Skip to main content

Table 10 Probit results using option implied volatility index -(VIX)

From: Can news-based economic sentiment predict bubbles in precious metal markets?

 

Dependent variable: Bubble

Gold

Silver

Palladium

Platinum

\(VIX_{t - 1}\)

0.0879***

− 0.0022

0.0315

0.0481***

(0.0000)

(0.7500)

(0.1270)

(0.0040)

\(Inflation_{t - 1}\)

2.0117**

0.6214*

1.9999***

1.7865***

(0.0340)

(0.0733)

(0.0010)

(0.0000)

\(US{\text{DI}}_{t - 1}\)

− 1.3535***

− 1.0177***

− 3.1302***

− 2.8887***

(0.0000)

(0.0000)

(0.0010)

(0.0000)

\({\text{EFR}}_{t - 1}\)

− 0.1018**

− 0.2849**

− 0.2213***

− 0.5029***

(0.0199)

(0.0380)

(0.0000)

(0.0000)

\(T - Spread_{t - 1}\)

− 0.4770**

− 0.6280*

− 0.1583

− 0.3606**

(0.0137)

(0.0600)

(0.0520) ***

(0.0375)

\({\text{GEA}}_{t - 1}\)

0.0042***

0.0101**

0.0081**

0.0097***

(0.0010)

(0.0281)

(0.0150)

(0.0010)

\(Constant\)

0.3928***

0.2285***

0.3282***

− 0.1095***

(0.0000)

(0.0020)

(0.0067)

(0.0000)

\(Observations\)

360

360

360

360

McFadden's pseud-R2

0.6170

0.5523

0.3227

0.5950

Log-likelihood

− 95.451

− 79.9894

− 172.0924

− 83.1346

Hosmer–Lemeshow test

3.060

3.780

7.920*

5.770

(0.3831)

(0.4361)

(0.0832)

(0.1450)

  1. This table reports the results using the option implied volatility index-(VIX). The dependent variable is a binary that equals 1 (bubble dates) and 0 (none-bubble dates) identified by the GSADF procedure. The Hosmer–Lemeshow test is a statistical test for goodness of fit for probit regressions, following the \(\chi^{2}\) distribution. A large \(\chi^{2}\) value (with small p value \(< 0.05\)) indicates poor fit regression model. Robust standard errors are given in parentheses. p values are given in brackets.*, **, and *** indicate significance at 10%, 5%, and 1% levels, respectively.