Is there any rules regarding the number of observations required to run a cross section regression? Any number of observation-variable rules of thumb? I have 16 independent variables with 45 observations.
Dear Mohammed,
Refer to the following one.
Item parceling can be applied for small samples to achieve a better variable-to-sample size ratio (Bagozzi & Edwards, 1998). However, opinions vary regarding a good variable-to-sample size ratio: the 3–6 range (Cattell, 1978), a minimum of 5 (Gorsuch, 1983), at least 10 (Nunnally, 1978), and 20 (Hair, Anderson, Tatham, & Black, 1995; Hogarty, Hines, Kromrey, Ferron, & Mumford, 2005). In our data, the variable-to-sample size ratio is 6.2 (52: 322), which is relatively low; thus, item parceling can be applied to achieve a better variable-to-sample size ratio.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression