defines a list with optional parameters in gam quantlets. The list is either created or new options are appended to an existing list. Note that gamopt does accept any values for the parameters without validation.
generates a time series e_t=u_t*s_t, where u_t is standard normal distributed and the variances s^2_t follow the GARCH process s^2_t = a_0 + a(B)e^2_t + b(B)s^2_t Here, B denotes the backshift (or lag) operator. You have to deliver the coefficient vectors a and b and the length T of t
generates an autoregressive moving average process (ARMA) in deviations from the mean form y_t = a(B)y_t + eps_t + b(B)eps_t B denotes the backshift (or lag) operator. You have to deliver the AR coefficients vector a, the MA coefficients vector b and the (T x 1) white noise series eps. Th
generates the bilinear process x that has the following form x_t = phi(B)x_t + e_t + theta(B)e_t + sum sum c_(i,j)x_(t-i)e_(t-j) B denotes the backshift (or lag) operator. The AR polynom phi(B) has p coefficients and the MA polynom theta(B) has q coefficients. The first sum of the double sum goes
generates the amplitude-dependent exponential AR (EXPAR) process x that has the following form x_t = a(B)x_t + exp{-delta x^2_(t-thrlag)}b(B)x_t + e_t B is the backshift (or lag) operator. The coefficient delta must be positive. The lag polynoms a(B) and b(B) must have the same order. e_t is a se
genmultlo generates data according to a multinomial logit model with P( Y = j | Xa , Xi) proportional to exp( Xa * ba + Xi * bi[j] ). Here, Xi denotes the part of the explanatory variables which merely depends on the individuals, Xa covers variables which may vary with the alternatives j. Either pa
generates the threshold AR (TAR) process x that has the following form x_t = sum I{x_(t-thrlag) in (k_(i-1),k_i]}[phi_i(B)x_t]+e_t The sum goes from i=1 to nr (the number of threshold regions). I{} is an indicator function that takes the value 1 if the specified lagged value of x lies in the inte
gintestpl fits an additive generalized partially linear model E[y|x,t] = G(x*b + m(t)). This quantlet offers a convenient interface for GPLM estimation. A preparation of data is performed (inclusive sorting).
Calculates a filtered time series for a state space model (uni- or multivariate) with time variable system matrices using the Kalman filter. Furthermore, gkalfilter gives the value of the log likelihood function.
Calculates covariance matrices for the smoothed series of a state space model (uni- or multivariate) with one lag. The quantlet gkallag needs a pre-run of gkalfilter. The state space model has the form (for the notation, see Harvey 1989): State equation alpha_t = c_t + T_t alpha_t-1 + e^s_t M
Calculates the innovations v_t and the standardized v^s_t residuals for a state space form that is estimated with the Kalman filter. As input, the output from the Kalman filter is needed. See the help to gkalfilter or the tutorial for a thorough discussion of the model.
calculates a smoothed time series for a state space model (uni- or multivariate) using the Kalman smoother. The quantlet gkalsmoother needs a pre-run of gkalfilter.
glmbackward performs a backward model selection by searching the best of all subset models w.r.t. the AIC or BIC criterion. Optionally, a number of columns can be given, which are always included in the submodels.
fits a generalized linear model E[y|x] = G(x*b). This is the core routine for GLM estimation. It assumes that all input variables are given in the right manner. No preparation of data is performed. A more convenient way to estimate a GLM is to call the function glmest.
glmest fits a generalized linear model E[y|x] = G(x*b). This routine offers a convenient interface for GLM estimation. A check of the data is performed.
glmforward performs a forward model selection by searching the best of all subset models w.r.t. the AIC or BIC criterion. Optionally, a number of columns can be given, which are always included in the submodels.
glmmultlo fits a multinomial/conditional logit model where the response Y is multinomial distributed. This means, P( Y = j | Xa , Xi) is proportional to exp( Xa * ba + Xi * bi[j] ). Here, Xi denotes that part of the explanatory variables which merely depends on the individuals and Xa covers va
glmopt defines a list with optional parameters in glm functions. The list is either created or new options are appended to an existing list. Note that glmopt does accept _any_ values for the parameters without validity.
glmplot creates a display and plots for a one-dimensional explanatory variable: the distribution, a scatterplot of the marginal influence versus the response and a scatterplot of the variabel versus the response.
glmselect performs a model selection by searching the best of all subset models w.r.t. the AIC or BIC criterion. Optionally a number of columns can be given, which are always included in the submodels.
Bootstrap test for comparing GLM vs. GPLM. The hypothesis E[y|x,t] = G(x*b + t*g + c) is tested against the alternative E[y|x,t] = G(x*b + m(t)). This routine offers a convenient interface for GPLM estimation and testing. A preparation of data is performed (inclusive sorting).
gplmcore fits a generalized partially linear model E(y|x,t) = G(x*b + m(t)). This is the core routine for GPLM estimation. It assumes that all input variables are given in the right manner. No preparation of data is performed. A more convenient way to estimate a GPLM is to call the function gplmes
gplmest fits a generalized partially linear model E[y|x,t] = G(x*b + m(t)). This routine offers a convenient interface for GPLM estimation. A preparation of data is performed (inclusive sorting).
gplminit checks the validity of input and performs the initial calculations for an GPLM fit (inclusive sorting). The output is ready to be used with gplmcore.
gplmopt defines a list with optional parameters in gplm functions. The list is either created or new options are appended to an existing list. Note that gplmopt does accept _any_ values for the parameters without validity.
Generates a boxplot with mean line and median line. Outliers outside the interval [Q_25-3*IQR, Q_75+3*IQR] will be plotted as crosses, outliers outside the interval [Q_25-1.5*IQR, Q_75+1.5*IQR] will be plotted as circles.
generates a boxplot of classified data with mean line and median line. Outliers outside the interval [Q_25-3*IQR, Q_75+3*IQR] will be plotted as crosses, outliers ouside the interval [Q_25-1.5*IQR, Q_75+1.5*IQR] will be plotted as circles.
Generates a boxplot with the mean line. The box borders are plus/minus one standard deviation of the mean line and the whiskers are plus/minus two standard deviations.
generates a boxplot of classified data with the mean line. The box borders are plus/minus one standard deviation from the mean line and the whiskers plus/minus two standard deviations.
Generates a boxplot with the median line. The box borders are the percentiles which are equivalent to the mean plus/minus one standard deviation in the normal case (16% and 84% percentile) and the whiskers are equivalent to to the mean plus/minus two standard deviations in the normal case (2.5% and
generates a boxplot of classified data with the median line. The box borders are the percentiles which are equivalent to the mean plus/minus one standard deviation in the normal case (16% and 84% percentile) and the whiskers are equivalent to the mean plus/minus two standard deviations in the norma
A coxcomb graph is a special pie chart. Its frequency is proportional to the area of the corresponding segment and the angles of the segments are all equal. Consequently, the frequency is proportional to the square of the radius of the segment.
This command generates a grid with origin x and stepwidth h with respect to each dimension, n indicating the number of gridpoints in the respective dimension.