework for looking at these correlates is noted and an abbreviated summary of the correlates is presented.

Data Analysis in Factorial Ecology

The methodology of factorial ecology is examined with regard to its main objective, to discover stable patterns of covariation for census tract variables across cities and over time.

Special Issue on Measurement

some practical applications. The growth in interest in sociological measurement is relatively recent. While textbooks in sociological methodology have long argued for the assessment of reliability and validity, until recently it has been rare to see any data on reliability and validity reported in research papers. Even a casual inspection of a volume such as Robinson and Shaver’s (1973) Measures of Social Psychological Attitudes underscores this point. Although scores of measures are reported, the information available on their reliability and validity is sparse. And even when reliability coefficients have been available, it is again the case that, until recently, it was almost unheard of to correct a parameter estimate for

On Determining Critical Health Problem Areas

Factor analytic study of small area units of a city may be used as an approach to identification ofparticular indices, such as that of Critical health problem areas. Problems with such indices have been discussed in the literature. A reanalysis of a data set is presented to illustrate some problems and to suggest that use of a single index may be questionable.

Correlates of Sex among the Aged The NORC General Social Survey

The NORC General Social Survey provides a sufficient sample base to examine the correlates of sex among the aged. The data for the older groups are put in perspective by comparison with data for younger groups, and the analysis is reported in abbreviated form. A model for controlling for important background and experience variables is applied in a standard way.