Philip A Viton's Pavtest

Philip A Viton's very helpful Hevea: the Win32 Port includes a small test file pavtest.tex. Below are the results of converting pavtest.tex with H^EV^EA, T_TH, TeX4ht, L^ATEX2HTML using T_EX Converter.

No special style files or settings (which may improve the results) were used, and the results have not been enhanced in any way. I haven't altered the text so all conversions refer to H^EV^EA whether they use it or not.

You may also like to compare these results with IBM's techexplorer Hypermedia Browser on pavtest.tex.
Here is a screenshot of techexplorer's output in Internet Explorer 5.5

Previous example

Home to T_EX Converter

H^EV^EA

A HEVEA Example

Philip A. Viton

Abstract: We demonstrate some easy LaTeX-to-HTML conversion using Hevea

1 Introduction

Let an individual i have a choice set of size K, and let i's choices be discrete. The conditional indirect utility that i achieves if kÎ K is selected is

v_ik=X_ikb +e _ik

where X_ik is an n-vector of attributes of choice k as perceived by individual i, b is an n-element weighting vector, and e _ik is a random variable. The individual chooses that alternative m whose conditional indirect utility is greatest (ie, maximizes utility). If the e _ik are independent, identically distributed Type-1-Extreme-Value variates, then we have the alternative-m choice probability P_im given by

P_im

=

Pr [v_im>v_ik,," k¹ m]

=

æ
ç
ç
ç
ç
ç
è

e

X_imb

å

k

e

X_ikb

ö
÷
÷
÷
÷
÷
ø

the logit model.

This document was translated from L^AT_EX by H^EV^EA.

T_TH

Philip A. Viton

A HEVEA Example

Abstract

We demonstrate some easy LaTeX-to-HTML conversion using Hevea

1 Introduction

Let an individual i have a choice set of size K, and let i's choices be discrete. The conditional indirect utility that i achieves if k Î K is selected is

v_ik = X_ikb+e_ik

where X_ik is an n-vector of attributes of choice k as perceived by individual i, b is an n-element weighting vector, and e_ik is a random variable. The individual chooses that alternative m whose conditional indirect utility is greatest (ie, maximizes utility). If the e_ik are independent, identically distributed Type-1-Extreme-Value variates, then we have the alternative-m choice probability P_im given by

P_im

=

Pr

[v_im > v_ik,,"k ¹ m]

=

æ
ç
ç
ç
è

e^X_imb

å
k

e^X_ikb

ö
÷
÷
÷
ø

the logit model.

File translated from T_EX by T_TH, version 2.25.
On 24 Dec 1999, 10:47.

TeX4ht

A HEVEA Example

Philip A. Viton

March 25, 2000

Abstract

We demonstrate some easy LaTeX-to-HTML conversion using Hevea

1 Introduction

Let an individual i have a choice set of size K, and let i's choices be discrete. The conditional indirect utility that i achieves if k K is selected is

vik = Xikb + eik

where X_ik is an n-vector of attributes of choice k as perceived by individual i, is an n-element weighting vector, and _ik is a random variable. The individual chooses that alternative m whose conditional indirect utility is greatest (ie, maximizes utility). If the _ik are independent, identically distributed Type-1-Extreme-Value variates, then we have the alternative-m choice probability P_im given by

Pim = P(r[vim > vik),, A k /= m]
eXimb
= sum -eXikb-
k

the logit model.

L^ATEX2HTML

A HEVEA Example

Philip A. Viton

Abstract:

We demonstrate some easy LaTeX-to-HTML conversion using Hevea

Introduction

Let an individual i have a choice set of size K, and let i's choices be discrete. The conditional indirect utility that i achieves if k $\in$ K is selected is

v_ik = X_ik $\displaystyle \beta$ + $\displaystyle \epsilon_{ik}^{}$

where X_ik is an n-vector of attributes of choice k as perceived by individual i, $\beta$ is an n-element weighting vector, and $\epsilon_{ik}^{}$ is a random variable. The individual chooses that alternative m whose conditional indirect utility is greatest (ie, maximizes utility). If the $\epsilon_{ik}^{}$ are independent, identically distributed Type-1-Extreme-Value variates, then we have the alternative-m choice probability P_im given by

P_im

=

Pr[v_im > v_ik,, $\displaystyle \forall$ k $\displaystyle \neq$ m]

=

$\displaystyle \left(\vphantom{ \frac{e^{\mathbf{X}_{im}\beta }}{\sum_{k}e^{\mathbf{X}_{ik}\beta }}%% }\right.$ $\displaystyle {\frac{e^{\mathbf{X}_{im}\beta }}{\sum_{k}e^{\mathbf{X}_{ik}\beta }}}$ $\displaystyle \left.\vphantom{ \frac{e^{\mathbf{X}_{im}\beta }}{\sum_{k}e^{\mathbf{X}_{ik}\beta }}%% }\right)$

the logit model.

14 March 2000

Philip A Viton's Pavtest

H^EV^EA

A `HEVEA` Example

Philip A. Viton

1 Introduction

T_TH

Philip A. Viton

A `HEVEA` Example

Abstract

1 Introduction

TeX4ht

A HEVEA Example

1 Introduction

L^ATEX2`HTML`

A `HEVEA` Example

Abstract:

Introduction

Philip A Viton's Pavtest

HEVEA

A HEVEA Example

Philip A. Viton

1 Introduction

TTH

Philip A. Viton

A HEVEA Example

Abstract

1 Introduction

TeX4ht

A HEVEA Example

1 Introduction

LATEX2HTML

A HEVEA Example

Abstract:

Introduction

H^EV^EA

A `HEVEA` Example

T_TH

A `HEVEA` Example

L^ATEX2`HTML`

A `HEVEA` Example