%0 Journal Article
%T Dealing with Model Mis-Specification in the Analysis of Morale in Old Age
%A Said Shahtahmasebi
%J Open Journal of Social Sciences
%P 64-71
%@ 2327-5960
%D 2014
%I Scientific Research Publishing
%R 10.4236/jss.2014.21008
%X <p style=\"text-align:justify;\">
	<span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">A major challenge for</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">analysis of data from
observational and survey studies is dealing with model mi<span>s-specification. A common reason for model
mis-specification is the violation of the independence assumption.</span></span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">Model mis-specification is frequently due to the
inclusion of variables</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">that
are correlated with the error terms (serial correlation) or due to variables
omitted from the study. The appli</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"></span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">cation
of standard regression models to such data could lead to over inflated results,</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><i><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">i.e.</span></i><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> erroneous results, and misleading conclusions.
Longitudinally designed studies make substantial improve</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"></span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">ments and provide an</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">additional handle to control omitted variables.
However, even with longitu</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"></span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">dinal data,</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"> </span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\">model mis-specification could occur because of the
nature of observations, <i>i.e.</i> surveys
often include objectively as well as subjectively measured variables.
Subjective variables are respon</span><span style=\"font-size:10.0pt;line-height:97%;font-family:;\" \"=\"\"></span><span
%K Morale
%K Old Age
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=41716