Your PDF has successfully downloaded.

You may be interested in finding more content on these topics:


You are not currently logged in.

Access JSTOR through your library or other institution:


Log in through your institution.

Journal Article

Science and Sociology

Hornell Hart
American Journal of Sociology
Vol. 27, No. 3 (Nov., 1921), pp. 364-383
Stable URL:
Page Count: 20
Were these topics helpful?
See something inaccurate? Let us know!

Select the topics that are inaccurate.

  • Download PDF
  • Add to My Lists
  • Cite this Item
We're having trouble loading this content. Download PDF instead.


The scientific achievements of sociology have been disappointing. Sociology is properly a utilitarian science. The five methods of sociology.-In it five inductive methods of seeking truth may be considered. The common-sense method, consisting in generalizing from data which chance to come to hand, has been the most prominent. The historical method uses documents as its data. The museum or census method, having classification as its goal, has been used extensively in social surveys and government investigations. The laboratory or experimental method is restricted in sociological research by the length of time required for social experiments, by the number and complexity of the variables involved, and by the difficulty of controlling human variables. Superiority of the statistical method.-The statistical method consists in applying rigidly objective methods, aided by mathematics, to the interpretation of the social phenomena which spontaneously occur. In the form of simple comparisons the method has been widely used, but its value has been limited by the lack of comprehension of the method even in its crude form, and by the failure of crude comparisons to answer adequately the questions involved. Partial correlation and regression meet the needs of social research by furnishing predictions of stated variables in terms of other measured of classified variables, and by indicating the importance of the variables not considered. The development of reliable indices for certain social variables is prerequiste to the solution of fundamental sociological problems by statistical methods.