表格中列之间的间距更大

Question

我希望 AIC 列和 BIC 列之间留出更多间距，以便 BIC 列中的减号不会与 AIC 列中的数字重叠。我该如何解决这个问题？

\documentclass[11pt,a4paper]{article}
\usepackage{amssymb, amsmath, bm}
\usepackage[flushleft]{threeparttable}
\usepackage{float, booktabs, makecell, caption, tabularx}
\usepackage{siunitx}

\begin{document}

\begin{table}[htb!]
\caption{\textbf{Log-likelihood and information criteria of the Nelson-Siegel models}}
\label{table:loglikelihood_aic}
\footnotesize
\begin{threeparttable}
\renewcommand{\TPTminimum}{\linewidth}
\makebox[\linewidth]{%
\begin{tabular}{@{} l *{8}{S[table-format=1.1]} @{}}
\toprule
\hline 
& {Log-likelihood}   & {\# parameters} & & {AIC} & & {BIC} &  {LR-stat. (DNS)} & {LR-stat. (MS-DNS)} \\ 
\midrule
DNS      & 4239.95  & 18 & & -8443.91  & & -8372.24 &          &          \\
MS-DNS   & 4930.78  & 20 & & -9821.55  & & -9741.93 & 1381.66  &          \\
MS-DRA   & 5067.14  & 38 & & -10058.28 & & -9906.98 & \times   & 272.72   \\
MS-TVTP  & 5012.43  & 26 & & -9972.85  & & -9869.34 & \times   & 163.30   \\
MS-DNS-X & 5148.40  & 44 & & -10208.80  & & -10033.62 & \times   & \times   \\
\bottomrule
\end{tabular}
}
\smallskip

\begin{tablenotes}[flushleft]\footnotesize\smallskip
 \item Note: This table presents log-likelihood values, the number of parameters, the Akaike information criterion (AIC) and Bayesian information criterion (BIC) for the DNS model and its regime-switching (macro) extensions. In the fifth and sixth column, I present likelihood-ratio test statistics (\textit{LR-stat.}) of the regime-switching models against the DNS model, and of the regime-switching macro models against the MS-DNS model, respectively. \par 
\end{tablenotes}
\end{threeparttable}
\end{table}

\end{document}

先感谢您。

Answer 1

您可以轻松地做到这一点，更改列的规格S，并makecell在必要时使用多行列标题：

\documentclass[11pt,a4paper]{article}
\usepackage{amssymb, amsmath, bm}
\usepackage[flushleft]{threeparttable}
\usepackage{float, booktabs, makecell, caption, tabularx}
\usepackage{siunitx}

\begin{document}

\begin{table}[htb!]
\setlength{\tabcolsep}{5pt}
\caption{\textbf{Log-likelihood and information criteria of the Nelson-Siegel models}}
\label{table:loglikelihood_aic}
\footnotesize
\sisetup{table-format=-5.2, table-number-alignment=center}
\begin{threeparttable}
\centering
\begin{tabular}{@{} l S[table-format=4.2]c*{2}{S}S[table-format=4.2]S[table-format=3.2] @{}}%
\toprule
\midrule[0.4pt]
& {\makecell{Log-\\likelihood}} & {\makecell{n\textsuperscript{o}\,of \\parameters}} & {AIC} & {BIC} & {\makecell{LR-stat.\\ (DNS)}} & {\makecell{LR-stat.\\ (MS-DNS)}} \\
\midrule
DNS & 4239.95 & 18 & -8443.91 & -8372.24 & \\
MS-DNS & 4930.78 & 20 & -9821.55 & -9741.93 & 1381.66 & \\
MS-DRA & 5067.14 & 38 & -10058.28 & -9906.98 & $ \times $ & 272.72 \\
MS-TVTP & 5012.43 & 26 & -9972.85 & -9869.34 & $ \times $ & 163.30 \\
MS-DNS-X & 5148.40 & 44 & -10208.80 & -10033.62 & $ \times $ & $ \times $ \\
\bottomrule
\end{tabular}
\smallskip
\begin{tablenotes}[flushleft]\footnotesize\smallskip
 \item Note: This table presents log-likelihood values, the number of parameters, the Akaike information criterion (AIC) and Bayesian information criterion (BIC) for the DNS model and its regime-switching (macro) extensions. In the fifth and sixth column, I present likelihood-ratio test statistics (\textit{LR-stat.}) of the regime-switching models against the DNS model, and of the regime-switching macro models against the MS-DNS model, respectively. \par
\end{tablenotes}
\end{threeparttable}
\end{table}

\end{document}