Search

Flipped classroom teaching means, in short, to change/flip where students and teachers dothings. Instead of students (passively) listening to a teacher’s lecture in the classroom andthen going home to solve problems on their own, the idea is that students first watch video lectures at home and then come to the classroom to (actively) solve problems together with other students and the teacher. As part of a pedagogical project, we have used special learning management system (LMS)called “Scalable Learning”, which facilitates teaching with flipped classroom techniques. The Scalable Learning LMS allows the teacher to make the video lectures interactive by adding quizzes and surveys to the videos (as is very common in Massive Open Online Courses (MOOCs)), thereby helping the students to be more active while watching the videos. Moreover, there are different tools implemented in the LMS so that students e.g., can ask questions in direct connection to the videos. The student supplied questions and their answers to the quizzes can then, together with other data from the LMS, be used by theteacher to prepare classroom activities customized to the students’ needs. We present our experiences of teaching a course in statistics using this LMS; there are both pros and cons from a teachers’ point of view. Also, we present the students’ opinions with the LMS and with the flipped classroom teaching that they were exposed to during the course. Most of them were very satisfied with the concept but they also provided us with several interesting ideas on how to improve the course.

For a linear regression model subject to left-truncation and right-censoring where the truncation and censoring points are known constants (or always observed if random), Karlsson and Laitila (Stat Probab Lett 78:2567–2571,2008) proposed a semiparametric estimator which deals with left-truncation by trimming and right-censoring by ‘winsorizing’. The estimator was motivated by a zero moment condition where a transformed error term appears with trimmed and winsorized tails. This paper takes the semiparametric estimator further by deriving the asymptotic distribution that was not shown in Karlsson and Laitila (Stat Probab Lett 78:2567–2571,2008) and discusses its implementation aspects in practice, albeit brief.

A finite mixture of Tobit models is suggested for estimation of regression models with a censored response variable. A mixture of models is not primarily adapted due to a true component structure in the population; the flexibility of the mixture is suggested as a way of avoiding non-robust parametrically specified models. The new estimator has several interesting features. One is its potential to yield valid estimates in cases with a high degree of censoring. The estimator is in a Monte Carlo simulation compared with earlier suggestions of estimators based on semi-parametric censored regression models. Simulation results are partly in favor of the proposed estimator and indicate potentials for further improvements.

Problems with truncated data occur in many areas, complicating estimation and inference. Regarding linear regression models, the ordinary least squares estimator is inconsistent and biased for these types of data and is therefore unsuitable for use. Alternative estimators, designed for the estimation of truncated regression models, have been developed. This paper presents the R package truncSP. The package contains functions for the estimation of semi-parametric truncated linear regression models using three different estimators: the symmetrically trimmed least squares, quadratic mode, and left truncated estimators, all of which have been shown to have good asymptotic and finite sample properties. The package also provides functions for the analysis of the estimated models. Data from the environmental sciences are used to illustrate the functions in the package.

An R-package with functions for estimation of semi-parametric linear regression models with truncated response variables (fixed truncation point). Estimation using the Symmetrically Trimmed Least Squares (STLS) estimator (Powell 1986), Quadratic Mode (QME) estimator (Lee 1993) and Left Truncated (LT) estimator (Karlsson 2006).

An estimator is proposed for semiparametric linear regression models with left truncated and right censored dependent variables. The estimator is derived from a moment condition following the principles of Newey [Newey, W.K., 2001. Conditional moment restrictions in censored and truncated regression models. Econometric Theory 17, 863–888] on conditional moment conditions. Consistency of the estimator is shown and simulation is used for illustration of the small sample properties., Ändrat till publicerad artikel 21/8-09

Estimators of parameters in semi-parametric left truncated and right censored regression models are proposed. In contrast to the majority of existing estimators, the proposed estimators do not require the error term of the regression model to have a symmetric distribution. In addition the estimators use asymmetric “trimming” of observations. Consistency and asymptotic normality of the estimators are shown. Finite sample properties are considered in a small simulation study. For the left truncated case, an empirical application illustrates the usefulness of the estimator., Ändrat till published 21/8-09

Bias and MSE of the QME are studied by means of simulation. A bootstrap estimator of the QME covariance matrix is also included in the study. The simulation is based on travel distances reported in the Swedish Travel Habit Survey. The results are in accordance with the asymptotic properties of the QME. For example, the QME is better than other suggested estimators under asymmetric distributions of the error term. The results also suggest that the bootstrap technique is potentially useful for estimation of the QME covariance matrix.