Page 57 - Annual Report 2016_17

Year No. of Downloads No. of Publications
2004 3251103 4464
2005 5938928 5071

2006 5188078 5879
2007 8116670 6693
2008 9389190 7646
2009 10555937 8218
2010 12567617 8819
2011 11407486 9434
2012 12876334 10404

2013 15685592 12062
2014 17370409 13970
2015 16148191 16286

Table 16: No of Full-Text Downloads and No. of Publications of
Member Institutions of INDEST AICTE Consortium

Figure 26: Correlation between no of Full-Text Downloads and Publications of
Member Institutions of INDEST AICTE Consortium

The correlations between number of publications against the number of articles downloads by the
member institutions over a period of 12 years, i.e. 2004–2015 has been calculated for both the consortia.

To get a measure of the statistical correlation between the two variables, without assuming any
parametric relation between them, Spearman’s rank-order correlation coefficient and Pearson’s linear
correlation (r) has been measured as data points shown in Figure 25 and Figure 26 given above. The
Spearman’s rank-order correlation provides a non-parametric measure of the positive or negative

correlation between the variables and would be zero if there is no association between the number of
publications and the number of downloads. Pearson Correlation Coefficient is a measure of the linear
correlation between two variables. It has a value between +1 and “1, where 1 is total positive linear

- 48 -