Home

Menu

Loading wiki pages...

View
Wiki Version:
<p>We checked the main results of the reported analyses using data multiply imputed by predictive mean matching with <em>mice</em> R package (van Buuren & Groothuis-Oudshoorn, 2011). We imputed the answers to the two mindset questions for participants who did not answer one of them or both. The data were imputed 49 times using data on participants’ preferred university and faculty, age, sex, geographic region, GAP test results, the number of GAP test administration the participants already attended and the number they signed up for. For estimation of reported linear regression coefficients, we used <em>pool</em> function provided in <em>mice</em> package and for correlation, we report results using imputed data set that resulted in the median correlation coefficient. </p> <p>Using the imputed data, the average of the two questions used for measuring mindset correlated slightly negatively with the result in the GAP test, r(5987) = -.02, 95% CI = [-.05, .00], p = .09, meaning that participants with more fixed mindset had slightly better results. An analysis conducted using only participants who took part in the test for the first time showed similar results, r(3397) = -.01, 95% CI = [-.04, .02], p = .58. The analysis of the two items separately shows that the item “I can learn new things, but I can’t really change my basic intelligence.” had no relationship to the result in the test, r(5987) = .00, 95% CI = [-.02, .03], p = .82, and the item “I have a certain amount of intelligence and I really can’t do much to change it.” had a significantly negative, but very weak, relationship to the result, r(5987) = -.04, 95% CI = [-.07, -.02], p &lt; .001. A polynomial regression using a centered mindset score as a predictor showed that the GAP test results were significantly associated with both mindset score, t(4517.8) = -2.33, p = .02, b = -0.021, 95% CI = [-0.039, -0.003], and squared mindset score, t(4466.6) = 7.14, p &lt; .001, b = 0.039, 95% CI = [0.029, 0.050]. Mindset had also no association with the number of GAP tests participants had already taken, r(5987) = -.01, 95% CI = [-.04, .01], p = .26, and with the total number of administrations participants signed up for, r(5987) = -.00, 95% CI = [-.03, .02], p = .78. We also estimated the association between mindset and the probability of participating in later administrations of the GAP test.</p>
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
Accept
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.
Accept
×

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.